change error handler behavior and fix error when a model isn't found

.dockerignore

@@ -1,9 +1,7 @@
+build
+llama/build
+.venv
 .vscode
 ollama
 app
-dist
-scripts
-llm/llama.cpp/ggml
-llm/llama.cpp/gguf
-.env
-.cache
+web

.gitignore

@@ -2,8 +2,5 @@
 .vscode
 .env
 .venv
-.swp
 dist
 ollama
-ggml-metal.metal
-.cache

.gitmodules

@@ -1,10 +0,0 @@
-[submodule "llm/llama.cpp/ggml"]
-    path = llm/llama.cpp/ggml
-    url = https://github.com/ggerganov/llama.cpp.git
-    ignore = dirty
-    shallow = true
-[submodule "llm/llama.cpp/gguf"]
-    path = llm/llama.cpp/gguf
-    url = https://github.com/ggerganov/llama.cpp.git
-    ignore = dirty
-    shallow = true

Dockerfile

@@ -1,23 +1,15 @@
-FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
-
-ARG TARGETARCH
-ARG GOFLAGS="'-ldflags=-w -s'"
-
+FROM golang:1.20
 WORKDIR /go/src/github.com/jmorganca/ollama
-RUN apt-get update && apt-get install -y git build-essential cmake
-ADD https://dl.google.com/go/go1.21.3.linux-$TARGETARCH.tar.gz /tmp/go1.21.3.tar.gz
-RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.3.tar.gz
-
 COPY . .
-ENV GOARCH=$TARGETARCH
-ENV GOFLAGS=$GOFLAGS
-RUN /usr/local/go/bin/go generate ./... \
-    && /usr/local/go/bin/go build .
+RUN CGO_ENABLED=1 go build -ldflags '-linkmode external -extldflags "-static"' .
 
-FROM ubuntu:22.04
-RUN apt-get update && apt-get install -y ca-certificates
+FROM alpine
 COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
 EXPOSE 11434
-ENV OLLAMA_HOST 0.0.0.0
+ARG USER=ollama
+ARG GROUP=ollama
+RUN addgroup -g 1000 $GROUP && adduser -u 1000 -DG $GROUP $USER
+USER $USER:$GROUP
 ENTRYPOINT ["/bin/ollama"]
+ENV OLLAMA_HOST 0.0.0.0
 CMD ["serve"]

Dockerfile.build

@@ -1,31 +0,0 @@
-# centos7 amd64 dependencies
-FROM --platform=linux/amd64 nvidia/cuda:11.3.1-devel-centos7 AS base-amd64
-RUN yum install -y https://repo.ius.io/ius-release-el7.rpm centos-release-scl && \
-    yum update -y && \
-    yum install -y devtoolset-10-gcc devtoolset-10-gcc-c++ git236 wget
-RUN wget "https://github.com/Kitware/CMake/releases/download/v3.27.6/cmake-3.27.6-linux-x86_64.sh" -O cmake-installer.sh && chmod +x cmake-installer.sh && ./cmake-installer.sh --skip-license --prefix=/usr/local
-ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
-
-# centos8 arm64 dependencies
-FROM --platform=linux/arm64 nvidia/cuda-arm64:11.3.1-devel-centos8 AS base-arm64
-RUN sed -i -e 's/mirrorlist/#mirrorlist/g' -e 's|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g' /etc/yum.repos.d/CentOS-*
-RUN yum install -y git cmake
-
-FROM base-${TARGETARCH}
-ARG TARGETARCH
-ARG GOFLAGS="'-ldflags -w -s'"
-
-# install go
-ADD https://dl.google.com/go/go1.21.3.linux-$TARGETARCH.tar.gz /tmp/go1.21.3.tar.gz
-RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.3.tar.gz
-
-# build the final binary
-WORKDIR /go/src/github.com/jmorganca/ollama
-COPY . .
-
-ENV GOOS=linux
-ENV GOARCH=$TARGETARCH
-ENV GOFLAGS=$GOFLAGS
-
-RUN /usr/local/go/bin/go generate ./... && \
-    /usr/local/go/bin/go build .

README.md

@@ -9,31 +9,19 @@
 
 [![Discord](https://dcbadge.vercel.app/api/server/ollama?style=flat&compact=true)](https://discord.gg/ollama)
 
-Get up and running with large language models locally.
+> Note: Ollama is in early preview. Please report any issues you find.
 
-### macOS
+Run, create, and share large language models (LLMs).
 
-[Download](https://ollama.ai/download/Ollama-darwin.zip)
+## Download
 
-### Windows
-
-Coming soon!
-
-### Linux & WSL2
-
-```
-curl https://ollama.ai/install.sh | sh
-```
-
-[Manual install instructions](https://github.com/jmorganca/ollama/blob/main/docs/linux.md)
-
-### Docker
-
-The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama` is available on Docker Hub.
+- [Download](https://ollama.ai/download) for macOS on Apple Silicon (Intel coming soon)
+- Download for Windows and Linux (coming soon)
+- Build [from source](#building)
 
 ## Quickstart
 
-To run and chat with [Llama 2](https://ollama.ai/library/llama2):
+To run and chat with [Llama 2](https://ai.meta.com/llama), the new model by Meta:
 
 ```
 ollama run llama2
@@ -41,54 +29,32 @@ ollama run llama2
 
 ## Model library
 
-Ollama supports a list of open-source models available on [ollama.ai/library](https://ollama.ai/library 'ollama model library')
+`ollama` includes a library of open-source models:
 
-Here are some example open-source models that can be downloaded:
-
-| Model              | Parameters | Size  | Download                       |
-| ------------------ | ---------- | ----- | ------------------------------ |
-| Mistral            | 7B         | 4.1GB | `ollama run mistral`           |
-| Llama 2            | 7B         | 3.8GB | `ollama run llama2`            |
-| Code Llama         | 7B         | 3.8GB | `ollama run codellama`         |
-| Llama 2 Uncensored | 7B         | 3.8GB | `ollama run llama2-uncensored` |
-| Llama 2 13B        | 13B        | 7.3GB | `ollama run llama2:13b`        |
-| Llama 2 70B        | 70B        | 39GB  | `ollama run llama2:70b`        |
-| Orca Mini          | 3B         | 1.9GB | `ollama run orca-mini`         |
-| Vicuna             | 7B         | 3.8GB | `ollama run vicuna`            |
+| Model                    | Parameters | Size  | Download                    |
+| ------------------------ | ---------- | ----- | --------------------------- |
+| Llama2                   | 7B         | 3.8GB | `ollama pull llama2`        |
+| Llama2 13B               | 13B        | 7.3GB | `ollama pull llama2:13b`    |
+| Orca Mini                | 3B         | 1.9GB | `ollama pull orca`          |
+| Vicuna                   | 7B         | 3.8GB | `ollama pull vicuna`        |
+| Nous-Hermes              | 13B        | 7.3GB | `ollama pull nous-hermes`   |
+| Wizard Vicuna Uncensored | 13B        | 7.3GB | `ollama pull wizard-vicuna` |
 
 > Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.
 
-## Customize your own model
+## Examples
 
-### Import from GGUF
+### Run a model
 
-Ollama supports importing GGUF models in the Modelfile:
+```
+ollama run llama2
+>>> hi
+Hello! How can I help you today?
+```
 
-1. Create a file named `Modelfile`, with a `FROM` instruction with the local filepath to the model you want to import.
+### Create a custom model
 
-   ```
-   FROM ./vicuna-33b.Q4_0.gguf
-   ```
-
-2. Create the model in Ollama
-
-   ```
-   ollama create example -f Modelfile
-   ```
-
-3. Run the model
-
-   ```
-   ollama run example
-   ```
-
-### Import from PyTorch or Safetensors
-
-See the [guide](docs/import.md) on importing models for more information.
-
-### Customize a prompt
-
-Models from the Ollama library can be customized with a prompt. For example, to customize the `llama2` model:
+Pull a base model:
 
 ```
 ollama pull llama2
@@ -117,84 +83,44 @@ ollama run mario
 Hello! It's your friend Mario.
 ```
 
-For more examples, see the [examples](examples) directory. For more information on working with a Modelfile, see the [Modelfile](docs/modelfile.md) documentation.
+For more examples, see the [examples](./examples) directory.
 
-## CLI Reference
-
-### Create a model
-
-`ollama create` is used to create a model from a Modelfile.
-
-### Pull a model
+### Pull a model from the registry
 
 ```
-ollama pull llama2
+ollama pull orca
 ```
 
-> This command can also be used to update a local model. Only the diff will be pulled.
-
-### Remove a model
-
-```
-ollama rm llama2
-```
-
-### Copy a model
-
-```
-ollama cp llama2 my-llama2
-```
-
-### Multiline input
-
-For multiline input, you can wrap text with `"""`:
-
-```
->>> """Hello,
-... world!
-... """
-I'm a basic program that prints the famous "Hello, world!" message to the console.
-```
-
-### Pass in prompt as arguments
-
-```
-$ ollama run llama2 "Summarize this file: $(cat README.md)"
- Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.
-```
-
-### List models on your computer
+### Listing local models
 
 ```
 ollama list
 ```
 
-### Start Ollama
+## Model packages
 
-`ollama serve` is used when you want to start ollama without running the desktop application.
+### Overview
+
+Ollama bundles model weights, configuration, and data into a single package, defined by a [Modelfile](./docs/modelfile.md).
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" height="480" srcset="https://github.com/jmorganca/ollama/assets/251292/2fd96b5f-191b-45c1-9668-941cfad4eb70">
+  <img alt="logo" height="480" src="https://github.com/jmorganca/ollama/assets/251292/2fd96b5f-191b-45c1-9668-941cfad4eb70">
+</picture>
 
 ## Building
 
-Install `cmake` and `go`:
-
 ```
-brew install cmake go
-```
-
-Then generate dependencies and build:
-
-```
-go generate ./...
 go build .
 ```
 
-Next, start the server:
+To run it start the server:
 
 ```
-./ollama serve
+./ollama serve &
 ```
 
-Finally, in a separate shell, run a model:
+Finally, run a model!
 
 ```
 ./ollama run llama2
@@ -202,67 +128,10 @@ Finally, in a separate shell, run a model:
 
 ## REST API
 
-Ollama has a REST API for running and managing models.
-For example, to generate text from a model:
+### `POST /api/generate`
+
+Generate text from a model.
 
 ```
-curl http://localhost:11434/api/generate -d '{
-  "model": "llama2",
-  "prompt":"Why is the sky blue?"
-}'
+curl -X POST http://localhost:11434/api/generate -d '{"model": "llama2", "prompt":"Why is the sky blue?"}'
 ```
-
-See the [API documentation](./docs/api.md) for all endpoints.
-
-## Community Integrations
-
-### Web & Desktop
-
-- [HTML UI](https://github.com/rtcfirefly/ollama-ui)
-- [Chatbot UI](https://github.com/ivanfioravanti/chatbot-ollama)
-- [Typescript UI](https://github.com/ollama-interface/Ollama-Gui?tab=readme-ov-file)
-- [Minimalistic React UI for Ollama Models](https://github.com/richawo/minimal-llm-ui)
-- [Web UI](https://github.com/ollama-webui/ollama-webui)
-- [Ollamac](https://github.com/kevinhermawan/Ollamac)
-- [big-AGI](https://github.com/enricoros/big-agi/blob/main/docs/config-ollama.md)
-- [Cheshire Cat assistant framework](https://github.com/cheshire-cat-ai/core)
-
-### Terminal
-
-- [oterm](https://github.com/ggozad/oterm)
-- [Ellama Emacs client](https://github.com/s-kostyaev/ellama)
-- [Emacs client](https://github.com/zweifisch/ollama)
-- [gen.nvim](https://github.com/David-Kunz/gen.nvim)
-- [ollama.nvim](https://github.com/nomnivore/ollama.nvim)
-- [ogpt.nvim](https://github.com/huynle/ogpt.nvim)
-- [gptel Emacs client](https://github.com/karthink/gptel)
-
-### Libraries
-
-- [LangChain](https://python.langchain.com/docs/integrations/llms/ollama) and [LangChain.js](https://js.langchain.com/docs/modules/model_io/models/llms/integrations/ollama) with [example](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa)
-- [LangChainGo](https://github.com/tmc/langchaingo/) with [example](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example)
-- [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/llm/ollama.html)
-- [LiteLLM](https://github.com/BerriAI/litellm)
-- [OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp)
-- [Ollama-rs for Rust](https://github.com/pepperoni21/ollama-rs)
-- [Ollama4j for Java](https://github.com/amithkoujalgi/ollama4j)
-- [ModelFusion Typescript Library](https://modelfusion.dev/integration/model-provider/ollama)
-- [OllamaKit for Swift](https://github.com/kevinhermawan/OllamaKit)
-- [Ollama for Dart](https://github.com/breitburg/dart-ollama)
-- [Ollama for Laravel](https://github.com/cloudstudio/ollama-laravel)
-
-### Mobile
-
-- [Maid](https://github.com/danemadsen/Maid) (Mobile Artificial Intelligence Distribution)
-
-### Extensions & Plugins
-
-- [Raycast extension](https://github.com/MassimilianoPasquini97/raycast_ollama)
-- [Discollama](https://github.com/mxyng/discollama) (Discord bot inside the Ollama discord channel)
-- [Continue](https://github.com/continuedev/continue)
-- [Obsidian Ollama plugin](https://github.com/hinterdupfinger/obsidian-ollama)
-- [Logseq Ollama plugin](https://github.com/omagdy7/ollama-logseq)
-- [Dagger Chatbot](https://github.com/samalba/dagger-chatbot)
-- [Discord AI Bot](https://github.com/mekb-turtle/discord-ai-bot)
-- [Hass Ollama Conversation](https://github.com/ej52/hass-ollama-conversation)
-- [Rivet plugin](https://github.com/abrenneke/rivet-plugin-ollama)

api/client.go

@@ -5,27 +5,20 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
-	"errors"
 	"fmt"
 	"io"
-	"net"
 	"net/http"
 	"net/url"
-	"os"
-	"runtime"
-	"strings"
-
-	"github.com/jmorganca/ollama/format"
-	"github.com/jmorganca/ollama/version"
 )
 
 type Client struct {
-	base *url.URL
-	http http.Client
+	base    url.URL
+	HTTP    http.Client
+	Headers http.Header
 }
 
 func checkError(resp *http.Response, body []byte) error {
-	if resp.StatusCode < http.StatusBadRequest {
+	if resp.StatusCode >= 200 && resp.StatusCode < 400 {
 		return nil
 	}
 
@@ -40,89 +33,45 @@ func checkError(resp *http.Response, body []byte) error {
 	return apiError
 }
 
-func ClientFromEnvironment() (*Client, error) {
-	defaultPort := "11434"
-
-	scheme, hostport, ok := strings.Cut(os.Getenv("OLLAMA_HOST"), "://")
-	switch {
-	case !ok:
-		scheme, hostport = "http", os.Getenv("OLLAMA_HOST")
-	case scheme == "http":
-		defaultPort = "80"
-	case scheme == "https":
-		defaultPort = "443"
+func NewClient(hosts ...string) *Client {
+	host := "127.0.0.1:11434"
+	if len(hosts) > 0 {
+		host = hosts[0]
 	}
 
-	// trim trailing slashes
-	hostport = strings.TrimRight(hostport, "/")
-
-	host, port, err := net.SplitHostPort(hostport)
-	if err != nil {
-		host, port = "127.0.0.1", defaultPort
-		if ip := net.ParseIP(strings.Trim(hostport, "[]")); ip != nil {
-			host = ip.String()
-		} else if hostport != "" {
-			host = hostport
-		}
+	return &Client{
+		base: url.URL{Scheme: "http", Host: host},
+		HTTP: http.Client{},
 	}
-
-	client := Client{
-		base: &url.URL{
-			Scheme: scheme,
-			Host:   net.JoinHostPort(host, port),
-		},
-	}
-
-	mockRequest, err := http.NewRequest(http.MethodHead, client.base.String(), nil)
-	if err != nil {
-		return nil, err
-	}
-
-	proxyURL, err := http.ProxyFromEnvironment(mockRequest)
-	if err != nil {
-		return nil, err
-	}
-
-	client.http = http.Client{
-		Transport: &http.Transport{
-			Proxy: http.ProxyURL(proxyURL),
-		},
-	}
-
-	return &client, nil
 }
 
 func (c *Client) do(ctx context.Context, method, path string, reqData, respData any) error {
 	var reqBody io.Reader
 	var data []byte
 	var err error
-
-	switch reqData := reqData.(type) {
-	case io.Reader:
-		// reqData is already an io.Reader
-		reqBody = reqData
-	case nil:
-		// noop
-	default:
+	if reqData != nil {
 		data, err = json.Marshal(reqData)
 		if err != nil {
 			return err
 		}
-
 		reqBody = bytes.NewReader(data)
 	}
 
-	requestURL := c.base.JoinPath(path)
-	request, err := http.NewRequestWithContext(ctx, method, requestURL.String(), reqBody)
+	url := c.base.JoinPath(path).String()
+
+	req, err := http.NewRequestWithContext(ctx, method, url, reqBody)
 	if err != nil {
 		return err
 	}
 
-	request.Header.Set("Content-Type", "application/json")
-	request.Header.Set("Accept", "application/json")
-	request.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Accept", "application/json")
 
-	respObj, err := c.http.Do(request)
+	for k, v := range c.Headers {
+		req.Header[k] = v
+	}
+
+	respObj, err := c.HTTP.Do(req)
 	if err != nil {
 		return err
 	}
@@ -145,8 +94,6 @@ func (c *Client) do(ctx context.Context, method, path string, reqData, respData
 	return nil
 }
 
-const maxBufferSize = 512 * format.KiloByte
-
 func (c *Client) stream(ctx context.Context, method, path string, data any, fn func([]byte) error) error {
 	var buf *bytes.Buffer
 	if data != nil {
@@ -158,26 +105,21 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
 		buf = bytes.NewBuffer(bts)
 	}
 
-	requestURL := c.base.JoinPath(path)
-	request, err := http.NewRequestWithContext(ctx, method, requestURL.String(), buf)
+	request, err := http.NewRequestWithContext(ctx, method, c.base.JoinPath(path).String(), buf)
 	if err != nil {
 		return err
 	}
 
 	request.Header.Set("Content-Type", "application/json")
-	request.Header.Set("Accept", "application/x-ndjson")
-	request.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))
+	request.Header.Set("Accept", "application/json")
 
-	response, err := c.http.Do(request)
+	response, err := http.DefaultClient.Do(request)
 	if err != nil {
 		return err
 	}
 	defer response.Body.Close()
 
 	scanner := bufio.NewScanner(response.Body)
-	// increase the buffer size to avoid running out of space
-	scanBuf := make([]byte, 0, maxBufferSize)
-	scanner.Buffer(scanBuf, maxBufferSize)
 	for scanner.Scan() {
 		var errorResponse struct {
 			Error string `json:"error,omitempty"`
@@ -189,10 +131,10 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
 		}
 
 		if errorResponse.Error != "" {
-			return fmt.Errorf(errorResponse.Error)
+			return fmt.Errorf("stream: %s", errorResponse.Error)
 		}
 
-		if response.StatusCode >= http.StatusBadRequest {
+		if response.StatusCode >= 400 {
 			return StatusError{
 				StatusCode:   response.StatusCode,
 				Status:       response.Status,
@@ -247,11 +189,11 @@ func (c *Client) Push(ctx context.Context, req *PushRequest, fn PushProgressFunc
 	})
 }
 
-type CreateProgressFunc func(ProgressResponse) error
+type CreateProgressFunc func(CreateProgress) error
 
 func (c *Client) Create(ctx context.Context, req *CreateRequest, fn CreateProgressFunc) error {
 	return c.stream(ctx, http.MethodPost, "/api/create", req, func(bts []byte) error {
-		var resp ProgressResponse
+		var resp CreateProgress
 		if err := json.Unmarshal(bts, &resp); err != nil {
 			return err
 		}
@@ -268,46 +210,9 @@ func (c *Client) List(ctx context.Context) (*ListResponse, error) {
 	return &lr, nil
 }
 
-func (c *Client) Copy(ctx context.Context, req *CopyRequest) error {
-	if err := c.do(ctx, http.MethodPost, "/api/copy", req, nil); err != nil {
-		return err
-	}
-	return nil
-}
-
 func (c *Client) Delete(ctx context.Context, req *DeleteRequest) error {
 	if err := c.do(ctx, http.MethodDelete, "/api/delete", req, nil); err != nil {
 		return err
 	}
 	return nil
 }
-
-func (c *Client) Show(ctx context.Context, req *ShowRequest) (*ShowResponse, error) {
-	var resp ShowResponse
-	if err := c.do(ctx, http.MethodPost, "/api/show", req, &resp); err != nil {
-		return nil, err
-	}
-	return &resp, nil
-}
-
-func (c *Client) Heartbeat(ctx context.Context) error {
-	if err := c.do(ctx, http.MethodHead, "/", nil, nil); err != nil {
-		return err
-	}
-	return nil
-}
-
-func (c *Client) CreateBlob(ctx context.Context, digest string, r io.Reader) error {
-	if err := c.do(ctx, http.MethodHead, fmt.Sprintf("/api/blobs/%s", digest), nil, nil); err != nil {
-		var statusError StatusError
-		if !errors.As(err, &statusError) || statusError.StatusCode != http.StatusNotFound {
-			return err
-		}
-
-		if err := c.do(ctx, http.MethodPost, fmt.Sprintf("/api/blobs/%s", digest), r, nil); err != nil {
-			return err
-		}
-	}
-
-	return nil
-}

api/client.py

@@ -1,226 +0,0 @@
-import os
-import json
-import requests
-
-BASE_URL = os.environ.get('OLLAMA_HOST', 'http://localhost:11434')
-
-# Generate a response for a given prompt with a provided model. This is a streaming endpoint, so will be a series of responses.
-# The final response object will include statistics and additional data from the request. Use the callback function to override
-# the default handler.
-def generate(model_name, prompt, system=None, template=None, format="", context=None, options=None, callback=None):
-    try:
-        url = f"{BASE_URL}/api/generate"
-        payload = {
-            "model": model_name, 
-            "prompt": prompt, 
-            "system": system, 
-            "template": template, 
-            "context": context, 
-            "options": options,
-            "format": format,
-        }
-        
-        # Remove keys with None values
-        payload = {k: v for k, v in payload.items() if v is not None}
-        
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-            
-            # Creating a variable to hold the context history of the final chunk
-            final_context = None
-            
-            # Variable to hold concatenated response strings if no callback is provided
-            full_response = ""
-
-            # Iterating over the response line by line and displaying the details
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the details
-                    chunk = json.loads(line)
-                    
-                    # If a callback function is provided, call it with the chunk
-                    if callback:
-                        callback(chunk)
-                    else:
-                        # If this is not the last chunk, add the "response" field value to full_response and print it
-                        if not chunk.get("done"):
-                            response_piece = chunk.get("response", "")
-                            full_response += response_piece
-                            print(response_piece, end="", flush=True)
-                    
-                    # Check if it's the last chunk (done is true)
-                    if chunk.get("done"):
-                        final_context = chunk.get("context")
-            
-            # Return the full response and the final context
-            return full_response, final_context
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None, None
-
-# Create a model from a Modelfile. Use the callback function to override the default handler.
-def create(model_name, model_path, callback=None):
-    try:
-        url = f"{BASE_URL}/api/create"
-        payload = {"name": model_name, "path": model_path}
-        
-        # Making a POST request with the stream parameter set to True to handle streaming responses
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-
-            # Iterating over the response line by line and displaying the status
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the status
-                    chunk = json.loads(line)
-
-                    if callback:
-                        callback(chunk)
-                    else:
-                        print(f"Status: {chunk.get('status')}")
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-
-# Pull a model from a the model registry. Cancelled pulls are resumed from where they left off, and multiple
-# calls to will share the same download progress. Use the callback function to override the default handler.
-def pull(model_name, insecure=False, callback=None):
-    try:
-        url = f"{BASE_URL}/api/pull"
-        payload = {
-            "name": model_name,
-            "insecure": insecure
-        }
-
-        # Making a POST request with the stream parameter set to True to handle streaming responses
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-
-            # Iterating over the response line by line and displaying the details
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the details
-                    chunk = json.loads(line)
-
-                    # If a callback function is provided, call it with the chunk
-                    if callback:
-                        callback(chunk)
-                    else:
-                        # Print the status message directly to the console
-                        print(chunk.get('status', ''), end='', flush=True)
-                    
-                    # If there's layer data, you might also want to print that (adjust as necessary)
-                    if 'digest' in chunk:
-                        print(f" - Digest: {chunk['digest']}", end='', flush=True)
-                        print(f" - Total: {chunk['total']}", end='', flush=True)
-                        print(f" - Completed: {chunk['completed']}", end='\n', flush=True)
-                    else:
-                        print()
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-
-# Push a model to the model registry. Use the callback function to override the default handler.
-def push(model_name, insecure=False, callback=None):
-    try:
-        url = f"{BASE_URL}/api/push"
-        payload = {
-            "name": model_name,
-            "insecure": insecure
-        }
-
-        # Making a POST request with the stream parameter set to True to handle streaming responses
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-
-            # Iterating over the response line by line and displaying the details
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the details
-                    chunk = json.loads(line)
-
-                    # If a callback function is provided, call it with the chunk
-                    if callback:
-                        callback(chunk)
-                    else:
-                        # Print the status message directly to the console
-                        print(chunk.get('status', ''), end='', flush=True)
-                    
-                    # If there's layer data, you might also want to print that (adjust as necessary)
-                    if 'digest' in chunk:
-                        print(f" - Digest: {chunk['digest']}", end='', flush=True)
-                        print(f" - Total: {chunk['total']}", end='', flush=True)
-                        print(f" - Completed: {chunk['completed']}", end='\n', flush=True)
-                    else:
-                        print()
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-
-# List models that are available locally.
-def list():
-    try:
-        response = requests.get(f"{BASE_URL}/api/tags")
-        response.raise_for_status()
-        data = response.json()
-        models = data.get('models', [])
-        return models
-
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-# Copy a model. Creates a model with another name from an existing model.
-def copy(source, destination):
-    try:
-        # Create the JSON payload
-        payload = {
-            "source": source,
-            "destination": destination
-        }
-        
-        response = requests.post(f"{BASE_URL}/api/copy", json=payload)
-        response.raise_for_status()
-        
-        # If the request was successful, return a message indicating that the copy was successful
-        return "Copy successful"
-
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-# Delete a model and its data.
-def delete(model_name):
-    try:
-        url = f"{BASE_URL}/api/delete"
-        payload = {"name": model_name}
-        response = requests.delete(url, json=payload)
-        response.raise_for_status()
-        return "Delete successful"
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-# Show info about a model.
-def show(model_name):
-    try:
-        url = f"{BASE_URL}/api/show"
-        payload = {"name": model_name}
-        response = requests.post(url, json=payload)
-        response.raise_for_status()
-        
-        # Parse the JSON response and return it
-        data = response.json()
-        return data
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-def heartbeat():
-    try:
-        url = f"{BASE_URL}/"
-        response = requests.head(url)
-        response.raise_for_status()
-        return "Ollama is running"
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return "Ollama is not running"
-
-

api/client_test.go

@@ -1,43 +0,0 @@
-package api
-
-import "testing"
-
-func TestClientFromEnvironment(t *testing.T) {
-	type testCase struct {
-		value  string
-		expect string
-		err    error
-	}
-
-	testCases := map[string]*testCase{
-		"empty":                      {value: "", expect: "http://127.0.0.1:11434"},
-		"only address":               {value: "1.2.3.4", expect: "http://1.2.3.4:11434"},
-		"only port":                  {value: ":1234", expect: "http://:1234"},
-		"address and port":           {value: "1.2.3.4:1234", expect: "http://1.2.3.4:1234"},
-		"scheme http and address":    {value: "http://1.2.3.4", expect: "http://1.2.3.4:80"},
-		"scheme https and address":   {value: "https://1.2.3.4", expect: "https://1.2.3.4:443"},
-		"scheme, address, and port":  {value: "https://1.2.3.4:1234", expect: "https://1.2.3.4:1234"},
-		"hostname":                   {value: "example.com", expect: "http://example.com:11434"},
-		"hostname and port":          {value: "example.com:1234", expect: "http://example.com:1234"},
-		"scheme http and hostname":   {value: "http://example.com", expect: "http://example.com:80"},
-		"scheme https and hostname":  {value: "https://example.com", expect: "https://example.com:443"},
-		"scheme, hostname, and port": {value: "https://example.com:1234", expect: "https://example.com:1234"},
-		"trailing slash":             {value: "example.com/", expect: "http://example.com:11434"},
-		"trailing slash port":        {value: "example.com:1234/", expect: "http://example.com:1234"},
-	}
-
-	for k, v := range testCases {
-		t.Run(k, func(t *testing.T) {
-			t.Setenv("OLLAMA_HOST", v.value)
-
-			client, err := ClientFromEnvironment()
-			if err != v.err {
-				t.Fatalf("expected %s, got %s", v.err, err)
-			}
-
-			if client.base.String() != v.expect {
-				t.Fatalf("expected %s, got %s", v.expect, client.base.String())
-			}
-		})
-	}
-}

api/types.go

@@ -1,12 +1,9 @@
 package api
 
 import (
-	"encoding/json"
 	"fmt"
-	"math"
 	"os"
-	"reflect"
-	"strings"
+	"runtime"
 	"time"
 )
 
@@ -31,114 +28,38 @@ func (e StatusError) Error() string {
 }
 
 type GenerateRequest struct {
-	Model    string `json:"model"`
-	Prompt   string `json:"prompt"`
-	System   string `json:"system"`
-	Template string `json:"template"`
-	Context  []int  `json:"context,omitempty"`
-	Stream   *bool  `json:"stream,omitempty"`
-	Raw      bool   `json:"raw,omitempty"`
-	Format   string `json:"format"`
+	Model   string `json:"model"`
+	Prompt  string `json:"prompt"`
+	Context []int  `json:"context,omitempty"`
 
-	Options map[string]interface{} `json:"options"`
-}
-
-// Options specfied in GenerateRequest, if you add a new option here add it to the API docs also
-type Options struct {
-	Runner
-
-	// Predict options used at runtime
-	NumKeep          int      `json:"num_keep,omitempty"`
-	Seed             int      `json:"seed,omitempty"`
-	NumPredict       int      `json:"num_predict,omitempty"`
-	TopK             int      `json:"top_k,omitempty"`
-	TopP             float32  `json:"top_p,omitempty"`
-	TFSZ             float32  `json:"tfs_z,omitempty"`
-	TypicalP         float32  `json:"typical_p,omitempty"`
-	RepeatLastN      int      `json:"repeat_last_n,omitempty"`
-	Temperature      float32  `json:"temperature,omitempty"`
-	RepeatPenalty    float32  `json:"repeat_penalty,omitempty"`
-	PresencePenalty  float32  `json:"presence_penalty,omitempty"`
-	FrequencyPenalty float32  `json:"frequency_penalty,omitempty"`
-	Mirostat         int      `json:"mirostat,omitempty"`
-	MirostatTau      float32  `json:"mirostat_tau,omitempty"`
-	MirostatEta      float32  `json:"mirostat_eta,omitempty"`
-	PenalizeNewline  bool     `json:"penalize_newline,omitempty"`
-	Stop             []string `json:"stop,omitempty"`
-}
-
-// Runner options which must be set when the model is loaded into memory
-type Runner struct {
-	UseNUMA            bool    `json:"numa,omitempty"`
-	NumCtx             int     `json:"num_ctx,omitempty"`
-	NumBatch           int     `json:"num_batch,omitempty"`
-	NumGQA             int     `json:"num_gqa,omitempty"`
-	NumGPU             int     `json:"num_gpu,omitempty"`
-	MainGPU            int     `json:"main_gpu,omitempty"`
-	LowVRAM            bool    `json:"low_vram,omitempty"`
-	F16KV              bool    `json:"f16_kv,omitempty"`
-	LogitsAll          bool    `json:"logits_all,omitempty"`
-	VocabOnly          bool    `json:"vocab_only,omitempty"`
-	UseMMap            bool    `json:"use_mmap,omitempty"`
-	UseMLock           bool    `json:"use_mlock,omitempty"`
-	EmbeddingOnly      bool    `json:"embedding_only,omitempty"`
-	RopeFrequencyBase  float32 `json:"rope_frequency_base,omitempty"`
-	RopeFrequencyScale float32 `json:"rope_frequency_scale,omitempty"`
-	NumThread          int     `json:"num_thread,omitempty"`
-}
-
-type EmbeddingRequest struct {
-	Model  string `json:"model"`
-	Prompt string `json:"prompt"`
-
-	Options map[string]interface{} `json:"options"`
-}
-
-type EmbeddingResponse struct {
-	Embedding []float64 `json:"embedding"`
+	Options `json:"options"`
 }
 
 type CreateRequest struct {
-	Name      string `json:"name"`
-	Path      string `json:"path"`
-	Modelfile string `json:"modelfile"`
-	Stream    *bool  `json:"stream,omitempty"`
+	Name string `json:"name"`
+	Path string `json:"path"`
+}
+
+type CreateProgress struct {
+	Status string `json:"status"`
 }
 
 type DeleteRequest struct {
 	Name string `json:"name"`
 }
 
-type ShowRequest struct {
-	Name string `json:"name"`
-}
-
-type ShowResponse struct {
-	License    string `json:"license,omitempty"`
-	Modelfile  string `json:"modelfile,omitempty"`
-	Parameters string `json:"parameters,omitempty"`
-	Template   string `json:"template,omitempty"`
-	System     string `json:"system,omitempty"`
-}
-
-type CopyRequest struct {
-	Source      string `json:"source"`
-	Destination string `json:"destination"`
-}
-
 type PullRequest struct {
 	Name     string `json:"name"`
 	Insecure bool   `json:"insecure,omitempty"`
 	Username string `json:"username"`
 	Password string `json:"password"`
-	Stream   *bool  `json:"stream,omitempty"`
 }
 
 type ProgressResponse struct {
 	Status    string `json:"status"`
 	Digest    string `json:"digest,omitempty"`
-	Total     int64  `json:"total,omitempty"`
-	Completed int64  `json:"completed,omitempty"`
+	Total     int    `json:"total,omitempty"`
+	Completed int    `json:"completed,omitempty"`
 }
 
 type PushRequest struct {
@@ -146,34 +67,27 @@ type PushRequest struct {
 	Insecure bool   `json:"insecure,omitempty"`
 	Username string `json:"username"`
 	Password string `json:"password"`
-	Stream   *bool  `json:"stream,omitempty"`
 }
 
 type ListResponse struct {
-	Models []ModelResponse `json:"models"`
+	Models []ListResponseModel `json:"models"`
 }
 
-type ModelResponse struct {
+type ListResponseModel struct {
 	Name       string    `json:"name"`
 	ModifiedAt time.Time `json:"modified_at"`
-	Size       int64     `json:"size"`
-	Digest     string    `json:"digest"`
-}
-
-type TokenResponse struct {
-	Token string `json:"token"`
+	Size       int       `json:"size"`
 }
 
 type GenerateResponse struct {
 	Model     string    `json:"model"`
 	CreatedAt time.Time `json:"created_at"`
-	Response  string    `json:"response"`
+	Response  string    `json:"response,omitempty"`
 
 	Done    bool  `json:"done"`
 	Context []int `json:"context,omitempty"`
 
 	TotalDuration      time.Duration `json:"total_duration,omitempty"`
-	LoadDuration       time.Duration `json:"load_duration,omitempty"`
 	PromptEvalCount    int           `json:"prompt_eval_count,omitempty"`
 	PromptEvalDuration time.Duration `json:"prompt_eval_duration,omitempty"`
 	EvalCount          int           `json:"eval_count,omitempty"`
@@ -185,10 +99,6 @@ func (r *GenerateResponse) Summary() {
 		fmt.Fprintf(os.Stderr, "total duration:       %v\n", r.TotalDuration)
 	}
 
-	if r.LoadDuration > 0 {
-		fmt.Fprintf(os.Stderr, "load duration:        %v\n", r.LoadDuration)
-	}
-
 	if r.PromptEvalCount > 0 {
 		fmt.Fprintf(os.Stderr, "prompt eval count:    %d token(s)\n", r.PromptEvalCount)
 	}
@@ -208,155 +118,69 @@ func (r *GenerateResponse) Summary() {
 	}
 }
 
-var ErrInvalidOpts = fmt.Errorf("invalid options")
+type Options struct {
+	Seed int `json:"seed,omitempty"`
 
-func (opts *Options) FromMap(m map[string]interface{}) error {
-	valueOpts := reflect.ValueOf(opts).Elem() // names of the fields in the options struct
-	typeOpts := reflect.TypeOf(opts).Elem()   // types of the fields in the options struct
+	// Backend options
+	UseNUMA bool `json:"numa,omitempty"`
 
-	// build map of json struct tags to their types
-	jsonOpts := make(map[string]reflect.StructField)
-	for _, field := range reflect.VisibleFields(typeOpts) {
-		jsonTag := strings.Split(field.Tag.Get("json"), ",")[0]
-		if jsonTag != "" {
-			jsonOpts[jsonTag] = field
-		}
-	}
+	// Model options
+	NumCtx        int  `json:"num_ctx,omitempty"`
+	NumBatch      int  `json:"num_batch,omitempty"`
+	NumGPU        int  `json:"num_gpu,omitempty"`
+	MainGPU       int  `json:"main_gpu,omitempty"`
+	LowVRAM       bool `json:"low_vram,omitempty"`
+	F16KV         bool `json:"f16_kv,omitempty"`
+	LogitsAll     bool `json:"logits_all,omitempty"`
+	VocabOnly     bool `json:"vocab_only,omitempty"`
+	UseMMap       bool `json:"use_mmap,omitempty"`
+	UseMLock      bool `json:"use_mlock,omitempty"`
+	EmbeddingOnly bool `json:"embedding_only,omitempty"`
 
-	invalidOpts := []string{}
-	for key, val := range m {
-		if opt, ok := jsonOpts[key]; ok {
-			field := valueOpts.FieldByName(opt.Name)
-			if field.IsValid() && field.CanSet() {
-				if val == nil {
-					continue
-				}
+	// Predict options
+	RepeatLastN      int     `json:"repeat_last_n,omitempty"`
+	RepeatPenalty    float32 `json:"repeat_penalty,omitempty"`
+	FrequencyPenalty float32 `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float32 `json:"presence_penalty,omitempty"`
+	Temperature      float32 `json:"temperature,omitempty"`
+	TopK             int     `json:"top_k,omitempty"`
+	TopP             float32 `json:"top_p,omitempty"`
+	TFSZ             float32 `json:"tfs_z,omitempty"`
+	TypicalP         float32 `json:"typical_p,omitempty"`
+	Mirostat         int     `json:"mirostat,omitempty"`
+	MirostatTau      float32 `json:"mirostat_tau,omitempty"`
+	MirostatEta      float32 `json:"mirostat_eta,omitempty"`
 
-				switch field.Kind() {
-				case reflect.Int:
-					switch t := val.(type) {
-					case int64:
-						field.SetInt(t)
-					case float64:
-						// when JSON unmarshals numbers, it uses float64, not int
-						field.SetInt(int64(t))
-					default:
-						return fmt.Errorf("option %q must be of type integer", key)
-					}
-				case reflect.Bool:
-					val, ok := val.(bool)
-					if !ok {
-						return fmt.Errorf("option %q must be of type boolean", key)
-					}
-					field.SetBool(val)
-				case reflect.Float32:
-					// JSON unmarshals to float64
-					val, ok := val.(float64)
-					if !ok {
-						return fmt.Errorf("option %q must be of type float32", key)
-					}
-					field.SetFloat(val)
-				case reflect.String:
-					val, ok := val.(string)
-					if !ok {
-						return fmt.Errorf("option %q must be of type string", key)
-					}
-					field.SetString(val)
-				case reflect.Slice:
-					// JSON unmarshals to []interface{}, not []string
-					val, ok := val.([]interface{})
-					if !ok {
-						return fmt.Errorf("option %q must be of type array", key)
-					}
-					// convert []interface{} to []string
-					slice := make([]string, len(val))
-					for i, item := range val {
-						str, ok := item.(string)
-						if !ok {
-							return fmt.Errorf("option %q must be of an array of strings", key)
-						}
-						slice[i] = str
-					}
-					field.Set(reflect.ValueOf(slice))
-				default:
-					return fmt.Errorf("unknown type loading config params: %v", field.Kind())
-				}
-			}
-		} else {
-			invalidOpts = append(invalidOpts, key)
-		}
-	}
-
-	if len(invalidOpts) > 0 {
-		return fmt.Errorf("%w: %v", ErrInvalidOpts, strings.Join(invalidOpts, ", "))
-	}
-	return nil
+	NumThread int `json:"num_thread,omitempty"`
 }
 
 func DefaultOptions() Options {
 	return Options{
-		// options set on request to runner
-		NumPredict:       -1,
-		NumKeep:          0,
+		Seed: -1,
+
+		UseNUMA: false,
+
+		NumCtx:   2048,
+		NumBatch: 512,
+		NumGPU:   1,
+		LowVRAM:  false,
+		F16KV:    true,
+		UseMMap:  true,
+		UseMLock: false,
+
+		RepeatLastN:      512,
+		RepeatPenalty:    1.1,
+		FrequencyPenalty: 0.0,
+		PresencePenalty:  0.0,
 		Temperature:      0.8,
 		TopK:             40,
 		TopP:             0.9,
 		TFSZ:             1.0,
 		TypicalP:         1.0,
-		RepeatLastN:      64,
-		RepeatPenalty:    1.1,
-		PresencePenalty:  0.0,
-		FrequencyPenalty: 0.0,
 		Mirostat:         0,
 		MirostatTau:      5.0,
 		MirostatEta:      0.1,
-		PenalizeNewline:  true,
-		Seed:             -1,
 
-		Runner: Runner{
-			// options set when the model is loaded
-			NumCtx:             2048,
-			RopeFrequencyBase:  10000.0,
-			RopeFrequencyScale: 1.0,
-			NumBatch:           512,
-			NumGPU:             -1, // -1 here indicates that NumGPU should be set dynamically
-			NumGQA:             1,
-			NumThread:          0, // let the runtime decide
-			LowVRAM:            false,
-			F16KV:              true,
-			UseMLock:           false,
-			UseMMap:            true,
-			UseNUMA:            false,
-			EmbeddingOnly:      true,
-		},
+		NumThread: runtime.NumCPU(),
 	}
 }
-
-type Duration struct {
-	time.Duration
-}
-
-func (d *Duration) UnmarshalJSON(b []byte) (err error) {
-	var v any
-	if err := json.Unmarshal(b, &v); err != nil {
-		return err
-	}
-
-	d.Duration = 5 * time.Minute
-
-	switch t := v.(type) {
-	case float64:
-		if t < 0 {
-			t = math.MaxFloat64
-		}
-
-		d.Duration = time.Duration(t)
-	case string:
-		d.Duration, err = time.ParseDuration(t)
-		if err != nil {
-			return err
-		}
-	}
-
-	return nil
-}

app/README.md

@@ -1,5 +1,7 @@
 # Desktop
 
+_Note: the Ollama desktop app is a work in progress and is not ready yet for general use._
+
 This app builds upon Ollama to provide a desktop experience for running models.
 
 ## Developing
@@ -7,15 +9,19 @@ This app builds upon Ollama to provide a desktop experience for running models.
 First, build the `ollama` binary:
 
 ```
-cd ..
-go build .
+make -C ..
 ```
 
 Then run the desktop app with `npm start`:
 
 ```
-cd app
 npm install
 npm start
 ```
 
+## Coming soon
+
+- Browse the latest available models on Hugging Face and other sources
+- Keep track of previous conversations with models
+- Switch quickly between models
+- Connect to remote Ollama servers to run models

app/forge.config.ts

@@ -18,15 +18,12 @@ const config: ForgeConfig = {
     asar: true,
     icon: './assets/icon.icns',
     extraResource: [
-      '../dist/ollama',
-      path.join(__dirname, './assets/iconTemplate.png'),
-      path.join(__dirname, './assets/iconTemplate@2x.png'),
-      path.join(__dirname, './assets/iconUpdateTemplate.png'),
-      path.join(__dirname, './assets/iconUpdateTemplate@2x.png'),
-      path.join(__dirname, './assets/iconDarkTemplate.png'),
-      path.join(__dirname, './assets/iconDarkTemplate@2x.png'),
-      path.join(__dirname, './assets/iconDarkUpdateTemplate.png'),
-      path.join(__dirname, './assets/iconDarkUpdateTemplate@2x.png'),
+      '../ollama',
+      path.join(__dirname, './assets/ollama_icon_16x16Template.png'),
+      path.join(__dirname, './assets/ollama_icon_16x16Template@2x.png'),
+      path.join(__dirname, './assets/ollama_outline_icon_16x16Template.png'),
+      path.join(__dirname, './assets/ollama_outline_icon_16x16Template@2x.png'),
+      ...(process.platform === 'darwin' ? ['../llama/ggml-metal.metal'] : []),
     ],
     ...(process.env.SIGN
       ? {
@@ -41,12 +38,19 @@ const config: ForgeConfig = {
           },
         }
       : {}),
-    osxUniversal: {
-      x64ArchFiles: '**/ollama',
-    },
   },
   rebuildConfig: {},
   makers: [new MakerSquirrel({}), new MakerZIP({}, ['darwin'])],
+  publishers: [
+    new PublisherGithub({
+      repository: {
+        name: 'ollama',
+        owner: 'jmorganca',
+      },
+      draft: false,
+      prerelease: true,
+    }),
+  ],
   hooks: {
     readPackageJson: async (_, packageJson) => {
       return { ...packageJson, version: process.env.VERSION || packageJson.version }

app/package.json

@@ -6,14 +6,12 @@
   "main": ".webpack/main",
   "scripts": {
     "start": "electron-forge start",
-    "package": "electron-forge package --arch universal",
-    "package:sign": "SIGN=1 electron-forge package --arch universal",
-    "make": "electron-forge make --arch universal",
-    "make:sign": "SIGN=1 electron-forge make --arch universal",
+    "package": "electron-forge package",
+    "package:sign": "SIGN=1 electron-forge package",
+    "make": "electron-forge make",
+    "make:sign": "SIGN=1 electron-forge make",
     "publish": "SIGN=1 electron-forge publish",
-    "lint": "eslint --ext .ts,.tsx .",
-    "format": "prettier --check . --ignore-path .gitignore",
-    "format:fix": "prettier --write . --ignore-path .gitignore"
+    "lint": "eslint --ext .ts,.tsx ."
   },
   "keywords": [],
   "author": {
@@ -32,7 +30,6 @@
     "@electron-forge/plugin-auto-unpack-natives": "^6.2.1",
     "@electron-forge/plugin-webpack": "^6.2.1",
     "@electron-forge/publisher-github": "^6.2.1",
-    "@electron/universal": "^1.4.1",
     "@svgr/webpack": "^8.0.1",
     "@types/chmodr": "^1.0.0",
     "@types/node": "^20.4.0",
@@ -46,7 +43,7 @@
     "chmodr": "^1.2.0",
     "copy-webpack-plugin": "^11.0.0",
     "css-loader": "^6.8.1",
-    "electron": "25.9.2",
+    "electron": "25.2.0",
     "eslint": "^8.43.0",
     "eslint-plugin-import": "^2.27.5",
     "fork-ts-checker-webpack-plugin": "^7.3.0",

app/src/app.tsx

@@ -2,7 +2,7 @@ import { useState } from 'react'
 import copy from 'copy-to-clipboard'
 import { CheckIcon, DocumentDuplicateIcon } from '@heroicons/react/24/outline'
 import Store from 'electron-store'
-import { getCurrentWindow, app } from '@electron/remote'
+import { getCurrentWindow } from '@electron/remote'
 
 import { install } from './install'
 import OllamaIcon from './ollama.svg'
@@ -51,15 +51,10 @@ export default function () {
               <div className='mx-auto'>
                 <button
                   onClick={async () => {
-                    try {
-                      await install()
-                      setStep(Step.FINISH)
-                    } catch (e) {
-                      console.error('could not install: ', e)
-                    } finally {
-                      getCurrentWindow().show()
-                      getCurrentWindow().focus()
-                    }
+                    await install()
+                    getCurrentWindow().show()
+                    getCurrentWindow().focus()
+                    setStep(Step.FINISH)
                   }}
                   className='no-drag rounded-dm mx-auto w-[60%] rounded-md bg-black px-4 py-2 text-sm text-white hover:brightness-110'
                 >

app/src/declarations.d.ts

@@ -1,4 +1,4 @@
 declare module '*.svg' {
-  const content: string
-  export default content
-}
+  const content: string;
+  export default content;
+}

app/src/index.ts

@@ -1,21 +1,17 @@
-import { spawn, ChildProcess } from 'child_process'
-import { app, autoUpdater, dialog, Tray, Menu, BrowserWindow, MenuItemConstructorOptions, nativeTheme } from 'electron'
+import { spawn } from 'child_process'
+import { app, autoUpdater, dialog, Tray, Menu, BrowserWindow, nativeTheme } from 'electron'
 import Store from 'electron-store'
 import winston from 'winston'
 import 'winston-daily-rotate-file'
 import * as path from 'path'
 
-import { v4 as uuidv4 } from 'uuid'
+import { analytics, id } from './telemetry'
 import { installed } from './install'
 
 require('@electron/remote/main').initialize()
 
-if (require('electron-squirrel-startup')) {
-  app.quit()
-}
-
 const store = new Store()
-
+let tray: Tray | null = null
 let welcomeWindow: BrowserWindow | null = null
 
 declare const MAIN_WINDOW_WEBPACK_ENTRY: string
@@ -32,30 +28,10 @@ const logger = winston.createLogger({
   format: winston.format.printf(info => info.message),
 })
 
-app.on('ready', () => {
-  const gotTheLock = app.requestSingleInstanceLock()
-  if (!gotTheLock) {
-    app.exit(0)
-    return
-  }
-
-  app.on('second-instance', () => {
-    if (app.hasSingleInstanceLock()) {
-      app.releaseSingleInstanceLock()
-    }
-
-    if (proc) {
-      proc.off('exit', restart)
-      proc.kill()
-    }
-
-    app.exit(0)
-  })
-
-  app.focus({ steal: true })
-
-  init()
-})
+const SingleInstanceLock = app.requestSingleInstanceLock()
+if (!SingleInstanceLock) {
+  app.quit()
+}
 
 function firstRunWindow() {
   // Create the browser window.
@@ -71,74 +47,65 @@ function firstRunWindow() {
       nodeIntegration: true,
       contextIsolation: false,
     },
+    alwaysOnTop: true,
   })
 
   require('@electron/remote/main').enable(welcomeWindow.webContents)
 
+  // and load the index.html of the app.
   welcomeWindow.loadURL(MAIN_WINDOW_WEBPACK_ENTRY)
+
   welcomeWindow.on('ready-to-show', () => welcomeWindow.show())
-  welcomeWindow.on('closed', () => {
-    if (process.platform === 'darwin') {
-      app.dock.hide()
+
+  // for debugging
+  // welcomeWindow.webContents.openDevTools()
+
+  if (process.platform === 'darwin') {
+    app.dock.hide()
+  }
+}
+
+function createSystemtray() {
+  let iconPath = nativeTheme.shouldUseDarkColors
+    ? path.join(__dirname, '..', '..', 'assets', 'ollama_icon_16x16Template.png') 
+    : path.join(__dirname, '..', '..', 'assets', 'ollama_outline_icon_16x16Template.png')
+
+  if (app.isPackaged) {
+    iconPath = nativeTheme.shouldUseDarkColors
+    ? path.join(process.resourcesPath, 'ollama_icon_16x16Template.png') 
+    : path.join(process.resourcesPath, 'ollama_outline_icon_16x16Template.png')
+  }
+
+  tray = new Tray(iconPath)
+
+  nativeTheme.on('updated', function theThemeHasChanged () {
+    if (nativeTheme.shouldUseDarkColors) {
+      app.isPackaged 
+        ? tray.setImage(path.join(process.resourcesPath, 'ollama_icon_16x16Template.png')) 
+        : tray.setImage(path.join(__dirname, '..', '..', 'assets', 'ollama_icon_16x16Template.png'))
+    } else {
+      app.isPackaged 
+        ? tray.setImage(path.join(process.resourcesPath, 'ollama_outline_icon_16x16Template.png')) 
+        : tray.setImage(path.join(__dirname, '..', '..', 'assets', 'ollama_outline_icon_16x16Template.png'))
     }
   })
+
+  const contextMenu = Menu.buildFromTemplate([{ role: 'quit', label: 'Quit Ollama', accelerator: 'Command+Q' }])
+
+  tray.setContextMenu(contextMenu)
+  tray.setToolTip('Ollama')
 }
 
-let tray: Tray | null = null
-let updateAvailable = false
-const assetPath = app.isPackaged ? process.resourcesPath : path.join(__dirname, '..', '..', 'assets')
-
-function trayIconPath() {
-  return nativeTheme.shouldUseDarkColors
-    ? updateAvailable
-      ? path.join(assetPath, 'iconDarkUpdateTemplate.png')
-      : path.join(assetPath, 'iconDarkTemplate.png')
-    : updateAvailable
-    ? path.join(assetPath, 'iconUpdateTemplate.png')
-    : path.join(assetPath, 'iconTemplate.png')
+if (require('electron-squirrel-startup')) {
+  app.quit()
 }
 
-function updateTrayIcon() {
-  if (tray) {
-    tray.setImage(trayIconPath())
-  }
-}
-
-function updateTray() {
-  const updateItems: MenuItemConstructorOptions[] = [
-    { label: 'An update is available', enabled: false },
-    {
-      label: 'Restart to update',
-      click: () => autoUpdater.quitAndInstall(),
-    },
-    { type: 'separator' },
-  ]
-
-  const menu = Menu.buildFromTemplate([
-    ...(updateAvailable ? updateItems : []),
-    { role: 'quit', label: 'Quit Ollama', accelerator: 'Command+Q' },
-  ])
-
-  if (!tray) {
-    tray = new Tray(trayIconPath())
-  }
-
-  tray.setToolTip(updateAvailable ? 'An update is available' : 'Ollama')
-  tray.setContextMenu(menu)
-  tray.setImage(trayIconPath())
-
-  nativeTheme.off('updated', updateTrayIcon)
-  nativeTheme.on('updated', updateTrayIcon)
-}
-
-let proc: ChildProcess = null
-
 function server() {
   const binary = app.isPackaged
     ? path.join(process.resourcesPath, 'ollama')
     : path.resolve(process.cwd(), '..', 'ollama')
 
-  proc = spawn(binary, ['serve'])
+  const proc = spawn(binary, ['serve'])
 
   proc.stdout.on('data', data => {
     logger.info(data.toString().trim())
@@ -148,75 +115,24 @@ function server() {
     logger.error(data.toString().trim())
   })
 
+  function restart() {
+    logger.info('Restarting the server...')
+    server()
+  }
+
   proc.on('exit', restart)
-}
 
-function restart() {
-  setTimeout(server, 1000)
-}
-
-app.on('before-quit', () => {
-  if (proc) {
+  app.on('before-quit', () => {
     proc.off('exit', restart)
-    proc.kill('SIGINT') // send SIGINT signal to the server, which also stops any loaded llms
-  }
-})
-
-const updateURL = `https://ollama.ai/api/update?os=${process.platform}&arch=${
-  process.arch
-}&version=${app.getVersion()}&id=${id()}`
-
-let latest = ''
-async function isNewReleaseAvailable() {
-  try {
-    const response = await fetch(updateURL)
-
-    if (!response.ok) {
-      return false
-    }
-
-    if (response.status === 204) {
-      return false
-    }
-
-    const data = await response.json()
-
-    const url = data?.url
-    if (!url) {
-      return false
-    }
-
-    if (latest === url) {
-      return false
-    }
-
-    latest = url
-
-    return true
-  } catch (error) {
-    logger.error(`update check failed - ${error}`)
-    return false
-  }
+    proc.kill()
+  })
 }
 
-async function checkUpdate() {
-  const available = await isNewReleaseAvailable()
-  if (available) {
-    logger.info('checking for update')
-    autoUpdater.checkForUpdates()
-  }
+if (process.platform === 'darwin') {
+  app.dock.hide()
 }
 
-function init() {
-  if (app.isPackaged) {
-    checkUpdate()
-    setInterval(() => {
-      checkUpdate()
-    }, 60 * 60 * 1000)
-  }
-
-  updateTray()
-
+app.on('ready', () => {
   if (process.platform === 'darwin') {
     if (app.isPackaged) {
       if (!app.isInApplicationsFolder()) {
@@ -252,13 +168,10 @@ function init() {
     }
   }
 
+  createSystemtray()
   server()
 
   if (store.get('first-time-run') && installed()) {
-    if (process.platform === 'darwin') {
-      app.dock.hide()
-    }
-
     app.setLoginItemSettings({ openAtLogin: app.getLoginItemSettings().openAtLogin })
     return
   }
@@ -266,7 +179,7 @@ function init() {
   // This is the first run or the CLI is no longer installed
   app.setLoginItemSettings({ openAtLogin: true })
   firstRunWindow()
-}
+})
 
 // Quit when all windows are closed, except on macOS. There, it's common
 // for applications and their menu bar to stay active until the user quits
@@ -277,26 +190,45 @@ app.on('window-all-closed', () => {
   }
 })
 
-function id(): string {
-  const id = store.get('id') as string
+// In this file you can include the rest of your app's specific main process
+// code. You can also put them in separate files and import them here.
+autoUpdater.setFeedURL({
+  url: `https://ollama.ai/api/update?os=${process.platform}&arch=${process.arch}&version=${app.getVersion()}`,
+})
 
-  if (id) {
-    return id
-  }
-
-  const uuid = uuidv4()
-  store.set('id', uuid)
-  return uuid
+async function heartbeat() {
+  analytics.track({
+    anonymousId: id(),
+    event: 'heartbeat',
+    properties: {
+      version: app.getVersion(),
+    },
+  })
 }
 
-autoUpdater.setFeedURL({ url: updateURL })
+if (app.isPackaged) {
+  heartbeat()
+  autoUpdater.checkForUpdates()
+  setInterval(() => {
+    heartbeat()
+    autoUpdater.checkForUpdates()
+  }, 60 * 60 * 1000)
+}
 
 autoUpdater.on('error', e => {
   logger.error(`update check failed - ${e.message}`)
-  console.error(`update check failed - ${e.message}`)
 })
 
-autoUpdater.on('update-downloaded', () => {
-  updateAvailable = true
-  updateTray()
+autoUpdater.on('update-downloaded', (event, releaseNotes, releaseName) => {
+  dialog
+    .showMessageBox({
+      type: 'info',
+      buttons: ['Restart Now', 'Later'],
+      title: 'New update available',
+      message: process.platform === 'win32' ? releaseNotes : releaseName,
+      detail: 'A new version of Ollama is available. Restart to apply the update.',
+    })
+    .then(returnValue => {
+      if (returnValue.response === 0) autoUpdater.quitAndInstall()
+    })
 })

app/src/install.ts

@@ -15,7 +15,12 @@ export function installed() {
 export async function install() {
   const command = `do shell script "mkdir -p ${path.dirname(
     symlinkPath
-  )} && ln -F -s \\"${ollama}\\" \\"${symlinkPath}\\"" with administrator privileges`
+  )} && ln -F -s ${ollama} ${symlinkPath}" with administrator privileges`
 
-  await exec(`osascript -e '${command}'`)
+  try {
+    await exec(`osascript -e '${command}'`)
+  } catch (error) {
+    console.error(`cli: failed to install cli: ${error.message}`)
+    return
+  }
 }

app/src/telemetry.ts

@@ -0,0 +1,19 @@
+import { Analytics } from '@segment/analytics-node'
+import { v4 as uuidv4 } from 'uuid'
+import Store from 'electron-store'
+
+const store = new Store()
+
+export const analytics = new Analytics({ writeKey: process.env.TELEMETRY_WRITE_KEY || '<empty>' })
+
+export function id(): string {
+  const id = store.get('id') as string
+
+  if (id) {
+    return id
+  }
+
+  const uuid = uuidv4()
+  store.set('id', uuid)
+  return uuid
+}

cmd/spinner.go

@@ -0,0 +1,44 @@
+package cmd
+
+import (
+	"fmt"
+	"os"
+	"time"
+
+	"github.com/jmorganca/ollama/progressbar"
+)
+
+type Spinner struct {
+	description string
+	*progressbar.ProgressBar
+}
+
+func NewSpinner(description string) *Spinner {
+	return &Spinner{
+		description: description,
+		ProgressBar: progressbar.NewOptions(-1,
+			progressbar.OptionSetWriter(os.Stderr),
+			progressbar.OptionThrottle(60*time.Millisecond),
+			progressbar.OptionSpinnerType(14),
+			progressbar.OptionSetRenderBlankState(true),
+			progressbar.OptionSetElapsedTime(false),
+			progressbar.OptionClearOnFinish(),
+			progressbar.OptionSetDescription(description),
+		),
+	}
+}
+
+func (s *Spinner) Spin(tick time.Duration) {
+	for range time.Tick(tick) {
+		if s.IsFinished() {
+			break
+		}
+
+		s.Add(1)
+	}
+}
+
+func (s *Spinner) Stop() {
+	s.Finish()
+	fmt.Println(s.description)
+}

docs/README.md

@@ -1,6 +0,0 @@
-# Documentation
-
-- [Modelfile](./modelfile.md)
-- [How to develop Ollama](./development.md)
-- [API](./api.md)
-- [Tutorials](./tutorials.md)

docs/api.md

@@ -1,668 +0,0 @@
-# API
-
-## Endpoints
-
-- [Generate a completion](#generate-a-completion)
-- [Create a Model](#create-a-model)
-- [List Local Models](#list-local-models)
-- [Show Model Information](#show-model-information)
-- [Copy a Model](#copy-a-model)
-- [Delete a Model](#delete-a-model)
-- [Pull a Model](#pull-a-model)
-- [Push a Model](#push-a-model)
-- [Generate Embeddings](#generate-embeddings)
-
-## Conventions
-
-### Model names
-
-Model names follow a `model:tag` format. Some examples are `orca-mini:3b-q4_1` and `llama2:70b`. The tag is optional and, if not provided, will default to `latest`. The tag is used to identify a specific version.
-
-### Durations
-
-All durations are returned in nanoseconds.
-
-### Streaming responses
-
-Certain endpoints stream responses as JSON objects delineated with the newline (`\n`) character.
-
-## Generate a completion
-
-```shell
-POST /api/generate
-```
-
-Generate a response for a given prompt with a provided model. This is a streaming endpoint, so will be a series of responses. The final response object will include statistics and additional data from the request.
-
-### Parameters
-
-- `model`: (required) the [model name](#model-names)
-- `prompt`: the prompt to generate a response for
-
-Advanced parameters (optional):
-
-- `format`: the format to return a response in. Currently the only accepted value is `json`
-- `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
-- `system`: system prompt to (overrides what is defined in the `Modelfile`)
-- `template`: the full prompt or prompt template (overrides what is defined in the `Modelfile`)
-- `context`: the context parameter returned from a previous request to `/generate`, this can be used to keep a short conversational memory
-- `stream`: if `false` the response will be returned as a single response object, rather than a stream of objects
-- `raw`: if `true` no formatting will be applied to the prompt and no context will be returned. You may choose to use the `raw` parameter if you are specifying a full templated prompt in your request to the API, and are managing history yourself.
-
-### JSON mode
-
-Enable JSON mode by setting the `format` parameter to `json`. This will structure the response as valid JSON. See the JSON mode [example](#request-json-mode) below.
-
-> Note: it's important to instruct the model to use JSON in the `prompt`. Otherwise, the model may generate large amounts whitespace.
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/generate -d '{
-  "model": "llama2",
-  "prompt": "Why is the sky blue?"
-}'
-```
-
-#### Response
-
-A stream of JSON objects is returned:
-
-```json
-{
-  "model": "llama2",
-  "created_at": "2023-08-04T08:52:19.385406455-07:00",
-  "response": "The",
-  "done": false
-}
-```
-
-The final response in the stream also includes additional data about the generation:
-
-- `total_duration`: time spent generating the response
-- `load_duration`: time spent in nanoseconds loading the model
-- `sample_count`: number of samples generated
-- `sample_duration`: time spent generating samples
-- `prompt_eval_count`: number of tokens in the prompt
-- `prompt_eval_duration`: time spent in nanoseconds evaluating the prompt
-- `eval_count`: number of tokens the response
-- `eval_duration`: time in nanoseconds spent generating the response
-- `context`: an encoding of the conversation used in this response, this can be sent in the next request to keep a conversational memory
-- `response`: empty if the response was streamed, if not streamed, this will contain the full response
-
-To calculate how fast the response is generated in tokens per second (token/s), divide `eval_count` / `eval_duration`.
-
-```json
-{
-  "model": "llama2",
-  "created_at": "2023-08-04T19:22:45.499127Z",
-  "response": "",
-  "context": [1, 2, 3],
-  "done": true,
-  "total_duration": 5589157167,
-  "load_duration": 3013701500,
-  "sample_count": 114,
-  "sample_duration": 81442000,
-  "prompt_eval_count": 46,
-  "prompt_eval_duration": 1160282000,
-  "eval_count": 113,
-  "eval_duration": 1325948000
-}
-```
-
-#### Request (No streaming)
-
-```shell
-curl http://localhost:11434/api/generate -d '{
-  "model": "llama2",
-  "prompt": "Why is the sky blue?",
-  "stream": false
-}'
-```
-
-#### Response
-
-If `stream` is set to `false`, the response will be a single JSON object:
-
-```json
-{
-  "model": "llama2",
-  "created_at": "2023-08-04T19:22:45.499127Z",
-  "response": "The sky is blue because it is the color of the sky.",
-  "context": [1, 2, 3],
-  "done": true,
-  "total_duration": 5589157167,
-  "load_duration": 3013701500,
-  "sample_count": 114,
-  "sample_duration": 81442000,
-  "prompt_eval_count": 46,
-  "prompt_eval_duration": 1160282000,
-  "eval_count": 13,
-  "eval_duration": 1325948000
-}
-```
-
-#### Request (Raw mode)
-
-In some cases you may wish to bypass the templating system and provide a full prompt. In this case, you can use the `raw` parameter to disable formatting and context.
-
-```shell
-curl http://localhost:11434/api/generate -d '{
-  "model": "mistral",
-  "prompt": "[INST] why is the sky blue? [/INST]",
-  "raw": true,
-  "stream": false
-}'
-```
-
-#### Response
-
-```json
-{
-  "model": "mistral",
-  "created_at": "2023-11-03T15:36:02.583064Z",
-  "response": " The sky appears blue because of a phenomenon called Rayleigh scattering.",
-  "done": true,
-  "total_duration": 14648695333,
-  "load_duration": 3302671417,
-  "prompt_eval_count": 14,
-  "prompt_eval_duration": 286243000,
-  "eval_count": 129,
-  "eval_duration": 10931424000
-}
-```
-
-#### Request (JSON mode)
-
-```shell
-curl http://localhost:11434/api/generate -d '{
-  "model": "llama2",
-  "prompt": "What color is the sky at different times of the day? Respond using JSON",
-  "format": "json",
-  "stream": false
-}'
-```
-
-#### Response
-
-```json
-{
-  "model": "llama2",
-  "created_at": "2023-11-09T21:07:55.186497Z",
-  "response": "{\n\"morning\": {\n\"color\": \"blue\"\n},\n\"noon\": {\n\"color\": \"blue-gray\"\n},\n\"afternoon\": {\n\"color\": \"warm gray\"\n},\n\"evening\": {\n\"color\": \"orange\"\n}\n}\n",
-  "done": true,
-  "total_duration": 4661289125,
-  "load_duration": 1714434500,
-  "prompt_eval_count": 36,
-  "prompt_eval_duration": 264132000,
-  "eval_count": 75,
-  "eval_duration": 2112149000
-}
-```
-
-The value of `response` will be a string containing JSON similar to:
-
-```json
-{
-  "morning": {
-    "color": "blue"
-  },
-  "noon": {
-    "color": "blue-gray"
-  },
-  "afternoon": {
-    "color": "warm gray"
-  },
-  "evening": {
-    "color": "orange"
-  }
-}
-```
-
-#### Request (With options)
-
-If you want to set custom options for the model at runtime rather than in the Modelfile, you can do so with the `options` parameter. This example sets every available option, but you can set any of them individually and omit the ones you do not want to override.
-
-```shell
-curl http://localhost:11434/api/generate -d '{
-  "model": "llama2",
-  "prompt": "Why is the sky blue?",
-  "stream": false,
-  "options": {
-    "num_keep": 5,
-    "seed": 42,
-    "num_predict": 100,
-    "top_k": 20,
-    "top_p": 0.9,
-    "tfs_z": 0.5,
-    "typical_p": 0.7,
-    "repeat_last_n": 33,
-    "temperature": 0.8,
-    "repeat_penalty": 1.2,
-    "presence_penalty": 1.5,
-    "frequency_penalty": 1.0,
-    "mirostat": 1,
-    "mirostat_tau": 0.8,
-    "mirostat_eta": 0.6,
-    "penalize_newline": true,
-    "stop": ["\n", "user:"],
-    "numa": false,
-    "num_ctx": 4,
-    "num_batch": 2,
-    "num_gqa": 1,
-    "num_gpu": 1,
-    "main_gpu": 0,
-    "low_vram": false,
-    "f16_kv": true,
-    "logits_all": false,
-    "vocab_only": false,
-    "use_mmap": true,
-    "use_mlock": false,
-    "embedding_only": false,
-    "rope_frequency_base": 1.1,
-    "rope_frequency_scale": 0.8,
-    "num_thread": 8
-    }
-}'
-```
-
-#### Response
-
-```json
-{
-  "model": "llama2",
-  "created_at": "2023-08-04T19:22:45.499127Z",
-  "response": "The sky is blue because it is the color of the sky.",
-  "context": [1, 2, 3],
-  "done": true,
-  "total_duration": 5589157167,
-  "load_duration": 3013701500,
-  "sample_count": 114,
-  "sample_duration": 81442000,
-  "prompt_eval_count": 46,
-  "prompt_eval_duration": 1160282000,
-  "eval_count": 13,
-  "eval_duration": 1325948000
-}
-```
-
-## Create a Model
-
-```shell
-POST /api/create
-```
-
-Create a model from a [`Modelfile`](./modelfile.md). It is recommended to set `modelfile` to the content of the Modelfile rather than just set `path`. This is a requirement for remote create. Remote model creation should also create any file blobs, fields such as `FROM` and `ADAPTER`, explicitly with the server using [Create a Blob](#create-a-blob) and the value to the path indicated in the response.
-
-### Parameters
-
-- `name`: name of the model to create
-- `modelfile`: contents of the Modelfile
-- `stream`: (optional) if `false` the response will be returned as a single response object, rather than a stream of objects
-- `path` (deprecated): path to the Modelfile
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/create -d '{
-  "name": "mario",
-  "modelfile": "FROM llama2\nSYSTEM You are mario from Super Mario Bros."
-}'
-```
-
-#### Response
-
-A stream of JSON objects. When finished, `status` is `success`.
-
-```json
-{
-  "status": "parsing modelfile"
-}
-```
-
-### Check if a Blob Exists
-
-```shell
-HEAD /api/blobs/:digest
-```
-
-Check if a blob is known to the server.
-
-#### Query Parameters
-
-- `digest`: the SHA256 digest of the blob
-
-#### Examples
-
-##### Request
-
-```shell
-curl -I http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2
-```
-
-##### Response
-
-Return 200 OK if the blob exists, 404 Not Found if it does not.
-
-### Create a Blob
-
-```shell
-POST /api/blobs/:digest
-```
-
-Create a blob from a file. Returns the server file path.
-
-#### Query Parameters
-
-- `digest`: the expected SHA256 digest of the file
-
-#### Examples
-
-##### Request
-
-```shell
-curl -T model.bin -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2
-```
-
-##### Response
-
-Return 201 Created if the blob was successfully created.
-
-## List Local Models
-
-```shell
-GET /api/tags
-```
-
-List models that are available locally.
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/tags
-```
-
-#### Response
-
-A single JSON object will be returned.
-
-```json
-{
-  "models": [
-    {
-      "name": "llama2",
-      "modified_at": "2023-08-02T17:02:23.713454393-07:00",
-      "size": 3791730596
-    },
-    {
-      "name": "llama2:13b",
-      "modified_at": "2023-08-08T12:08:38.093596297-07:00",
-      "size": 7323310500
-    }
-  ]
-}
-```
-
-## Show Model Information
-
-```shell
-POST /api/show
-```
-
-Show details about a model including modelfile, template, parameters, license, and system prompt.
-
-### Parameters
-
-- `name`: name of the model to show
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/show -d '{
-  "name": "llama2"
-}'
-```
-
-#### Response
-
-```json
-{
-  "license": "<contents of license block>",
-  "modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llama2:latest\n\nFROM /Users/username/.ollama/models/blobs/sha256:8daa9615cce30c259a9555b1cc250d461d1bc69980a274b44d7eda0be78076d8\nTEMPLATE \"\"\"[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>\n\n{{ end }}{{ .Prompt }} [/INST] \"\"\"\nSYSTEM \"\"\"\"\"\"\nPARAMETER stop [INST]\nPARAMETER stop [/INST]\nPARAMETER stop <<SYS>>\nPARAMETER stop <</SYS>>\n",
-  "parameters": "stop                           [INST]\nstop                           [/INST]\nstop                           <<SYS>>\nstop                           <</SYS>>",
-  "template": "[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>\n\n{{ end }}{{ .Prompt }} [/INST] "
-}
-```
-
-## Copy a Model
-
-```shell
-POST /api/copy
-```
-
-Copy a model. Creates a model with another name from an existing model.
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/copy -d '{
-  "source": "llama2",
-  "destination": "llama2-backup"
-}'
-```
-
-#### Response
-
-The only response is a 200 OK if successful.
-
-## Delete a Model
-
-```shell
-DELETE /api/delete
-```
-
-Delete a model and its data.
-
-### Parameters
-
-- `name`: model name to delete
-
-### Examples
-
-#### Request
-
-```shell
-curl -X DELETE http://localhost:11434/api/delete -d '{
-  "name": "llama2:13b"
-}'
-```
-
-#### Response
-
-If successful, the only response is a 200 OK.
-
-## Pull a Model
-
-```shell
-POST /api/pull
-```
-
-Download a model from the ollama library. Cancelled pulls are resumed from where they left off, and multiple calls will share the same download progress.
-
-### Parameters
-
-- `name`: name of the model to pull
-- `insecure`: (optional) allow insecure connections to the library. Only use this if you are pulling from your own library during development.
-- `stream`: (optional) if `false` the response will be returned as a single response object, rather than a stream of objects
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/pull -d '{
-  "name": "llama2"
-}'
-```
-
-#### Response
-
-If `stream` is not specified, or set to `true`, a stream of JSON objects is returned:
-
-The first object is the manifest:
-
-```json
-{
-  "status": "pulling manifest"
-}
-```
-
-Then there is a series of downloading responses. Until any of the download is completed, the `completed` key may not be included. The number of files to be downloaded depends on the number of layers specified in the manifest.
-
-```json
-{
-  "status": "downloading digestname",
-  "digest": "digestname",
-  "total": 2142590208,
-  "completed": 241970
-}
-```
-
-After all the files are downloaded, the final responses are:
-
-```json
-{
-    "status": "verifying sha256 digest"
-}
-{
-    "status": "writing manifest"
-}
-{
-    "status": "removing any unused layers"
-}
-{
-    "status": "success"
-}
-```
-
-if `stream` is set to false, then the response is a single JSON object:
-
-```json
-{
-  "status": "success"
-}
-```
-
-## Push a Model
-
-```shell
-POST /api/push
-```
-
-Upload a model to a model library. Requires registering for ollama.ai and adding a public key first.
-
-### Parameters
-
-- `name`: name of the model to push in the form of `<namespace>/<model>:<tag>`
-- `insecure`: (optional) allow insecure connections to the library. Only use this if you are pushing to your library during development.
-- `stream`: (optional) if `false` the response will be returned as a single response object, rather than a stream of objects
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/push -d '{
-  "name": "mattw/pygmalion:latest"
-}'
-```
-
-#### Response
-
-If `stream` is not specified, or set to `true`, a stream of JSON objects is returned:
-
-```json
-{ "status": "retrieving manifest" }
-```
-
-and then:
-
-```json
-{
-  "status": "starting upload",
-  "digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
-  "total": 1928429856
-}
-```
-
-Then there is a series of uploading responses:
-
-```json
-{
-  "status": "starting upload",
-  "digest": "sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711ab",
-  "total": 1928429856
-}
-```
-
-Finally, when the upload is complete:
-
-```json
-{"status":"pushing manifest"}
-{"status":"success"}
-```
-
-If `stream` is set to `false`, then the response is a single JSON object:
-
-```json
-{ "status": "success" }
-```
-
-## Generate Embeddings
-
-```shell
-POST /api/embeddings
-```
-
-Generate embeddings from a model
-
-### Parameters
-
-- `model`: name of model to generate embeddings from
-- `prompt`: text to generate embeddings for
-
-Advanced parameters:
-
-- `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
-
-### Examples
-
-#### Request
-
-```shell
-curl http://localhost:11434/api/embeddings -d '{
-  "model": "llama2",
-  "prompt": "Here is an article about llamas..."
-}'
-```
-
-#### Response
-
-```json
-{
-  "embedding": [
-    0.5670403838157654, 0.009260174818336964, 0.23178744316101074, -0.2916173040866852, -0.8924556970596313,
-    0.8785552978515625, -0.34576427936553955, 0.5742510557174683, -0.04222835972905159, -0.137906014919281
-  ]
-}
-```

docs/development.md

@@ -1,39 +1,46 @@
 # Development
 
-- Install cmake or (optionally, required tools for GPUs)
-- run `go generate ./...`
-- run `go build .`
-
 Install required tools:
 
-- cmake version 3.24 or higher
-- go version 1.20 or higher
-- gcc version 11.4.0 or higher
-
-```bash
-brew install go cmake gcc
+```
+brew install go
 ```
 
-Get the required libraries:
+Enable CGO:
 
-```bash
-go generate ./...
+```
+export CGO_ENABLED=1
 ```
 
 Then build ollama:
 
-```bash
+```
 go build .
 ```
 
 Now you can run `ollama`:
 
-```bash
+```
 ./ollama
 ```
 
-## Building on Linux with GPU support
+## Releasing
+
+To release a new version of Ollama you'll need to set some environment variables:
+
+* `GITHUB_TOKEN`: your GitHub token
+* `APPLE_IDENTITY`: the Apple signing identity (macOS only)
+* `APPLE_ID`: your Apple ID
+* `APPLE_PASSWORD`: your Apple ID app-specific password
+* `APPLE_TEAM_ID`: the Apple team ID for the signing identity
+* `TELEMETRY_WRITE_KEY`: segment write key for telemetry
+
+Then run the publish script with the target version:
+
+```
+VERSION=0.0.2 ./scripts/publish.sh
+```
+
+
+
 
-- Install cmake and nvidia-cuda-toolkit
-- run `go generate ./...`
-- run `go build .`

docs/faq.md

@@ -1,156 +0,0 @@
-# FAQ
-
-## How can I view the logs?
-
-On macOS:
-
-```
-cat ~/.ollama/logs/server.log
-```
-
-On Linux:
-
-```
-journalctl -u ollama
-```
-
-If you're running `ollama serve` directly, the logs will be printed to the console.
-
-## How can I expose Ollama on my network?
-
-Ollama binds to 127.0.0.1 port 11434 by default. Change the bind address with the `OLLAMA_HOST` environment variable.
-
-On macOS:
-
-```bash
-OLLAMA_HOST=0.0.0.0:11435 ollama serve
-```
-
-On Linux:
-
-Create a `systemd` drop-in directory and set `Environment=OLLAMA_HOST`
-
-```bash
-mkdir -p /etc/systemd/system/ollama.service.d
-echo '[Service]' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-```bash
-echo 'Environment="OLLAMA_HOST=0.0.0.0:11434"' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-Reload `systemd` and restart Ollama:
-
-```bash
-systemctl daemon-reload
-systemctl restart ollama
-```
-
-## How can I allow additional web origins to access Ollama?
-
-Ollama allows cross origin requests from `127.0.0.1` and `0.0.0.0` by default. Add additional origins with the `OLLAMA_ORIGINS` environment variable:
-
-On macOS:
-
-```bash
-OLLAMA_ORIGINS=http://192.168.1.1:*,https://example.com ollama serve
-```
-
-On Linux:
-
-```bash
-echo 'Environment="OLLAMA_ORIGINS=http://129.168.1.1:*,https://example.com"' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-Reload `systemd` and restart Ollama:
-
-```bash
-systemctl daemon-reload
-systemctl restart ollama
-```
-
-## Where are models stored?
-
-- macOS: Raw model data is stored under `~/.ollama/models`.
-- Linux: Raw model data is stored under `/usr/share/ollama/.ollama/models`
-
-Below the models directory you will find a structure similar to the following:
-
-```shell
-.
-├── blobs
-└── manifests
-   └── registry.ollama.ai
-      ├── f0rodo
-      ├── library
-      ├── mattw
-      └── saikatkumardey
-```
-
-There is a `manifests/registry.ollama.ai/namespace` path. In example above, the user has downloaded models from the official `library`, `f0rodo`, `mattw`, and `saikatkumardey` namespaces. Within each of those directories, you will find directories for each of the models downloaded. And in there you will find a file name representing each tag. Each tag file is the manifest for the model.  
-
-The manifest lists all the layers used in this model. You will see a `media type` for each layer, along with a digest. That digest corresponds with a file in the `models/blobs directory`.
-
-### How can I change where Ollama stores models?
-
-To modify where models are stored, you can use the `OLLAMA_MODELS` environment variable. Note that on Linux this means defining `OLLAMA_MODELS` in a drop-in `/etc/systemd/system/ollama.service.d` service file, reloading systemd, and restarting the ollama service.
-
-## Does Ollama send my prompts and answers back to Ollama.ai to use in any way?
-
-No. Anything you do with Ollama, such as generate a response from the model, stays with you. We don't collect any data about how you use the model. You are always in control of your own data.
-
-## How can I use Ollama in Visual Studio Code?
-
-There is already a large collection of plugins available for VSCode as well as other editors that leverage Ollama. You can see the list of [extensions & plugins](https://github.com/jmorganca/ollama#extensions--plugins) at the bottom of the main repository readme.
-
-## How do I use Ollama behind a proxy?
-
-Ollama is compatible with proxy servers if `HTTP_PROXY` or `HTTPS_PROXY` are configured. When using either variables, ensure it is set where `ollama serve` can access the values.
-
-When using `HTTPS_PROXY`, ensure the proxy certificate is installed as a system certificate.
-
-On macOS:
-
-```bash
-HTTPS_PROXY=http://proxy.example.com ollama serve
-```
-
-On Linux:
-
-```bash
-echo 'Environment="HTTPS_PROXY=https://proxy.example.com"' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-Reload `systemd` and restart Ollama:
-
-```bash
-systemctl daemon-reload
-systemctl restart ollama
-```
-
-### How do I use Ollama behind a proxy in Docker?
-
-The Ollama Docker container image can be configured to use a proxy by passing `-e HTTPS_PROXY=https://proxy.example.com` when starting the container.
-
-Alternatively, Docker daemon can be configured to use a proxy. Instructions are available for Docker Desktop on [macOS](https://docs.docker.com/desktop/settings/mac/#proxies), [Windows](https://docs.docker.com/desktop/settings/windows/#proxies), and [Linux](https://docs.docker.com/desktop/settings/linux/#proxies), and Docker [daemon with systemd](https://docs.docker.com/config/daemon/systemd/#httphttps-proxy).
-
-Ensure the certificate is installed as a system certificate when using HTTPS. This may require a new Docker image when using a self-signed certificate.
-
-```dockerfile
-FROM ollama/ollama
-COPY my-ca.pem /usr/local/share/ca-certificates/my-ca.crt
-RUN update-ca-certificate
-```
-
-Build and run this image:
-
-```shell
-docker build -t ollama-with-ca .
-docker run -d -e HTTPS_PROXY=https://my.proxy.example.com -p 11434:11434 ollama-with-ca
-```
-
-## How do I use Ollama with GPU acceleration in Docker?
-
-The Ollama Docker container can be configured with GPU acceleration in Linux or Windows (with WSL2). This requires the [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia-container-toolkit). See [ollama/ollama](https://hub.docker.com/r/ollama/ollama) for more details.
-
-GPU acceleration is not available for Docker Desktop in macOS due to the lack of GPU passthrough and emulation.

docs/import.md

@@ -1,198 +0,0 @@
-# Import a model
-
-This guide walks through importing a GGUF, PyTorch or Safetensors model.
-
-## Importing (GGUF)
-
-### Step 1: Write a `Modelfile`
-
-Start by creating a `Modelfile`. This file is the blueprint for your model, specifying weights, parameters, prompt templates and more.
-
-```
-FROM ./mistral-7b-v0.1.Q4_0.gguf
-```
-
-(Optional) many chat models require a prompt template in order to answer correctly. A default prompt template can be specified with the `TEMPLATE` instruction in the `Modelfile`:
-
-```
-FROM ./q4_0.bin
-TEMPLATE "[INST] {{ .Prompt }} [/INST]"
-```
-
-### Step 2: Create the Ollama model
-
-Finally, create a model from your `Modelfile`:
-
-```
-ollama create example -f Modelfile
-```
-
-### Step 3: Run your model
-
-Next, test the model with `ollama run`:
-
-```
-ollama run example "What is your favourite condiment?"
-```
-
-## Importing (PyTorch & Safetensors)
-
-### Supported models
-
-Ollama supports a set of model architectures, with support for more coming soon:
-
-- Llama & Mistral
-- Falcon & RW
-- GPT-NeoX
-- BigCode
-
-To view a model's architecture, check the `config.json` file in its HuggingFace repo. You should see an entry under `architectures` (e.g. `LlamaForCausalLM`).
-
-### Step 1: Clone the HuggingFace repository (optional)
-
-If the model is currently hosted in a HuggingFace repository, first clone that repository to download the raw model.
-
-```
-git lfs install
-git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
-cd Mistral-7B-Instruct-v0.1
-```
-
-### Step 2: Convert and quantize to a `.bin` file (optional, for PyTorch and Safetensors)
-
-If the model is in PyTorch or Safetensors format, a [Docker image](https://hub.docker.com/r/ollama/quantize) with the tooling required to convert and quantize models is available.
-
-First, Install [Docker](https://www.docker.com/get-started/).
-
-Next, to convert and quantize your model, run:
-
-```
-docker run --rm -v .:/model ollama/quantize -q q4_0 /model
-```
-
-This will output two files into the directory:
-
-- `f16.bin`: the model converted to GGUF
-- `q4_0.bin` the model quantized to a 4-bit quantization (we will use this file to create the Ollama model)
-
-### Step 3: Write a `Modelfile`
-
-Next, create a `Modelfile` for your model:
-
-```
-FROM ./q4_0.bin
-```
-
-(Optional) many chat models require a prompt template in order to answer correctly. A default prompt template can be specified with the `TEMPLATE` instruction in the `Modelfile`:
-
-```
-FROM ./q4_0.bin
-TEMPLATE "[INST] {{ .Prompt }} [/INST]"
-```
-
-### Step 4: Create the Ollama model
-
-Finally, create a model from your `Modelfile`:
-
-```
-ollama create example -f Modelfile
-```
-
-### Step 5: Run your model
-
-Next, test the model with `ollama run`:
-
-```
-ollama run example "What is your favourite condiment?"
-```
-
-## Publishing your model (optional – early alpha)
-
-Publishing models is in early alpha. If you'd like to publish your model to share with others, follow these steps:
-
-1. Create [an account](https://ollama.ai/signup)
-2. Run `cat ~/.ollama/id_ed25519.pub` to view your Ollama public key. Copy this to the clipboard.
-3. Add your public key to your [Ollama account](https://ollama.ai/settings/keys)
-
-Next, copy your model to your username's namespace:
-
-```
-ollama cp example <your username>/example
-```
-
-Then push the model:
-
-```
-ollama push <your username>/example
-```
-
-After publishing, your model will be available at `https://ollama.ai/<your username>/example`.
-
-## Quantization reference
-
-The quantization options are as follow (from highest highest to lowest levels of quantization). Note: some architectures such as Falcon do not support K quants.
-
-- `q2_K`
-- `q3_K`
-- `q3_K_S`
-- `q3_K_M`
-- `q3_K_L`
-- `q4_0` (recommended)
-- `q4_1`
-- `q4_K`
-- `q4_K_S`
-- `q4_K_M`
-- `q5_0`
-- `q5_1`
-- `q5_K`
-- `q5_K_S`
-- `q5_K_M`
-- `q6_K`
-- `q8_0`
-
-## Manually converting & quantizing models
-
-### Prerequisites
-
-Start by cloning the `llama.cpp` repo to your machine in another directory:
-
-```
-git clone https://github.com/ggerganov/llama.cpp.git
-cd llama.cpp
-```
-
-Next, install the Python dependencies:
-
-```
-pip install -r requirements.txt
-```
-
-Finally, build the `quantize` tool:
-
-```
-make quantize
-```
-
-### Convert the model
-
-Run the correct conversion script for your model architecture:
-
-```shell
-# LlamaForCausalLM or MistralForCausalLM
-python convert.py <path to model directory>
-
-# FalconForCausalLM
-python convert-falcon-hf-to-gguf.py <path to model directory>
-
-# GPTNeoXForCausalLM
-python convert-gptneox-hf-to-gguf.py <path to model directory>
-
-# GPTBigCodeForCausalLM
-python convert-starcoder-hf-to-gguf.py <path to model directory>
-```
-
-### Quantize the model
-
-```
-quantize <path to model dir>/ggml-model-f32.bin <path to model dir>/q4_0.bin q4_0
-```

docs/linux.md

@@ -1,116 +0,0 @@
-# Ollama on Linux
-
-## Install
-
-Install Ollama running this one-liner:
->
-```bash
-curl https://ollama.ai/install.sh | sh
-```
-
-## Manual install
-
-### Download the `ollama` binary
-
-Ollama is distributed as a self-contained binary. Download it to a directory in your PATH:
-
-```bash
-sudo curl -L https://ollama.ai/download/ollama-linux-amd64 -o /usr/bin/ollama
-sudo chmod +x /usr/bin/ollama
-```
-
-### Adding Ollama as a startup service (recommended)
-
-Create a user for Ollama:
-
-```bash
-sudo useradd -r -s /bin/false -m -d /usr/share/ollama ollama
-```
-
-Create a service file in `/etc/systemd/system/ollama.service`:
-
-```ini
-[Unit]
-Description=Ollama Service
-After=network-online.target
-
-[Service]
-ExecStart=/usr/bin/ollama serve
-User=ollama
-Group=ollama
-Restart=always
-RestartSec=3
-
-[Install]
-WantedBy=default.target
-```
-
-Then start the service:
-
-```bash
-sudo systemctl daemon-reload
-sudo systemctl enable ollama
-```
-
-### Install CUDA drivers (optional – for Nvidia GPUs)
-
-[Download and install](https://developer.nvidia.com/cuda-downloads) CUDA.
-
-Verify that the drivers are installed by running the following command, which should print details about your GPU:
-
-```bash
-nvidia-smi
-```
-
-### Start Ollama
-
-Start Ollama using `systemd`:
-
-```bash
-sudo systemctl start ollama
-```
-
-## Update
-
-Update ollama by running the install script again:
-
-```bash
-curl https://ollama.ai/install.sh | sh
-```
-
-Or by downloading the ollama binary:
-
-```bash
-sudo curl -L https://ollama.ai/download/ollama-linux-amd64 -o /usr/bin/ollama
-sudo chmod +x /usr/bin/ollama
-```
-
-## Viewing logs
-
-To view logs of Ollama running as a startup service, run:
-
-```bash
-journalctl -u ollama
-```
-
-## Uninstall
-
-Remove the ollama service:
-
-```bash
-sudo systemctl stop ollama
-sudo systemctl disable ollama
-sudo rm /etc/systemd/system/ollama.service
-```
-
-Remove the ollama binary from your bin directory (either `/usr/local/bin`, `/usr/bin`, or `/bin`):
-
-```bash
-sudo rm $(which ollama)
-```
-
-Remove the downloaded models and Ollama service user:
-```bash
-sudo rm -r /usr/share/ollama
-sudo userdel ollama
-```

docs/modelfile.md

@@ -1,212 +1,105 @@
 # Ollama Model File
 
-> Note: this `Modelfile` syntax is in development
+> Note: this model file syntax is in development
 
 A model file is the blueprint to create and share models with Ollama.
 
-## Table of Contents
-
-- [Format](#format)
-- [Examples](#examples)
-- [Instructions](#instructions)
-  - [FROM (Required)](#from-required)
-    - [Build from llama2](#build-from-llama2)
-    - [Build from a bin file](#build-from-a-bin-file)
-  - [PARAMETER](#parameter)
-    - [Valid Parameters and Values](#valid-parameters-and-values)
-  - [TEMPLATE](#template)
-    - [Template Variables](#template-variables)
-  - [SYSTEM](#system)
-  - [ADAPTER](#adapter)
-  - [LICENSE](#license)
-- [Notes](#notes)
-
 ## Format
 
-The format of the `Modelfile`:
+The format of the Modelfile:
 
 ```modelfile
 # comment
 INSTRUCTION arguments
 ```
 
-| Instruction                         | Description                                                   |
-| ----------------------------------- | ------------------------------------------------------------- |
-| [`FROM`](#from-required) (required) | Defines the base model to use.                                |
-| [`PARAMETER`](#parameter)           | Sets the parameters for how Ollama will run the model.        |
-| [`TEMPLATE`](#template)             | The full prompt template to be sent to the model.             |
-| [`SYSTEM`](#system)                 | Specifies the system prompt that will be set in the template. |
-| [`ADAPTER`](#adapter)               | Defines the (Q)LoRA adapters to apply to the model.           |
-| [`LICENSE`](#license)               | Specifies the legal license.                                  |
+| Instruction       | Description                                           |
+| ----------------- | ----------------------------------------------------- |
+| `FROM` (required) | Defines the base model to use                         |
+| `PARAMETER`       | Sets the parameters for how Ollama will run the model |
+| `SYSTEM`          | Specifies the system prompt that will set the context |
+| `TEMPLATE`        | The full prompt template to be sent to the model      |
+| `LICENSE`         | Specifies the legal license                           |
 
 ## Examples
 
-### Basic `Modelfile`
+An example of a model file creating a mario blueprint:
 
-An example of a `Modelfile` creating a mario blueprint:
-
-```modelfile
+```
 FROM llama2
 # sets the temperature to 1 [higher is more creative, lower is more coherent]
+# sets the context size to 4096
 PARAMETER temperature 1
-# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
 PARAMETER num_ctx 4096
 
-# sets a custom system prompt to specify the behavior of the chat assistant
+# Overriding the system prompt
 SYSTEM You are Mario from super mario bros, acting as an assistant.
 ```
 
 To use this:
 
-1. Save it as a file (e.g. `Modelfile`)
-2. `ollama create choose-a-model-name -f <location of the file e.g. ./Modelfile>'`
-3. `ollama run choose-a-model-name`
+1. Save it as a file (eg. `Modelfile``)
+2. `ollama create NAME -f <location of the file eg. ./Modelfile>'`
+3. `ollama run NAME`
 4. Start using the model!
 
-More examples are available in the [examples directory](../examples).
+## FROM (Required)
 
-### `Modelfile`s in [ollama.ai/library][1]
+The FROM instruction defines the base model to use when creating a model.
 
-There are two ways to view `Modelfile`s underlying the models in [ollama.ai/library][1]:
-
-- Option 1: view a details page from a model's tags page:
-   1. Go to a particular model's tags (e.g. https://ollama.ai/library/llama2/tags)
-   2. Click on a tag (e.g. https://ollama.ai/library/llama2:13b)
-   3. Scroll down to "Layers"
-      - Note: if the [`FROM` instruction](#from-required) is not present,
-        it means the model was created from a local file
-- Option 2: use `ollama show` to print the `Modelfile` like so:
-
-  ```bash
-  > ollama show --modelfile llama2:13b
-  # Modelfile generated by "ollama show"
-  # To build a new Modelfile based on this one, replace the FROM line with:
-  # FROM llama2:13b
-
-  FROM /root/.ollama/models/blobs/sha256:123abc
-  TEMPLATE """[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>
-
-  {{ end }}{{ .Prompt }} [/INST] """
-  SYSTEM """"""
-  PARAMETER stop [INST]
-  PARAMETER stop [/INST]
-  PARAMETER stop <<SYS>>
-  PARAMETER stop <</SYS>>
-  ```
-
-## Instructions
-
-### FROM (Required)
-
-The `FROM` instruction defines the base model to use when creating a model.
-
-```modelfile
+```
 FROM <model name>:<tag>
 ```
 
-#### Build from llama2
+### Build from llama2
 
-```modelfile
+```
 FROM llama2
 ```
 
 A list of available base models:
 <https://github.com/jmorganca/ollama#model-library>
 
-#### Build from a `bin` file
+### Build from a bin file
 
-```modelfile
+```
 FROM ./ollama-model.bin
 ```
 
-This bin file location should be specified as an absolute path or relative to the `Modelfile` location.
-
-### PARAMETER
+## PARAMETER (Optional)
 
 The `PARAMETER` instruction defines a parameter that can be set when the model is run.
 
-```modelfile
+```
 PARAMETER <parameter> <parametervalue>
 ```
 
 ### Valid Parameters and Values
 
-| Parameter      | Description                                                                                                                                                                                                                                             | Value Type | Example Usage        |
-| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------------- |
-| mirostat       | Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)                                                                                                                                         | int        | mirostat 0           |
-| mirostat_eta   | Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)                        | float      | mirostat_eta 0.1     |
-| mirostat_tau   | Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)                                                                                                         | float      | mirostat_tau 5.0     |
-| num_ctx        | Sets the size of the context window used to generate the next token. (Default: 2048)                                                                                                                                                                    | int        | num_ctx 4096         |
-| num_gqa        | The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for llama2:70b                                                                                                                                         | int        | num_gqa 1            |
-| num_gpu        | The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.                                                                                                                                            | int        | num_gpu 50           |
-| num_thread     | Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores). | int        | num_thread 8         |
-| repeat_last_n  | Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)                                                                                                                                           | int        | repeat_last_n 64     |
-| repeat_penalty | Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)                                                                     | float      | repeat_penalty 1.1   |
-| temperature    | The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)                                                                                                                                     | float      | temperature 0.7      |
-| seed           | Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)                                                                                       | int        | seed 42              |
-| stop           | Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate `stop` parameters in a modelfile.                                      | string     | stop "AI assistant:" |
-| tfs_z          | Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)                                               | float      | tfs_z 1              |
-| num_predict    | Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)                                                                                                                                   | int        | num_predict 42       |
-| top_k          | Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)                                                                        | int        | top_k 40             |
-| top_p          | Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)                                                                 | float      | top_p 0.9            |
+| Parameter      | Description                                                                                                                                                                                                                                             | Value Type | Example Usage      |
+| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ------------------ |
+| num_ctx        | Sets the size of the prompt context size length model. (Default: 2048)                                                                                                                                                                                  | int        | num_ctx 4096       |
+| temperature    | The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)                                                                                                                                     | float      | temperature 0.7    |
+| top_k          | Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)                                                                        | int        | top_k 40           |
+| top_p          | Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)                                                                 | float      | top_p 0.9          |
+| num_gpu        | The number of GPUs to use. On macOS it defaults to 1 to enable metal support, 0 to disable.                                                                                                                                                             | int        | num_gpu 1          |
+| repeat_last_n  | Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = ctx-size)                                                                                                                                          | int        | repeat_last_n 64   |
+| repeat_penalty | Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)                                                                     | float      | repeat_penalty 1.1 |
+| tfs_z          | Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)                                               | float      | tfs_z 1            |
+| mirostat       | Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)                                                                                                                                         | int        | mirostat 0         |
+| mirostat_tau   | Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)                                                                                                         | float      | mirostat_tau 5.0   |
+| mirostat_eta   | Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)                        | float      | mirostat_eta 0.1   |
+| num_thread     | Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores). | int        | num_thread 8       |
 
-### TEMPLATE
+## Prompt
 
-`TEMPLATE` of the full prompt template to be passed into the model. It may include (optionally) a system prompt and a user's prompt. This is used to create a full custom prompt, and syntax may be model specific. You can usually find the template for a given model in the readme for that model.
+When building on top of the base models supplied by Ollama, it comes with the prompt template predefined. To override the supplied system prompt, simply add `SYSTEM insert system prompt` to change the system prompt.
 
-#### Template Variables
+### Prompt Template
 
-| Variable        | Description                                                                                                  |
-| --------------- | ------------------------------------------------------------------------------------------------------------ |
-| `{{ .System }}` | The system prompt used to specify custom behavior, this must also be set in the Modelfile as an instruction. |
-| `{{ .Prompt }}` | The incoming prompt, this is not specified in the model file and will be set based on input.                 |
-| `{{ .First }}`  | A boolean value used to render specific template information for the first generation of a session.          |
-
-```modelfile
-TEMPLATE """
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
-
-### User:
-{{ .Prompt }}
-
-### Response:
-"""
-
-SYSTEM """<system message>"""
-```
-
-### SYSTEM
-
-The `SYSTEM` instruction specifies the system prompt to be used in the template, if applicable.
-
-```modelfile
-SYSTEM """<system message>"""
-```
-
-### ADAPTER
-
-The `ADAPTER` instruction specifies the LoRA adapter to apply to the base model. The value of this instruction should be an absolute path or a path relative to the Modelfile and the file must be in a GGML file format. The adapter should be tuned from the base model otherwise the behaviour is undefined.
-
-```modelfile
-ADAPTER ./ollama-lora.bin
-```
-
-### LICENSE
-
-The `LICENSE` instruction allows you to specify the legal license under which the model used with this Modelfile is shared or distributed.
-
-```modelfile
-LICENSE """
-<license text>
-"""
-```
+`TEMPLATE` the full prompt template to be passed into the model. It may include (optionally) a system prompt, user prompt, and assistant prompt. This is used to create a full custom prompt, and syntax may be model specific.
 
 ## Notes
 
-- the **`Modelfile` is not case sensitive**. In the examples, we use uppercase for instructions to make it easier to distinguish it from arguments.
+- the **modelfile is not case sensitive**. In the examples, we use uppercase for instructions to make it easier to distinguish it from arguments.
 - Instructions can be in any order. In the examples, we start with FROM instruction to keep it easily readable.
-
-[1]: https://ollama.ai/library

docs/tutorials.md

@@ -1,9 +0,0 @@
-# Tutorials
-
-Here is a list of ways you can use Ollama with other tools to build interesting applications.
-
-- [Using LangChain with Ollama in JavaScript](./tutorials/langchainjs.md)
-- [Using LangChain with Ollama in Python](./tutorials/langchainpy.md)
-- [Running Ollama on NVIDIA Jetson Devices](./tutorials/nvidia-jetson.md)
-
-Also be sure to check out the [examples](../examples) directory for more ways to use Ollama.

docs/tutorials/langchainjs.md

@@ -1,77 +0,0 @@
-# Using LangChain with Ollama using JavaScript
-
-In this tutorial, we are going to use JavaScript with LangChain and Ollama to learn about something just a touch more recent. In August 2023, there was a series of wildfires on Maui. There is no way an LLM trained before that time can know about this, since their training data would not include anything as recent as that. So we can find the [Wikipedia article about the fires](https://en.wikipedia.org/wiki/2023_Hawaii_wildfires) and ask questions about the contents.
-
-To get started, let's just use **LangChain** to ask a simple question to a model. To do this with JavaScript, we need to install **LangChain**:
-
-```bash
-npm install langchain
-```
-
-Now we can start building out our JavaScript:
-
-```javascript
-import { Ollama } from "langchain/llms/ollama";
-
-const ollama = new Ollama({
-  baseUrl: "http://localhost:11434",
-  model: "llama2",
-});
-
-const answer = await ollama.call(`why is the sky blue?`);
-
-console.log(answer);
-```
-
-That will get us the same thing as if we ran `ollama run llama2 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app.
-
-```bash
-npm install cheerio 
-```
-
-```javascript
-import { CheerioWebBaseLoader } from "langchain/document_loaders/web/cheerio";
-
-const loader = new CheerioWebBaseLoader("https://en.wikipedia.org/wiki/2023_Hawaii_wildfires");
-const data = await loader.load();
-```
-
-That will load the document. Although this page is smaller than the Odyssey, it is certainly bigger than the context size for most LLMs. So we are going to need to split into smaller pieces, and then select just the pieces relevant to our question. This is a great use for a vector datastore. In this example, we will use the **MemoryVectorStore** that is part of **LangChain**. But there is one more thing we need to get the content into the datastore. We have to run an embeddings process that converts the tokens in the text into a series of vectors. And for that, we are going to use **Tensorflow**. There is a lot of stuff going on in this one. First, install the **Tensorflow** components that we need.
-
-```javascript
-npm install @tensorflow/tfjs-core@3.6.0 @tensorflow/tfjs-converter@3.6.0 @tensorflow-models/universal-sentence-encoder@1.3.3 @tensorflow/tfjs-node@4.10.0
-```
-
-If you just install those components without the version numbers, it will install the latest versions, but there are conflicts within **Tensorflow**, so you need to install the compatible versions.
-
-```javascript
-import { RecursiveCharacterTextSplitter } from "langchain/text_splitter"
-import { MemoryVectorStore } from "langchain/vectorstores/memory";
-import "@tensorflow/tfjs-node";
-import { TensorFlowEmbeddings } from "langchain/embeddings/tensorflow";
-
-// Split the text into 500 character chunks. And overlap each chunk by 20 characters
-const textSplitter = new RecursiveCharacterTextSplitter({
- chunkSize: 500,
- chunkOverlap: 20
-});
-const splitDocs = await textSplitter.splitDocuments(data);
-
-// Then use the TensorFlow Embedding to store these chunks in the datastore
-const vectorStore = await MemoryVectorStore.fromDocuments(splitDocs, new TensorFlowEmbeddings());
-```
-
-To connect the datastore to a question asked to a LLM, we need to use the concept at the heart of **LangChain**: the chain. Chains are a way to connect a number of activities together to accomplish a particular tasks. There are a number of chain types available, but for this tutorial we are using the **RetrievalQAChain**.
-
-```javascript
-import { RetrievalQAChain } from "langchain/chains";
-
-const retriever = vectorStore.asRetriever();
-const chain = RetrievalQAChain.fromLLM(ollama, retriever);
-const result = await chain.call({query: "When was Hawaii's request for a major disaster declaration approved?"});
-console.log(result.text)
-```
-
-So we created a retriever, which is a way to return the chunks that match a query from a datastore. And then connect the retriever and the model via a chain. Finally, we send a query to the chain, which results in an answer using our document as a source. The answer it returned was correct, August 10, 2023.
-
-And that is a simple introduction to what you can do with **LangChain** and **Ollama.**

docs/tutorials/langchainpy.md

@@ -1,81 +0,0 @@
-# Using LangChain with Ollama in Python
-
-Let's imagine we are studying the classics, such as **the Odyssey** by **Homer**. We might have a question about Neleus and his family. If you ask llama2 for that info, you may get something like:
-
-> I apologize, but I'm a large language model, I cannot provide information on individuals or families that do not exist in reality. Neleus is not a real person or character, and therefore does not have a family or any other personal details. My apologies for any confusion. Is there anything else I can help you with?
-
-This sounds like a typical censored response, but even llama2-uncensored gives a mediocre answer:
-
-> Neleus was a legendary king of Pylos and the father of Nestor, one of the Argonauts. His mother was Clymene, a sea nymph, while his father was Neptune, the god of the sea.
-
-So let's figure out how we can use **LangChain** with Ollama to ask our question to the actual document, the Odyssey by Homer, using Python.
-
-Let's start by asking a simple question that we can get an answer to from the **Llama2** model using **Ollama**. First, we need to install the **LangChain** package:
-
-`pip install langchain`
-
-Then we can create a model and ask the question:
-
-```python
-from langchain.llms import Ollama
-ollama = Ollama(base_url='http://localhost:11434',
-model="llama2")
-print(ollama("why is the sky blue"))
-```
-
-Notice that we are defining the model and the base URL for Ollama.
-
-Now let's load a document to ask questions against. I'll load up the Odyssey by Homer, which you can find at Project Gutenberg. We will need **WebBaseLoader** which is part of **LangChain** and loads text from any webpage. On my machine, I also needed to install **bs4** to get that to work, so run `pip install bs4`.
-
-```python
-from langchain.document_loaders import WebBaseLoader
-loader = WebBaseLoader("https://www.gutenberg.org/files/1727/1727-h/1727-h.htm")
-data = loader.load()
-```
-
-This file is pretty big. Just the preface is 3000 tokens. Which means the full document won't fit into the context for the model. So we need to split it up into smaller pieces.
-
-```python
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-
-text_splitter=RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
-all_splits = text_splitter.split_documents(data)
-```
-
-It's split up, but we have to find the relevant splits and then submit those to the model. We can do this by creating embeddings and storing them in a vector database. For now, we don't have embeddings built in to Ollama, though we will be adding that soon, so for now, we can use the GPT4All library for that. We will use ChromaDB in this example for a vector database. `pip install GPT4All chromadb`
-
-```python
-from langchain.embeddings import GPT4AllEmbeddings
-from langchain.vectorstores import Chroma
-vectorstore = Chroma.from_documents(documents=all_splits, embedding=GPT4AllEmbeddings())
-```
-
-Now let's ask a question from the document. **Who was Neleus, and who is in his family?** Neleus is a character in the Odyssey, and the answer can be found in our text.
-
-```python
-question="Who is Neleus and who is in Neleus' family?"
-docs = vectorstore.similarity_search(question)
-len(docs)
-```
-
-This will output the number of matches for chunks of data similar to the search.
-
-The next thing is to send the question and the relevant parts of the docs to the model to see if we can get a good answer. But we are stitching two parts of the process together, and that is called a chain. This means we need to define a chain:
-
-```python
-from langchain.chains import RetrievalQA
-qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever())
-qachain({"query": question})
-```
-
-The answer received from this chain was:
-
-> Neleus is a character in Homer's "Odyssey" and is mentioned in the context of Penelope's suitors. Neleus is the father of Chloris, who is married to Neleus and bears him several children, including Nestor, Chromius, Periclymenus, and Pero. Amphinomus, the son of Nisus, is also mentioned as a suitor of Penelope and is known for his good natural disposition and agreeable conversation.
-
-It's not a perfect answer, as it implies Neleus married his daughter when actually Chloris "was the youngest daughter to Amphion son of Iasus and king of Minyan Orchomenus, and was Queen in Pylos".
-
-I updated the chunk_overlap for the text splitter to 20 and tried again and got a much better answer:
-
-> Neleus is a character in Homer's epic poem "The Odyssey." He is the husband of Chloris, who is the youngest daughter of Amphion son of Iasus and king of Minyan Orchomenus. Neleus has several children with Chloris, including Nestor, Chromius, Periclymenus, and Pero.
-
-And that is a much better answer.

docs/tutorials/nvidia-jetson.md

@@ -1,38 +0,0 @@
-# Running Ollama on NVIDIA Jetson Devices
-
-With some minor configuration, Ollama runs well on [NVIDIA Jetson Devices](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/). The following has been tested on [JetPack 5.1.2](https://developer.nvidia.com/embedded/jetpack).
-
-NVIDIA Jetson devices are Linux-based embedded AI computers that are purpose-built for AI applications.
-
-Jetsons have an integrated GPU that is wired directly to the memory controller of the machine. For this reason, the `nvidia-smi` command is unrecognized, and Ollama proceeds to operate in "CPU only"
-mode. This can be verified by using a monitoring tool like jtop.
-
-In order to address this, we simply pass the path to the Jetson's pre-installed CUDA libraries into `ollama serve` (while in a tmux session). We then hardcode the num_gpu parameters into a cloned
-version of our target model.
-
-Prerequisites:
-
-- curl
-- tmux
-
-Here are the steps:
-
-- Install Ollama via standard Linux command (ignore the 404 error): `curl https://ollama.ai/install.sh | sh`
-- Stop the Ollama service: `sudo systemctl stop ollama`
-- Start Ollama serve in a tmux session called ollama_jetson and reference the CUDA libraries path: `tmux has-session -t ollama_jetson 2>/dev/null || tmux new-session -d -s ollama_jetson 
-'LD_LIBRARY_PATH=/usr/local/cuda/lib64 ollama serve'`
-- Pull the model you want to use (e.g. mistral): `ollama pull mistral`
-- Create a new Modelfile specifically for enabling GPU support on the Jetson: `touch ModelfileMistralJetson`
-- In the ModelfileMistralJetson file, specify the FROM model and the num_gpu PARAMETER as shown below:
-
-```
-FROM mistral
-PARAMETER num_gpu 999
-```
-
-- Create a new model from your Modelfile: `ollama create mistral-jetson -f ./ModelfileMistralJetson`
-- Run the new model: `ollama run mistral-jetson`
-
-If you run a monitoring tool like jtop you should now see that Ollama is using the Jetson's integrated GPU.
-
-And that's it!

examples/.gitignore

@@ -1,171 +0,0 @@
-node_modules
-# OSX
-.DS_STORE
-
-# Models
-models/
-
-# Local Chroma db
-.chroma/
-db/
-
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

examples/README.md

@@ -1,3 +1,15 @@
 # Examples
 
-This directory contains different examples of using Ollama.
+This directory contains examples that can be created and run with `ollama`.
+
+To create a model:
+
+```
+ollama create example -f <example file>
+```
+
+To run a model:
+
+```
+ollama run example
+```

examples/bash-comparemodels/README.md

@@ -1,10 +0,0 @@
-# Bash Shell examples
-
-When calling `ollama`, you can pass it a file to run all the prompts in the file, one after the other:
-
-`ollama run llama2 < sourcequestions.txt`
-
-This concept is used in the following example.
-
-## Compare Models
-`comparemodels.sh` is a script that runs all the questions in `sourcequestions.txt` using any 4 models you choose that you have already pulled from the Ollama library or have created locally.

examples/bash-comparemodels/comparemodels.sh

@@ -1,64 +0,0 @@
-#! /usr/bin/env bash
-# Compare multiple models by running them with the same questions
-
-NUMBEROFCHOICES=4
-SELECTIONS=()
-declare -a SUMS=()
-
-# Get the list of models
-CHOICES=$(ollama list | awk '{print $1}')
-
-# Select which models to run as a comparison
-echo "Select $NUMBEROFCHOICES models to compare:"
-select ITEM in $CHOICES; do
-    if [[ -n $ITEM ]]; then
-        echo "You have selected $ITEM"
-        SELECTIONS+=("$ITEM")
-        ((COUNT++))
-        if [[ $COUNT -eq $NUMBEROFCHOICES ]]; then
-            break
-        fi
-    else
-        echo "Invalid selection"
-    fi
-done
-
-# Loop through each of the selected models
-for ITEM in "${SELECTIONS[@]}"; do
-    echo "--------------------------------------------------------------"
-    echo "Loading the model $ITEM into memory"
-    ollama run "$ITEM" ""
-    echo "--------------------------------------------------------------"
-    echo "Running the questions through the model $ITEM"
-    COMMAND_OUTPUT=$(ollama run "$ITEM" --verbose < sourcequestions.txt 2>&1| tee /dev/stderr)
-
-    # eval duration is sometimes listed in seconds and sometimes in milliseconds. 
-    # Add up the values for each model
-    SUM=$(echo "$COMMAND_OUTPUT" | awk '
-    /eval duration:/ {
-        value = $3
-        if (index(value, "ms") > 0) {
-            gsub("ms", "", value)
-            value /= 1000
-        } else {
-            gsub("s", "", value)
-        }
-        sum += value
-    }
-    END { print sum }')
-
-
-    SUMS+=("All questions for $ITEM completed in $SUM seconds")
-done
-
-echo ""
-echo "--------------------------------------------------------------"
-echo -e "Sums of eval durations for each run:"
-for val in "${SUMS[@]}"; do
-    echo "$val"
-done
-
-echo "--------------------------------------------------------------"
-echo "Comparison complete. Now you can decide"
-echo "which model is best."
-echo "--------------------------------------------------------------"

examples/bash-comparemodels/sourcequestions.txt

@@ -1,7 +0,0 @@
-Why is the sky blue
-What is a black hole
-Explain the big bang theory like I am 5?
-What is the quickest way to win a game of Monopoly with 3 others?
-Why does a vacuum bottle keep my coffee hot and my milkshake cold?
-What is the difference between a meteor, a meteorite, and a meteoroid?
-Create an array with 5 items and print to the console. Do this in Python, C#, Typescript, and Rust.

examples/golang-simplegenerate/main.go

@@ -1,27 +0,0 @@
-package main
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"log"
-	"net/http"
-	"os"
-)
-
-func main() {
-	body := []byte(`{"model":"mistral"}`)
-	resp, err := http.Post("http://localhost:11434/api/generate", "application/json", bytes.NewBuffer(body))
-
-	if err != nil {
-		fmt.Print(err.Error())
-		os.Exit(1)
-	}
-
-	responseData, err := io.ReadAll(resp.Body)
-	if err != nil {
-		log.Fatal(err)
-	}
-	fmt.Println(string(responseData))
-
-}

examples/jupyter-notebook/README.md

@@ -1,5 +0,0 @@
-# Ollama Jupyter Notebook
-
-This example downloads and installs Ollama in a Jupyter instance such as Google Colab. It will start the Ollama service and expose an endpoint using `ngrok` which can be used to communicate with the Ollama instance remotely.
-
-For best results, use an instance with GPU accelerator.

examples/jupyter-notebook/ollama.ipynb

@@ -1,102 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "93f59dcb-c588-41b8-a792-55d88ade739c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Download and run the Ollama Linux install script\n",
-    "!curl https://ollama.ai/install.sh | sh\n",
-    "!command -v systemctl >/dev/null && sudo systemctl stop ollama"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "658c147e-c7f8-490e-910e-62b80f577dda",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install aiohttp pyngrok\n",
-    "\n",
-    "import os\n",
-    "import asyncio\n",
-    "from aiohttp import ClientSession\n",
-    "\n",
-    "# Set LD_LIBRARY_PATH so the system NVIDIA library becomes preferred\n",
-    "# over the built-in library. This is particularly important for \n",
-    "# Google Colab which installs older drivers\n",
-    "os.environ.update({'LD_LIBRARY_PATH': '/usr/lib64-nvidia'})\n",
-    "\n",
-    "async def run(cmd):\n",
-    "  '''\n",
-    "  run is a helper function to run subcommands asynchronously.\n",
-    "  '''\n",
-    "  print('>>> starting', *cmd)\n",
-    "  p = await asyncio.subprocess.create_subprocess_exec(\n",
-    "      *cmd,\n",
-    "      stdout=asyncio.subprocess.PIPE,\n",
-    "      stderr=asyncio.subprocess.PIPE,\n",
-    "  )\n",
-    "\n",
-    "  async def pipe(lines):\n",
-    "    async for line in lines:\n",
-    "      print(line.strip().decode('utf-8'))\n",
-    "\n",
-    "  await asyncio.gather(\n",
-    "      pipe(p.stdout),\n",
-    "      pipe(p.stderr),\n",
-    "  )\n",
-    "\n",
-    "\n",
-    "await asyncio.gather(\n",
-    "    run(['ollama', 'serve']),\n",
-    "    run(['ngrok', 'http', '--log', 'stderr', '11434']),\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e7735a55-9aad-4caf-8683-52e2163ba53b",
-   "metadata": {},
-   "source": [
-    "The previous cell starts two processes, `ollama` and `ngrok`. The log output will show a line like the following which describes the external address.\n",
-    "\n",
-    "```\n",
-    "t=2023-11-12T22:55:56+0000 lvl=info msg=\"started tunnel\" obj=tunnels name=command_line addr=http://localhost:11434 url=https://8249-34-125-179-11.ngrok.io\n",
-    "```\n",
-    "\n",
-    "The external address in this case is `https://8249-34-125-179-11.ngrok.io` which can be passed into `OLLAMA_HOST` to access this instance.\n",
-    "\n",
-    "```bash\n",
-    "export OLLAMA_HOST=https://8249-34-125-179-11.ngrok.io\n",
-    "ollama list\n",
-    "ollama run mistral\n",
-    "```"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/kubernetes/README.md

@@ -1,36 +0,0 @@
-# Deploy Ollama to Kubernetes
-
-## Prerequisites
-
-- Ollama: https://ollama.ai/download
-- Kubernetes cluster. This example will use Google Kubernetes Engine.
-
-## Steps
-
-1. Create the Ollama namespace, daemon set, and service
-
-    ```bash
-    kubectl apply -f cpu.yaml
-    ```
-
-1. Port forward the Ollama service to connect and use it locally
-
-    ```bash
-    kubectl -n ollama port-forward service/ollama 11434:80
-    ```
-
-1. Pull and run a model, for example `orca-mini:3b`
-
-    ```bash
-    ollama run orca-mini:3b
-    ```
-
-## (Optional) Hardware Acceleration
-
-Hardware acceleration in Kubernetes requires NVIDIA's [`k8s-device-plugin`](https://github.com/NVIDIA/k8s-device-plugin). Follow the link for more details.
-
-Once configured, create a GPU enabled Ollama deployment.
-
-```bash
-kubectl apply -f gpu.yaml
-```

examples/kubernetes/cpu.yaml

@@ -1,42 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: ollama
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  selector:
-    matchLabels:
-      name: ollama
-  template:
-    metadata:
-      labels:
-        name: ollama
-    spec:
-      containers:
-      - name: ollama
-        image: ollama/ollama:latest
-        ports:
-        - name: http
-          containerPort: 11434
-          protocol: TCP
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  type: ClusterIP
-  selector:
-    name: ollama
-  ports:
-  - port: 80
-    name: http
-    targetPort: http
-    protocol: TCP

examples/kubernetes/gpu.yaml

@@ -1,56 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: ollama
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      name: ollama
-  template:
-    metadata:
-      labels:
-        name: ollama
-    spec:
-      containers:
-      - name: ollama
-        image: ollama/ollama:latest
-        env:
-        - name: PATH
-          value: /usr/local/nvidia/bin:/usr/local/nvidia/lib64:/usr/bin:/usr/sbin:/bin:/sbin
-        - name: LD_LIBRARY_PATH
-          value: /usr/local/nvidia/lib64
-        ports:
-        - name: http
-          containerPort: 11434
-          protocol: TCP
-        resources:
-          limits:
-            nvidia.com/gpu: 1
-      tolerations:
-      - key: nvidia.com/gpu
-        operator: Exists
-        effect: NoSchedule
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  type: ClusterIP
-  selector:
-    name: ollama
-  ports:
-  - port: 80
-    name: http
-    targetPort: http
-    protocol: TCP

examples/langchain-python-rag-document/README.md

@@ -1,21 +0,0 @@
-# LangChain Document QA
-
-This example provides an interface for asking questions to a PDF document.
-
-## Setup
-
-```
-pip install -r requirements.txt
-```
-
-## Run
-
-```
-python main.py
-```
-
-A prompt will appear, where questions may be asked:
-
-```
-Query: How many locations does WeWork have?
-```

examples/langchain-python-rag-document/main.py

@@ -1,61 +0,0 @@
-from langchain.document_loaders import OnlinePDFLoader
-from langchain.vectorstores import Chroma
-from langchain.embeddings import GPT4AllEmbeddings
-from langchain import PromptTemplate
-from langchain.llms import Ollama
-from langchain.callbacks.manager import CallbackManager
-from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain.chains import RetrievalQA
-import sys
-import os
-
-class SuppressStdout:
-    def __enter__(self):
-        self._original_stdout = sys.stdout
-        self._original_stderr = sys.stderr
-        sys.stdout = open(os.devnull, 'w')
-        sys.stderr = open(os.devnull, 'w')
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        sys.stdout.close()
-        sys.stdout = self._original_stdout
-        sys.stderr = self._original_stderr
-
-# load the pdf and split it into chunks
-loader = OnlinePDFLoader("https://d18rn0p25nwr6d.cloudfront.net/CIK-0001813756/975b3e9b-268e-4798-a9e4-2a9a7c92dc10.pdf")
-data = loader.load()
-
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
-all_splits = text_splitter.split_documents(data)
-
-with SuppressStdout():
-    vectorstore = Chroma.from_documents(documents=all_splits, embedding=GPT4AllEmbeddings())
-
-while True:
-    query = input("\nQuery: ")
-    if query == "exit":
-        break
-    if query.strip() == "":
-        continue
-
-    # Prompt
-    template = """Use the following pieces of context to answer the question at the end. 
-    If you don't know the answer, just say that you don't know, don't try to make up an answer. 
-    Use three sentences maximum and keep the answer as concise as possible. 
-    {context}
-    Question: {question}
-    Helpful Answer:"""
-    QA_CHAIN_PROMPT = PromptTemplate(
-        input_variables=["context", "question"],
-        template=template,
-    )
-
-    llm = Ollama(model="llama2:13b", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
-    qa_chain = RetrievalQA.from_chain_type(
-        llm,
-        retriever=vectorstore.as_retriever(),
-        chain_type_kwargs={"prompt": QA_CHAIN_PROMPT},
-    )
-
-    result = qa_chain({"query": query})

examples/langchain-python-rag-document/requirements.txt

@@ -1,109 +0,0 @@
-absl-py==1.4.0
-aiohttp==3.8.5
-aiosignal==1.3.1
-anyio==3.7.1
-astunparse==1.6.3
-async-timeout==4.0.3
-attrs==23.1.0
-backoff==2.2.1
-beautifulsoup4==4.12.2
-bs4==0.0.1
-cachetools==5.3.1
-certifi==2023.7.22
-cffi==1.15.1
-chardet==5.2.0
-charset-normalizer==3.2.0
-Chroma==0.2.0
-chroma-hnswlib==0.7.2
-chromadb==0.4.5
-click==8.1.6
-coloredlogs==15.0.1
-cryptography==41.0.3
-dataclasses-json==0.5.14
-fastapi==0.99.1
-filetype==1.2.0
-flatbuffers==23.5.26
-frozenlist==1.4.0
-gast==0.4.0
-google-auth==2.22.0
-google-auth-oauthlib==1.0.0
-google-pasta==0.2.0
-gpt4all==1.0.8
-grpcio==1.57.0
-h11==0.14.0
-h5py==3.9.0
-httptools==0.6.0
-humanfriendly==10.0
-idna==3.4
-importlib-resources==6.0.1
-joblib==1.3.2
-keras==2.13.1
-langchain==0.0.261
-langsmith==0.0.21
-libclang==16.0.6
-lxml==4.9.3
-Markdown==3.4.4
-MarkupSafe==2.1.3
-marshmallow==3.20.1
-monotonic==1.6
-mpmath==1.3.0
-multidict==6.0.4
-mypy-extensions==1.0.0
-nltk==3.8.1
-numexpr==2.8.5
-numpy==1.24.3
-oauthlib==3.2.2
-onnxruntime==1.15.1
-openapi-schema-pydantic==1.2.4
-opt-einsum==3.3.0
-overrides==7.4.0
-packaging==23.1
-pdf2image==1.16.3
-pdfminer==20191125
-pdfminer.six==20221105
-Pillow==10.0.0
-posthog==3.0.1
-protobuf==4.24.0
-pulsar-client==3.2.0
-pyasn1==0.5.0
-pyasn1-modules==0.3.0
-pycparser==2.21
-pycryptodome==3.18.0
-pydantic==1.10.12
-PyPika==0.48.9
-python-dateutil==2.8.2
-python-dotenv==1.0.0
-python-magic==0.4.27
-PyYAML==6.0.1
-regex==2023.8.8
-requests==2.31.0
-requests-oauthlib==1.3.1
-rsa==4.9
-six==1.16.0
-sniffio==1.3.0
-soupsieve==2.4.1
-SQLAlchemy==2.0.19
-starlette==0.27.0
-sympy==1.12
-tabulate==0.9.0
-tenacity==8.2.2
-tensorboard==2.13.0
-tensorboard-data-server==0.7.1
-tensorflow==2.13.0
-tensorflow-estimator==2.13.0
-tensorflow-hub==0.14.0
-tensorflow-macos==2.13.0
-termcolor==2.3.0
-tokenizers==0.13.3
-tqdm==4.66.1
-typing-inspect==0.9.0
-typing_extensions==4.5.0
-unstructured==0.9.2
-urllib3==1.26.16
-uvicorn==0.23.2
-uvloop==0.17.0
-watchfiles==0.19.0
-websockets==11.0.3
-Werkzeug==2.3.6
-wrapt==1.15.0
-yarl==1.9.2

examples/langchain-python-rag-privategpt/.gitignore

@@ -1,170 +0,0 @@
-# OSX
-.DS_STORE
-
-# Models
-models/
-
-# Local Chroma db
-.chroma/
-db/
-
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

examples/langchain-python-rag-privategpt/LICENSE

@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

examples/langchain-python-rag-privategpt/README.md

@@ -1,91 +0,0 @@
-# PrivateGPT with Llama 2 uncensored
-
-https://github.com/jmorganca/ollama/assets/3325447/20cf8ec6-ff25-42c6-bdd8-9be594e3ce1b
-
-> Note: this example is a slightly modified version of PrivateGPT using models such as Llama 2 Uncensored. All credit for PrivateGPT goes to Iván Martínez who is the creator of it, and you can find his GitHub repo [here](https://github.com/imartinez/privateGPT).
-
-### Setup
-
-Set up a virtual environment (optional):
-
-```
-python3 -m venv .venv
-source .venv/bin/activate
-```
-
-Install the Python dependencies:
-
-```shell
-pip install -r requirements.txt
-```
-
-Pull the model you'd like to use:
-
-```
-ollama pull llama2-uncensored
-```
-
-### Getting WeWork's latest quarterly earnings report (10-Q)
-
-```
-mkdir source_documents
-curl https://d18rn0p25nwr6d.cloudfront.net/CIK-0001813756/975b3e9b-268e-4798-a9e4-2a9a7c92dc10.pdf -o source_documents/wework.pdf
-```
-
-### Ingesting files
-
-```shell
-python ingest.py
-```
-
-Output should look like this:
-
-```shell
-Creating new vectorstore
-Loading documents from source_documents
-Loading new documents: 100%|██████████████████████| 1/1 [00:01<00:00,  1.73s/it]
-Loaded 1 new documents from source_documents
-Split into 90 chunks of text (max. 500 tokens each)
-Creating embeddings. May take some minutes...
-Using embedded DuckDB with persistence: data will be stored in: db
-Ingestion complete! You can now run privateGPT.py to query your documents
-```
-
-### Ask questions
-
-```shell
-python privateGPT.py
-
-Enter a query: How many locations does WeWork have?
-
-> Answer (took 17.7 s.):
-As of June 2023, WeWork has 777 locations worldwide, including 610 Consolidated Locations (as defined in the section entitled Key Performance Indicators).
-```
-
-### Try a different model:
-
-```
-ollama pull llama2:13b
-MODEL=llama2:13b python privateGPT.py
-```
-
-## Adding more files
-
-Put any and all your files into the `source_documents` directory
-
-The supported extensions are:
-
-- `.csv`: CSV,
-- `.docx`: Word Document,
-- `.doc`: Word Document,
-- `.enex`: EverNote,
-- `.eml`: Email,
-- `.epub`: EPub,
-- `.html`: HTML File,
-- `.md`: Markdown,
-- `.msg`: Outlook Message,
-- `.odt`: Open Document Text,
-- `.pdf`: Portable Document Format (PDF),
-- `.pptx` : PowerPoint Document,
-- `.ppt` : PowerPoint Document,
-- `.txt`: Text file (UTF-8),

examples/langchain-python-rag-privategpt/constants.py

@@ -1,11 +0,0 @@
-import os
-from chromadb.config import Settings
-
-# Define the folder for storing database
-PERSIST_DIRECTORY = os.environ.get('PERSIST_DIRECTORY', 'db')
-
-# Define the Chroma settings
-CHROMA_SETTINGS = Settings(
-        persist_directory=PERSIST_DIRECTORY,
-        anonymized_telemetry=False
-)

examples/langchain-python-rag-privategpt/ingest.py

@@ -1,161 +0,0 @@
-#!/usr/bin/env python3
-import os
-import glob
-from typing import List
-from multiprocessing import Pool
-from tqdm import tqdm
-
-from langchain.document_loaders import (
-    CSVLoader,
-    EverNoteLoader,
-    PyMuPDFLoader,
-    TextLoader,
-    UnstructuredEmailLoader,
-    UnstructuredEPubLoader,
-    UnstructuredHTMLLoader,
-    UnstructuredMarkdownLoader,
-    UnstructuredODTLoader,
-    UnstructuredPowerPointLoader,
-    UnstructuredWordDocumentLoader,
-)
-
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import Chroma
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.docstore.document import Document
-from constants import CHROMA_SETTINGS
-
-
-# Load environment variables
-persist_directory = os.environ.get('PERSIST_DIRECTORY', 'db')
-source_directory = os.environ.get('SOURCE_DIRECTORY', 'source_documents')
-embeddings_model_name = os.environ.get('EMBEDDINGS_MODEL_NAME', 'all-MiniLM-L6-v2')
-chunk_size = 500
-chunk_overlap = 50
-
-# Custom document loaders
-class MyElmLoader(UnstructuredEmailLoader):
-    """Wrapper to fallback to text/plain when default does not work"""
-
-    def load(self) -> List[Document]:
-        """Wrapper adding fallback for elm without html"""
-        try:
-            try:
-                doc = UnstructuredEmailLoader.load(self)
-            except ValueError as e:
-                if 'text/html content not found in email' in str(e):
-                    # Try plain text
-                    self.unstructured_kwargs["content_source"]="text/plain"
-                    doc = UnstructuredEmailLoader.load(self)
-                else:
-                    raise
-        except Exception as e:
-            # Add file_path to exception message
-            raise type(e)(f"{self.file_path}: {e}") from e
-
-        return doc
-
-
-# Map file extensions to document loaders and their arguments
-LOADER_MAPPING = {
-    ".csv": (CSVLoader, {}),
-    # ".docx": (Docx2txtLoader, {}),
-    ".doc": (UnstructuredWordDocumentLoader, {}),
-    ".docx": (UnstructuredWordDocumentLoader, {}),
-    ".enex": (EverNoteLoader, {}),
-    ".eml": (MyElmLoader, {}),
-    ".epub": (UnstructuredEPubLoader, {}),
-    ".html": (UnstructuredHTMLLoader, {}),
-    ".md": (UnstructuredMarkdownLoader, {}),
-    ".odt": (UnstructuredODTLoader, {}),
-    ".pdf": (PyMuPDFLoader, {}),
-    ".ppt": (UnstructuredPowerPointLoader, {}),
-    ".pptx": (UnstructuredPowerPointLoader, {}),
-    ".txt": (TextLoader, {"encoding": "utf8"}),
-    # Add more mappings for other file extensions and loaders as needed
-}
-
-
-def load_single_document(file_path: str) -> List[Document]:
-    ext = "." + file_path.rsplit(".", 1)[-1]
-    if ext in LOADER_MAPPING:
-        loader_class, loader_args = LOADER_MAPPING[ext]
-        loader = loader_class(file_path, **loader_args)
-        return loader.load()
-
-    raise ValueError(f"Unsupported file extension '{ext}'")
-
-def load_documents(source_dir: str, ignored_files: List[str] = []) -> List[Document]:
-    """
-    Loads all documents from the source documents directory, ignoring specified files
-    """
-    all_files = []
-    for ext in LOADER_MAPPING:
-        all_files.extend(
-            glob.glob(os.path.join(source_dir, f"**/*{ext}"), recursive=True)
-        )
-    filtered_files = [file_path for file_path in all_files if file_path not in ignored_files]
-
-    with Pool(processes=os.cpu_count()) as pool:
-        results = []
-        with tqdm(total=len(filtered_files), desc='Loading new documents', ncols=80) as pbar:
-            for i, docs in enumerate(pool.imap_unordered(load_single_document, filtered_files)):
-                results.extend(docs)
-                pbar.update()
-
-    return results
-
-def process_documents(ignored_files: List[str] = []) -> List[Document]:
-    """
-    Load documents and split in chunks
-    """
-    print(f"Loading documents from {source_directory}")
-    documents = load_documents(source_directory, ignored_files)
-    if not documents:
-        print("No new documents to load")
-        exit(0)
-    print(f"Loaded {len(documents)} new documents from {source_directory}")
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
-    texts = text_splitter.split_documents(documents)
-    print(f"Split into {len(texts)} chunks of text (max. {chunk_size} tokens each)")
-    return texts
-
-def does_vectorstore_exist(persist_directory: str) -> bool:
-    """
-    Checks if vectorstore exists
-    """
-    if os.path.exists(os.path.join(persist_directory, 'index')):
-        if os.path.exists(os.path.join(persist_directory, 'chroma-collections.parquet')) and os.path.exists(os.path.join(persist_directory, 'chroma-embeddings.parquet')):
-            list_index_files = glob.glob(os.path.join(persist_directory, 'index/*.bin'))
-            list_index_files += glob.glob(os.path.join(persist_directory, 'index/*.pkl'))
-            # At least 3 documents are needed in a working vectorstore
-            if len(list_index_files) > 3:
-                return True
-    return False
-
-def main():
-    # Create embeddings
-    embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
-
-    if does_vectorstore_exist(persist_directory):
-        # Update and store locally vectorstore
-        print(f"Appending to existing vectorstore at {persist_directory}")
-        db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
-        collection = db.get()
-        texts = process_documents([metadata['source'] for metadata in collection['metadatas']])
-        print(f"Creating embeddings. May take some minutes...")
-        db.add_documents(texts)
-    else:
-        # Create and store locally vectorstore
-        print("Creating new vectorstore")
-        texts = process_documents()
-        print(f"Creating embeddings. May take some minutes...")
-        db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory)
-    db.persist()
-    db = None
-
-    print(f"Ingestion complete! You can now run privateGPT.py to query your documents")
-
-
-if __name__ == "__main__":
-    main()

examples/langchain-python-rag-privategpt/privateGPT.py

@@ -1,74 +0,0 @@
-#!/usr/bin/env python3
-from langchain.chains import RetrievalQA
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain.vectorstores import Chroma
-from langchain.llms import Ollama
-import chromadb
-import os
-import argparse
-import time
-
-model = os.environ.get("MODEL", "llama2-uncensored")
-# For embeddings model, the example uses a sentence-transformers model
-# https://www.sbert.net/docs/pretrained_models.html 
-# "The all-mpnet-base-v2 model provides the best quality, while all-MiniLM-L6-v2 is 5 times faster and still offers good quality."
-embeddings_model_name = os.environ.get("EMBEDDINGS_MODEL_NAME", "all-MiniLM-L6-v2")
-persist_directory = os.environ.get("PERSIST_DIRECTORY", "db")
-target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
-
-from constants import CHROMA_SETTINGS
-
-def main():
-    # Parse the command line arguments
-    args = parse_arguments()
-    embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
-
-    db = Chroma(persist_directory=persist_directory, embedding_function=embeddings)
-
-    retriever = db.as_retriever(search_kwargs={"k": target_source_chunks})
-    # activate/deactivate the streaming StdOut callback for LLMs
-    callbacks = [] if args.mute_stream else [StreamingStdOutCallbackHandler()]
-
-    llm = Ollama(model=model, callbacks=callbacks)
-
-    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents= not args.hide_source)
-    # Interactive questions and answers
-    while True:
-        query = input("\nEnter a query: ")
-        if query == "exit":
-            break
-        if query.strip() == "":
-            continue
-
-        # Get the answer from the chain
-        start = time.time()
-        res = qa(query)
-        answer, docs = res['result'], [] if args.hide_source else res['source_documents']
-        end = time.time()
-
-        # Print the result
-        print("\n\n> Question:")
-        print(query)
-        print(answer)
-
-        # Print the relevant sources used for the answer
-        for document in docs:
-            print("\n> " + document.metadata["source"] + ":")
-            print(document.page_content)
-
-def parse_arguments():
-    parser = argparse.ArgumentParser(description='privateGPT: Ask questions to your documents without an internet connection, '
-                                                 'using the power of LLMs.')
-    parser.add_argument("--hide-source", "-S", action='store_true',
-                        help='Use this flag to disable printing of source documents used for answers.')
-
-    parser.add_argument("--mute-stream", "-M",
-                        action='store_true',
-                        help='Use this flag to disable the streaming StdOut callback for LLMs.')
-
-    return parser.parse_args()
-
-
-if __name__ == "__main__":
-    main()

examples/langchain-python-rag-privategpt/pyproject.toml

@@ -1,26 +0,0 @@
-[tool.poetry]
-name = "privategpt"
-version = "0.1.0"
-description = ""
-authors = ["Ivan Martinez <ivanmartit@gmail.com>"]
-license = "Apache Version 2.0"
-readme = "README.md"
-
-[tool.poetry.dependencies]
-python = "^3.10"
-langchain = "0.0.261"
-gpt4all = "^1.0.3"
-chromadb = "^0.3.26"
-PyMuPDF = "^1.22.5"
-python-dotenv = "^1.0.0"
-unstructured = "^0.8.0"
-extract-msg = "^0.41.5"
-tabulate = "^0.9.0"
-pandoc = "^2.3"
-pypandoc = "^1.11"
-tqdm = "^4.65.0"
-sentence-transformers = "^2.2.2"
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"

examples/langchain-python-rag-privategpt/requirements.txt

@@ -1,14 +0,0 @@
-langchain==0.0.274
-gpt4all==1.0.8
-chromadb==0.4.7
-llama-cpp-python==0.1.81
-urllib3==2.0.4
-PyMuPDF==1.23.5
-python-dotenv==1.0.0
-unstructured==0.10.8
-extract-msg==0.45.0
-tabulate==0.9.0
-pandoc==2.3
-pypandoc==1.11
-tqdm==4.66.1
-sentence_transformers==2.2.2

examples/langchain-python-rag-websummary/README.md

@@ -1,15 +0,0 @@
-# LangChain Web Summarization
-
-This example summarizes a website
-
-## Setup
-
-```
-pip install -r requirements.txt
-```
-
-## Run
-
-```
-python main.py
-```

examples/langchain-python-rag-websummary/main.py

@@ -1,12 +0,0 @@
-from langchain.llms import Ollama
-from langchain.document_loaders import WebBaseLoader
-from langchain.chains.summarize import load_summarize_chain
-
-loader = WebBaseLoader("https://ollama.ai/blog/run-llama2-uncensored-locally")
-docs = loader.load()
-
-llm = Ollama(model="llama2")
-chain = load_summarize_chain(llm, chain_type="stuff")
-
-result = chain.run(docs)
-print(result)

examples/langchain-python-rag-websummary/requirements.txt

@@ -1,2 +0,0 @@
-langchain==0.0.259
-bs4==0.0.1

examples/langchain-python-simple/README.md

@@ -1,21 +0,0 @@
-# LangChain
-
-This example is a basic "hello world" of using LangChain with Ollama.
-
-## Setup
-
-```
-pip install -r requirements.txt
-```
-
-## Run
-
-```
-python main.py
-```
-
-Running this example will print the response for "hello":
-
-```
-Hello! It's nice to meet you. hopefully you are having a great day! Is there something I can help you with or would you like to chat?
-```

examples/langchain-python-simple/main.py

@@ -1,4 +0,0 @@
-from langchain.llms import Ollama
-llm = Ollama(model="llama2")
-res = llm.predict("hello")
-print (res)

examples/langchain-python-simple/requirements.txt

@@ -1 +0,0 @@
-langchain==0.0.259

examples/langchain-typescript-simple/README.md

@@ -1,21 +0,0 @@
-# LangChain
-
-This example is a basic "hello world" of using LangChain with Ollama using Node.js and Typescript.
-
-## Setup
-
-```shell
-npm install
-```
-
-## Run
-
-```shell
-ts-node main.ts
-```
-
-Running this example will print the response for "hello":
-
-```plaintext
-Hello! It's nice to meet you. hopefully you are having a great day! Is there something I can help you with or would you like to chat?
-```

examples/langchain-typescript-simple/main.ts

@@ -1,15 +0,0 @@
-import { Ollama} from 'langchain/llms/ollama';
-
-async function main() {
-  const ollama = new Ollama({
-    model: 'mistral'    
-    // other parameters can be found at https://js.langchain.com/docs/api/llms_ollama/classes/Ollama
-  })
-  const stream = await ollama.stream("Hello");
-
-  for await (const chunk of stream) {
-    process.stdout.write(chunk);
-  }
-}
-
-main();

examples/langchain-typescript-simple/package-lock.json

@@ -1,997 +0,0 @@
-{
-  "name": "with-langchain-typescript-simplegenerate",
-  "lockfileVersion": 3,
-  "requires": true,
-  "packages": {
-    "": {
-      "dependencies": {
-        "langchain": "^0.0.165"
-      },
-      "devDependencies": {
-        "typescript": "^5.2.2"
-      }
-    },
-    "node_modules/@anthropic-ai/sdk": {
-      "version": "0.6.2",
-      "resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.6.2.tgz",
-      "integrity": "sha512-fB9PUj9RFT+XjkL+E9Ol864ZIJi+1P8WnbHspN3N3/GK2uSzjd0cbVIKTGgf4v3N8MwaQu+UWnU7C4BG/fap/g==",
-      "dependencies": {
-        "@types/node": "^18.11.18",
-        "@types/node-fetch": "^2.6.4",
-        "abort-controller": "^3.0.0",
-        "agentkeepalive": "^4.2.1",
-        "digest-fetch": "^1.3.0",
-        "form-data-encoder": "1.7.2",
-        "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7"
-      }
-    },
-    "node_modules/@types/node": {
-      "version": "18.18.4",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-18.18.4.tgz",
-      "integrity": "sha512-t3rNFBgJRugIhackit2mVcLfF6IRc0JE4oeizPQL8Zrm8n2WY/0wOdpOPhdtG0V9Q2TlW/axbF1MJ6z+Yj/kKQ=="
-    },
-    "node_modules/@types/node-fetch": {
-      "version": "2.6.6",
-      "resolved": "https://registry.npmjs.org/@types/node-fetch/-/node-fetch-2.6.6.tgz",
-      "integrity": "sha512-95X8guJYhfqiuVVhRFxVQcf4hW/2bCuoPwDasMf/531STFoNoWTT7YDnWdXHEZKqAGUigmpG31r2FE70LwnzJw==",
-      "dependencies": {
-        "@types/node": "*",
-        "form-data": "^4.0.0"
-      }
-    },
-    "node_modules/@types/retry": {
-      "version": "0.12.0",
-      "resolved": "https://registry.npmjs.org/@types/retry/-/retry-0.12.0.tgz",
-      "integrity": "sha512-wWKOClTTiizcZhXnPY4wikVAwmdYHp8q6DmC+EJUzAMsycb7HB32Kh9RN4+0gExjmPmZSAQjgURXIGATPegAvA=="
-    },
-    "node_modules/@types/uuid": {
-      "version": "9.0.5",
-      "resolved": "https://registry.npmjs.org/@types/uuid/-/uuid-9.0.5.tgz",
-      "integrity": "sha512-xfHdwa1FMJ082prjSJpoEI57GZITiQz10r3vEJCHa2khEFQjKy91aWKz6+zybzssCvXUwE1LQWgWVwZ4nYUvHQ=="
-    },
-    "node_modules/abort-controller": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
-      "integrity": "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg==",
-      "dependencies": {
-        "event-target-shim": "^5.0.0"
-      },
-      "engines": {
-        "node": ">=6.5"
-      }
-    },
-    "node_modules/agentkeepalive": {
-      "version": "4.5.0",
-      "resolved": "https://registry.npmjs.org/agentkeepalive/-/agentkeepalive-4.5.0.tgz",
-      "integrity": "sha512-5GG/5IbQQpC9FpkRGsSvZI5QYeSCzlJHdpBQntCsuTOxhKD8lqKhrleg2Yi7yvMIf82Ycmmqln9U8V9qwEiJew==",
-      "dependencies": {
-        "humanize-ms": "^1.2.1"
-      },
-      "engines": {
-        "node": ">= 8.0.0"
-      }
-    },
-    "node_modules/ansi-styles": {
-      "version": "5.2.0",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-5.2.0.tgz",
-      "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==",
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/ansi-styles?sponsor=1"
-      }
-    },
-    "node_modules/argparse": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/argparse/-/argparse-2.0.1.tgz",
-      "integrity": "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="
-    },
-    "node_modules/asynckit": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
-      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="
-    },
-    "node_modules/base-64": {
-      "version": "0.1.0",
-      "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
-      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA=="
-    },
-    "node_modules/base64-js": {
-      "version": "1.5.1",
-      "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
-      "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==",
-      "funding": [
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/feross"
-        },
-        {
-          "type": "patreon",
-          "url": "https://www.patreon.com/feross"
-        },
-        {
-          "type": "consulting",
-          "url": "https://feross.org/support"
-        }
-      ]
-    },
-    "node_modules/binary-extensions": {
-      "version": "2.2.0",
-      "resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.2.0.tgz",
-      "integrity": "sha512-jDctJ/IVQbZoJykoeHbhXpOlNBqGNcwXJKJog42E5HDPUwQTSdjCHdihjj0DlnheQ7blbT6dHOafNAiS8ooQKA==",
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/binary-search": {
-      "version": "1.3.6",
-      "resolved": "https://registry.npmjs.org/binary-search/-/binary-search-1.3.6.tgz",
-      "integrity": "sha512-nbE1WxOTTrUWIfsfZ4aHGYu5DOuNkbxGokjV6Z2kxfJK3uaAb8zNK1muzOeipoLHZjInT4Br88BHpzevc681xA=="
-    },
-    "node_modules/camelcase": {
-      "version": "6.3.0",
-      "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-6.3.0.tgz",
-      "integrity": "sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA==",
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/charenc": {
-      "version": "0.0.2",
-      "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
-      "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==",
-      "engines": {
-        "node": "*"
-      }
-    },
-    "node_modules/combined-stream": {
-      "version": "1.0.8",
-      "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
-      "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
-      "dependencies": {
-        "delayed-stream": "~1.0.0"
-      },
-      "engines": {
-        "node": ">= 0.8"
-      }
-    },
-    "node_modules/commander": {
-      "version": "10.0.1",
-      "resolved": "https://registry.npmjs.org/commander/-/commander-10.0.1.tgz",
-      "integrity": "sha512-y4Mg2tXshplEbSGzx7amzPwKKOCGuoSRP/CjEdwwk0FOGlUbq6lKuoyDZTNZkmxHdJtp54hdfY/JUrdL7Xfdug==",
-      "engines": {
-        "node": ">=14"
-      }
-    },
-    "node_modules/crypt": {
-      "version": "0.0.2",
-      "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
-      "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==",
-      "engines": {
-        "node": "*"
-      }
-    },
-    "node_modules/decamelize": {
-      "version": "1.2.0",
-      "resolved": "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz",
-      "integrity": "sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==",
-      "engines": {
-        "node": ">=0.10.0"
-      }
-    },
-    "node_modules/delayed-stream": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
-      "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
-      "engines": {
-        "node": ">=0.4.0"
-      }
-    },
-    "node_modules/digest-fetch": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
-      "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
-      "dependencies": {
-        "base-64": "^0.1.0",
-        "md5": "^2.3.0"
-      }
-    },
-    "node_modules/event-target-shim": {
-      "version": "5.0.1",
-      "resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz",
-      "integrity": "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ==",
-      "engines": {
-        "node": ">=6"
-      }
-    },
-    "node_modules/eventemitter3": {
-      "version": "4.0.7",
-      "resolved": "https://registry.npmjs.org/eventemitter3/-/eventemitter3-4.0.7.tgz",
-      "integrity": "sha512-8guHBZCwKnFhYdHr2ysuRWErTwhoN2X8XELRlrRwpmfeY2jjuUN4taQMsULKUVo1K4DvZl+0pgfyoysHxvmvEw=="
-    },
-    "node_modules/expr-eval": {
-      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/expr-eval/-/expr-eval-2.0.2.tgz",
-      "integrity": "sha512-4EMSHGOPSwAfBiibw3ndnP0AvjDWLsMvGOvWEZ2F96IGk0bIVdjQisOHxReSkE13mHcfbuCiXw+G4y0zv6N8Eg=="
-    },
-    "node_modules/flat": {
-      "version": "5.0.2",
-      "resolved": "https://registry.npmjs.org/flat/-/flat-5.0.2.tgz",
-      "integrity": "sha512-b6suED+5/3rTpUBdG1gupIl8MPFCAMA0QXwmljLhvCUKcUvdE4gWky9zpuGCcXHOsz4J9wPGNWq6OKpmIzz3hQ==",
-      "bin": {
-        "flat": "cli.js"
-      }
-    },
-    "node_modules/form-data": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz",
-      "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==",
-      "dependencies": {
-        "asynckit": "^0.4.0",
-        "combined-stream": "^1.0.8",
-        "mime-types": "^2.1.12"
-      },
-      "engines": {
-        "node": ">= 6"
-      }
-    },
-    "node_modules/form-data-encoder": {
-      "version": "1.7.2",
-      "resolved": "https://registry.npmjs.org/form-data-encoder/-/form-data-encoder-1.7.2.tgz",
-      "integrity": "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="
-    },
-    "node_modules/formdata-node": {
-      "version": "4.4.1",
-      "resolved": "https://registry.npmjs.org/formdata-node/-/formdata-node-4.4.1.tgz",
-      "integrity": "sha512-0iirZp3uVDjVGt9p49aTaqjk84TrglENEDuqfdlZQ1roC9CWlPk6Avf8EEnZNcAqPonwkG35x4n3ww/1THYAeQ==",
-      "dependencies": {
-        "node-domexception": "1.0.0",
-        "web-streams-polyfill": "4.0.0-beta.3"
-      },
-      "engines": {
-        "node": ">= 12.20"
-      }
-    },
-    "node_modules/humanize-ms": {
-      "version": "1.2.1",
-      "resolved": "https://registry.npmjs.org/humanize-ms/-/humanize-ms-1.2.1.tgz",
-      "integrity": "sha512-Fl70vYtsAFb/C06PTS9dZBo7ihau+Tu/DNCk/OyHhea07S+aeMWpFFkUaXRa8fI+ScZbEI8dfSxwY7gxZ9SAVQ==",
-      "dependencies": {
-        "ms": "^2.0.0"
-      }
-    },
-    "node_modules/is-any-array": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/is-any-array/-/is-any-array-2.0.1.tgz",
-      "integrity": "sha512-UtilS7hLRu++wb/WBAw9bNuP1Eg04Ivn1vERJck8zJthEvXCBEBpGR/33u/xLKWEQf95803oalHrVDptcAvFdQ=="
-    },
-    "node_modules/is-buffer": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
-      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w=="
-    },
-    "node_modules/js-tiktoken": {
-      "version": "1.0.7",
-      "resolved": "https://registry.npmjs.org/js-tiktoken/-/js-tiktoken-1.0.7.tgz",
-      "integrity": "sha512-biba8u/clw7iesNEWLOLwrNGoBP2lA+hTaBLs/D45pJdUPFXyxD6nhcDVtADChghv4GgyAiMKYMiRx7x6h7Biw==",
-      "dependencies": {
-        "base64-js": "^1.5.1"
-      }
-    },
-    "node_modules/js-yaml": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz",
-      "integrity": "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA==",
-      "dependencies": {
-        "argparse": "^2.0.1"
-      },
-      "bin": {
-        "js-yaml": "bin/js-yaml.js"
-      }
-    },
-    "node_modules/jsonpointer": {
-      "version": "5.0.1",
-      "resolved": "https://registry.npmjs.org/jsonpointer/-/jsonpointer-5.0.1.tgz",
-      "integrity": "sha512-p/nXbhSEcu3pZRdkW1OfJhpsVtW1gd4Wa1fnQc9YLiTfAjn0312eMKimbdIQzuZl9aa9xUGaRlP9T/CJE/ditQ==",
-      "engines": {
-        "node": ">=0.10.0"
-      }
-    },
-    "node_modules/langchain": {
-      "version": "0.0.165",
-      "resolved": "https://registry.npmjs.org/langchain/-/langchain-0.0.165.tgz",
-      "integrity": "sha512-CpbNpjwaE+9lzjdw+pZz0VgnRrFivEgr7CVp9dDaAb5JpaJAA4V2v6uQ9ZPN+TSqupTQ79HFn2sfyZVEl2EG7Q==",
-      "dependencies": {
-        "@anthropic-ai/sdk": "^0.6.2",
-        "ansi-styles": "^5.0.0",
-        "binary-extensions": "^2.2.0",
-        "camelcase": "6",
-        "decamelize": "^1.2.0",
-        "expr-eval": "^2.0.2",
-        "flat": "^5.0.2",
-        "js-tiktoken": "^1.0.7",
-        "js-yaml": "^4.1.0",
-        "jsonpointer": "^5.0.1",
-        "langchainhub": "~0.0.6",
-        "langsmith": "~0.0.31",
-        "ml-distance": "^4.0.0",
-        "object-hash": "^3.0.0",
-        "openai": "~4.4.0",
-        "openapi-types": "^12.1.3",
-        "p-queue": "^6.6.2",
-        "p-retry": "4",
-        "uuid": "^9.0.0",
-        "yaml": "^2.2.1",
-        "zod": "^3.22.3",
-        "zod-to-json-schema": "^3.20.4"
-      },
-      "engines": {
-        "node": ">=18"
-      },
-      "peerDependencies": {
-        "@aws-crypto/sha256-js": "^5.0.0",
-        "@aws-sdk/client-bedrock-runtime": "^3.422.0",
-        "@aws-sdk/client-dynamodb": "^3.310.0",
-        "@aws-sdk/client-kendra": "^3.352.0",
-        "@aws-sdk/client-lambda": "^3.310.0",
-        "@aws-sdk/client-s3": "^3.310.0",
-        "@aws-sdk/client-sagemaker-runtime": "^3.310.0",
-        "@aws-sdk/client-sfn": "^3.310.0",
-        "@aws-sdk/credential-provider-node": "^3.388.0",
-        "@azure/storage-blob": "^12.15.0",
-        "@clickhouse/client": "^0.0.14",
-        "@cloudflare/ai": "^1.0.12",
-        "@elastic/elasticsearch": "^8.4.0",
-        "@getmetal/metal-sdk": "*",
-        "@getzep/zep-js": "^0.7.0",
-        "@gomomento/sdk": "^1.23.0",
-        "@google-ai/generativelanguage": "^0.2.1",
-        "@google-cloud/storage": "^6.10.1",
-        "@huggingface/inference": "^1.5.1",
-        "@mozilla/readability": "*",
-        "@notionhq/client": "^2.2.10",
-        "@opensearch-project/opensearch": "*",
-        "@pinecone-database/pinecone": "^1.1.0",
-        "@planetscale/database": "^1.8.0",
-        "@qdrant/js-client-rest": "^1.2.0",
-        "@raycast/api": "^1.55.2",
-        "@smithy/eventstream-codec": "^2.0.5",
-        "@smithy/protocol-http": "^3.0.6",
-        "@smithy/signature-v4": "^2.0.10",
-        "@smithy/util-utf8": "^2.0.0",
-        "@supabase/postgrest-js": "^1.1.1",
-        "@supabase/supabase-js": "^2.10.0",
-        "@tensorflow-models/universal-sentence-encoder": "*",
-        "@tensorflow/tfjs-converter": "*",
-        "@tensorflow/tfjs-core": "*",
-        "@upstash/redis": "^1.20.6",
-        "@vercel/postgres": "^0.5.0",
-        "@writerai/writer-sdk": "^0.40.2",
-        "@xata.io/client": "^0.25.1",
-        "@xenova/transformers": "^2.5.4",
-        "@zilliz/milvus2-sdk-node": ">=2.2.7",
-        "apify-client": "^2.7.1",
-        "axios": "*",
-        "cassandra-driver": "^4.6.4",
-        "cheerio": "^1.0.0-rc.12",
-        "chromadb": "*",
-        "cohere-ai": ">=6.0.0",
-        "d3-dsv": "^2.0.0",
-        "epub2": "^3.0.1",
-        "faiss-node": "^0.3.0",
-        "fast-xml-parser": "^4.2.7",
-        "firebase-admin": "^11.9.0",
-        "google-auth-library": "^8.9.0",
-        "googleapis": "^126.0.1",
-        "hnswlib-node": "^1.4.2",
-        "html-to-text": "^9.0.5",
-        "ignore": "^5.2.0",
-        "ioredis": "^5.3.2",
-        "jsdom": "*",
-        "llmonitor": "*",
-        "lodash": "^4.17.21",
-        "mammoth": "*",
-        "mongodb": "^5.2.0",
-        "mysql2": "^3.3.3",
-        "neo4j-driver": "*",
-        "node-llama-cpp": "*",
-        "notion-to-md": "^3.1.0",
-        "pdf-parse": "1.1.1",
-        "peggy": "^3.0.2",
-        "pg": "^8.11.0",
-        "pg-copy-streams": "^6.0.5",
-        "pickleparser": "^0.1.0",
-        "playwright": "^1.32.1",
-        "portkey-ai": "^0.1.11",
-        "puppeteer": "^19.7.2",
-        "redis": "^4.6.4",
-        "replicate": "^0.18.0",
-        "sonix-speech-recognition": "^2.1.1",
-        "srt-parser-2": "^1.2.2",
-        "typeorm": "^0.3.12",
-        "typesense": "^1.5.3",
-        "usearch": "^1.1.1",
-        "vectordb": "^0.1.4",
-        "voy-search": "0.6.2",
-        "weaviate-ts-client": "^1.4.0",
-        "web-auth-library": "^1.0.3",
-        "youtube-transcript": "^1.0.6",
-        "youtubei.js": "^5.8.0"
-      },
-      "peerDependenciesMeta": {
-        "@aws-crypto/sha256-js": {
-          "optional": true
-        },
-        "@aws-sdk/client-bedrock-runtime": {
-          "optional": true
-        },
-        "@aws-sdk/client-dynamodb": {
-          "optional": true
-        },
-        "@aws-sdk/client-kendra": {
-          "optional": true
-        },
-        "@aws-sdk/client-lambda": {
-          "optional": true
-        },
-        "@aws-sdk/client-s3": {
-          "optional": true
-        },
-        "@aws-sdk/client-sagemaker-runtime": {
-          "optional": true
-        },
-        "@aws-sdk/client-sfn": {
-          "optional": true
-        },
-        "@aws-sdk/credential-provider-node": {
-          "optional": true
-        },
-        "@azure/storage-blob": {
-          "optional": true
-        },
-        "@clickhouse/client": {
-          "optional": true
-        },
-        "@cloudflare/ai": {
-          "optional": true
-        },
-        "@elastic/elasticsearch": {
-          "optional": true
-        },
-        "@getmetal/metal-sdk": {
-          "optional": true
-        },
-        "@getzep/zep-js": {
-          "optional": true
-        },
-        "@gomomento/sdk": {
-          "optional": true
-        },
-        "@google-ai/generativelanguage": {
-          "optional": true
-        },
-        "@google-cloud/storage": {
-          "optional": true
-        },
-        "@huggingface/inference": {
-          "optional": true
-        },
-        "@mozilla/readability": {
-          "optional": true
-        },
-        "@notionhq/client": {
-          "optional": true
-        },
-        "@opensearch-project/opensearch": {
-          "optional": true
-        },
-        "@pinecone-database/pinecone": {
-          "optional": true
-        },
-        "@planetscale/database": {
-          "optional": true
-        },
-        "@qdrant/js-client-rest": {
-          "optional": true
-        },
-        "@raycast/api": {
-          "optional": true
-        },
-        "@smithy/eventstream-codec": {
-          "optional": true
-        },
-        "@smithy/protocol-http": {
-          "optional": true
-        },
-        "@smithy/signature-v4": {
-          "optional": true
-        },
-        "@smithy/util-utf8": {
-          "optional": true
-        },
-        "@supabase/postgrest-js": {
-          "optional": true
-        },
-        "@supabase/supabase-js": {
-          "optional": true
-        },
-        "@tensorflow-models/universal-sentence-encoder": {
-          "optional": true
-        },
-        "@tensorflow/tfjs-converter": {
-          "optional": true
-        },
-        "@tensorflow/tfjs-core": {
-          "optional": true
-        },
-        "@upstash/redis": {
-          "optional": true
-        },
-        "@vercel/postgres": {
-          "optional": true
-        },
-        "@writerai/writer-sdk": {
-          "optional": true
-        },
-        "@xata.io/client": {
-          "optional": true
-        },
-        "@xenova/transformers": {
-          "optional": true
-        },
-        "@zilliz/milvus2-sdk-node": {
-          "optional": true
-        },
-        "apify-client": {
-          "optional": true
-        },
-        "axios": {
-          "optional": true
-        },
-        "cassandra-driver": {
-          "optional": true
-        },
-        "cheerio": {
-          "optional": true
-        },
-        "chromadb": {
-          "optional": true
-        },
-        "cohere-ai": {
-          "optional": true
-        },
-        "d3-dsv": {
-          "optional": true
-        },
-        "epub2": {
-          "optional": true
-        },
-        "faiss-node": {
-          "optional": true
-        },
-        "fast-xml-parser": {
-          "optional": true
-        },
-        "firebase-admin": {
-          "optional": true
-        },
-        "google-auth-library": {
-          "optional": true
-        },
-        "googleapis": {
-          "optional": true
-        },
-        "hnswlib-node": {
-          "optional": true
-        },
-        "html-to-text": {
-          "optional": true
-        },
-        "ignore": {
-          "optional": true
-        },
-        "ioredis": {
-          "optional": true
-        },
-        "jsdom": {
-          "optional": true
-        },
-        "llmonitor": {
-          "optional": true
-        },
-        "lodash": {
-          "optional": true
-        },
-        "mammoth": {
-          "optional": true
-        },
-        "mongodb": {
-          "optional": true
-        },
-        "mysql2": {
-          "optional": true
-        },
-        "neo4j-driver": {
-          "optional": true
-        },
-        "node-llama-cpp": {
-          "optional": true
-        },
-        "notion-to-md": {
-          "optional": true
-        },
-        "pdf-parse": {
-          "optional": true
-        },
-        "peggy": {
-          "optional": true
-        },
-        "pg": {
-          "optional": true
-        },
-        "pg-copy-streams": {
-          "optional": true
-        },
-        "pickleparser": {
-          "optional": true
-        },
-        "playwright": {
-          "optional": true
-        },
-        "portkey-ai": {
-          "optional": true
-        },
-        "puppeteer": {
-          "optional": true
-        },
-        "redis": {
-          "optional": true
-        },
-        "replicate": {
-          "optional": true
-        },
-        "sonix-speech-recognition": {
-          "optional": true
-        },
-        "srt-parser-2": {
-          "optional": true
-        },
-        "typeorm": {
-          "optional": true
-        },
-        "typesense": {
-          "optional": true
-        },
-        "usearch": {
-          "optional": true
-        },
-        "vectordb": {
-          "optional": true
-        },
-        "voy-search": {
-          "optional": true
-        },
-        "weaviate-ts-client": {
-          "optional": true
-        },
-        "web-auth-library": {
-          "optional": true
-        },
-        "youtube-transcript": {
-          "optional": true
-        },
-        "youtubei.js": {
-          "optional": true
-        }
-      }
-    },
-    "node_modules/langchainhub": {
-      "version": "0.0.6",
-      "resolved": "https://registry.npmjs.org/langchainhub/-/langchainhub-0.0.6.tgz",
-      "integrity": "sha512-SW6105T+YP1cTe0yMf//7kyshCgvCTyFBMTgH2H3s9rTAR4e+78DA/BBrUL/Mt4Q5eMWui7iGuAYb3pgGsdQ9w=="
-    },
-    "node_modules/langsmith": {
-      "version": "0.0.42",
-      "resolved": "https://registry.npmjs.org/langsmith/-/langsmith-0.0.42.tgz",
-      "integrity": "sha512-sFuN+e7E+pPBIRaRgFqZh/BRBWNHTZNAwi6uj4kydQawooCZYoJmM5snOkiQrhVSvAhgu6xFhLvmfvkPcKzD7w==",
-      "dependencies": {
-        "@types/uuid": "^9.0.1",
-        "commander": "^10.0.1",
-        "p-queue": "^6.6.2",
-        "p-retry": "4",
-        "uuid": "^9.0.0"
-      },
-      "bin": {
-        "langsmith": "dist/cli/main.cjs"
-      }
-    },
-    "node_modules/md5": {
-      "version": "2.3.0",
-      "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
-      "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
-      "dependencies": {
-        "charenc": "0.0.2",
-        "crypt": "0.0.2",
-        "is-buffer": "~1.1.6"
-      }
-    },
-    "node_modules/mime-db": {
-      "version": "1.52.0",
-      "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
-      "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
-      "engines": {
-        "node": ">= 0.6"
-      }
-    },
-    "node_modules/mime-types": {
-      "version": "2.1.35",
-      "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
-      "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
-      "dependencies": {
-        "mime-db": "1.52.0"
-      },
-      "engines": {
-        "node": ">= 0.6"
-      }
-    },
-    "node_modules/ml-array-mean": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/ml-array-mean/-/ml-array-mean-1.1.6.tgz",
-      "integrity": "sha512-MIdf7Zc8HznwIisyiJGRH9tRigg3Yf4FldW8DxKxpCCv/g5CafTw0RRu51nojVEOXuCQC7DRVVu5c7XXO/5joQ==",
-      "dependencies": {
-        "ml-array-sum": "^1.1.6"
-      }
-    },
-    "node_modules/ml-array-sum": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/ml-array-sum/-/ml-array-sum-1.1.6.tgz",
-      "integrity": "sha512-29mAh2GwH7ZmiRnup4UyibQZB9+ZLyMShvt4cH4eTK+cL2oEMIZFnSyB3SS8MlsTh6q/w/yh48KmqLxmovN4Dw==",
-      "dependencies": {
-        "is-any-array": "^2.0.0"
-      }
-    },
-    "node_modules/ml-distance": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/ml-distance/-/ml-distance-4.0.1.tgz",
-      "integrity": "sha512-feZ5ziXs01zhyFUUUeZV5hwc0f5JW0Sh0ckU1koZe/wdVkJdGxcP06KNQuF0WBTj8FttQUzcvQcpcrOp/XrlEw==",
-      "dependencies": {
-        "ml-array-mean": "^1.1.6",
-        "ml-distance-euclidean": "^2.0.0",
-        "ml-tree-similarity": "^1.0.0"
-      }
-    },
-    "node_modules/ml-distance-euclidean": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/ml-distance-euclidean/-/ml-distance-euclidean-2.0.0.tgz",
-      "integrity": "sha512-yC9/2o8QF0A3m/0IXqCTXCzz2pNEzvmcE/9HFKOZGnTjatvBbsn4lWYJkxENkA4Ug2fnYl7PXQxnPi21sgMy/Q=="
-    },
-    "node_modules/ml-tree-similarity": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/ml-tree-similarity/-/ml-tree-similarity-1.0.0.tgz",
-      "integrity": "sha512-XJUyYqjSuUQkNQHMscr6tcjldsOoAekxADTplt40QKfwW6nd++1wHWV9AArl0Zvw/TIHgNaZZNvr8QGvE8wLRg==",
-      "dependencies": {
-        "binary-search": "^1.3.5",
-        "num-sort": "^2.0.0"
-      }
-    },
-    "node_modules/ms": {
-      "version": "2.1.3",
-      "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
-      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="
-    },
-    "node_modules/node-domexception": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/node-domexception/-/node-domexception-1.0.0.tgz",
-      "integrity": "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==",
-      "funding": [
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/jimmywarting"
-        },
-        {
-          "type": "github",
-          "url": "https://paypal.me/jimmywarting"
-        }
-      ],
-      "engines": {
-        "node": ">=10.5.0"
-      }
-    },
-    "node_modules/node-fetch": {
-      "version": "2.7.0",
-      "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
-      "integrity": "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==",
-      "dependencies": {
-        "whatwg-url": "^5.0.0"
-      },
-      "engines": {
-        "node": "4.x || >=6.0.0"
-      },
-      "peerDependencies": {
-        "encoding": "^0.1.0"
-      },
-      "peerDependenciesMeta": {
-        "encoding": {
-          "optional": true
-        }
-      }
-    },
-    "node_modules/num-sort": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/num-sort/-/num-sort-2.1.0.tgz",
-      "integrity": "sha512-1MQz1Ed8z2yckoBeSfkQHHO9K1yDRxxtotKSJ9yvcTUUxSvfvzEq5GwBrjjHEpMlq/k5gvXdmJ1SbYxWtpNoVg==",
-      "engines": {
-        "node": ">=8"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/object-hash": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/object-hash/-/object-hash-3.0.0.tgz",
-      "integrity": "sha512-RSn9F68PjH9HqtltsSnqYC1XXoWe9Bju5+213R98cNGttag9q9yAOTzdbsqvIa7aNm5WffBZFpWYr2aWrklWAw==",
-      "engines": {
-        "node": ">= 6"
-      }
-    },
-    "node_modules/openai": {
-      "version": "4.4.0",
-      "resolved": "https://registry.npmjs.org/openai/-/openai-4.4.0.tgz",
-      "integrity": "sha512-JN0t628Kh95T0IrXl0HdBqnlJg+4Vq0Bnh55tio+dfCnyzHvMLiWyCM9m726MAJD2YkDU4/8RQB6rNbEq9ct2w==",
-      "dependencies": {
-        "@types/node": "^18.11.18",
-        "@types/node-fetch": "^2.6.4",
-        "abort-controller": "^3.0.0",
-        "agentkeepalive": "^4.2.1",
-        "digest-fetch": "^1.3.0",
-        "form-data-encoder": "1.7.2",
-        "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7"
-      },
-      "bin": {
-        "openai": "bin/cli"
-      }
-    },
-    "node_modules/openapi-types": {
-      "version": "12.1.3",
-      "resolved": "https://registry.npmjs.org/openapi-types/-/openapi-types-12.1.3.tgz",
-      "integrity": "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw=="
-    },
-    "node_modules/p-finally": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/p-finally/-/p-finally-1.0.0.tgz",
-      "integrity": "sha512-LICb2p9CB7FS+0eR1oqWnHhp0FljGLZCWBE9aix0Uye9W8LTQPwMTYVGWQWIw9RdQiDg4+epXQODwIYJtSJaow==",
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/p-queue": {
-      "version": "6.6.2",
-      "resolved": "https://registry.npmjs.org/p-queue/-/p-queue-6.6.2.tgz",
-      "integrity": "sha512-RwFpb72c/BhQLEXIZ5K2e+AhgNVmIejGlTgiB9MzZ0e93GRvqZ7uSi0dvRF7/XIXDeNkra2fNHBxTyPDGySpjQ==",
-      "dependencies": {
-        "eventemitter3": "^4.0.4",
-        "p-timeout": "^3.2.0"
-      },
-      "engines": {
-        "node": ">=8"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/p-retry": {
-      "version": "4.6.2",
-      "resolved": "https://registry.npmjs.org/p-retry/-/p-retry-4.6.2.tgz",
-      "integrity": "sha512-312Id396EbJdvRONlngUx0NydfrIQ5lsYu0znKVUzVvArzEIt08V1qhtyESbGVd1FGX7UKtiFp5uwKZdM8wIuQ==",
-      "dependencies": {
-        "@types/retry": "0.12.0",
-        "retry": "^0.13.1"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/p-timeout": {
-      "version": "3.2.0",
-      "resolved": "https://registry.npmjs.org/p-timeout/-/p-timeout-3.2.0.tgz",
-      "integrity": "sha512-rhIwUycgwwKcP9yTOOFK/AKsAopjjCakVqLHePO3CC6Mir1Z99xT+R63jZxAT5lFZLa2inS5h+ZS2GvR99/FBg==",
-      "dependencies": {
-        "p-finally": "^1.0.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/retry": {
-      "version": "0.13.1",
-      "resolved": "https://registry.npmjs.org/retry/-/retry-0.13.1.tgz",
-      "integrity": "sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg==",
-      "engines": {
-        "node": ">= 4"
-      }
-    },
-    "node_modules/tr46": {
-      "version": "0.0.3",
-      "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
-      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="
-    },
-    "node_modules/typescript": {
-      "version": "5.2.2",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.2.2.tgz",
-      "integrity": "sha512-mI4WrpHsbCIcwT9cF4FZvr80QUeKvsUsUvKDoR+X/7XHQH98xYD8YHZg7ANtz2GtZt/CBq2QJ0thkGJMHfqc1w==",
-      "dev": true,
-      "bin": {
-        "tsc": "bin/tsc",
-        "tsserver": "bin/tsserver"
-      },
-      "engines": {
-        "node": ">=14.17"
-      }
-    },
-    "node_modules/uuid": {
-      "version": "9.0.1",
-      "resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz",
-      "integrity": "sha512-b+1eJOlsR9K8HJpow9Ok3fiWOWSIcIzXodvv0rQjVoOVNpWMpxf1wZNpt4y9h10odCNrqnYp1OBzRktckBe3sA==",
-      "funding": [
-        "https://github.com/sponsors/broofa",
-        "https://github.com/sponsors/ctavan"
-      ],
-      "bin": {
-        "uuid": "dist/bin/uuid"
-      }
-    },
-    "node_modules/web-streams-polyfill": {
-      "version": "4.0.0-beta.3",
-      "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-4.0.0-beta.3.tgz",
-      "integrity": "sha512-QW95TCTaHmsYfHDybGMwO5IJIM93I/6vTRk+daHTWFPhwh+C8Cg7j7XyKrwrj8Ib6vYXe0ocYNrmzY4xAAN6ug==",
-      "engines": {
-        "node": ">= 14"
-      }
-    },
-    "node_modules/webidl-conversions": {
-      "version": "3.0.1",
-      "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
-      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="
-    },
-    "node_modules/whatwg-url": {
-      "version": "5.0.0",
-      "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
-      "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
-      "dependencies": {
-        "tr46": "~0.0.3",
-        "webidl-conversions": "^3.0.0"
-      }
-    },
-    "node_modules/yaml": {
-      "version": "2.3.2",
-      "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.3.2.tgz",
-      "integrity": "sha512-N/lyzTPaJasoDmfV7YTrYCI0G/3ivm/9wdG0aHuheKowWQwGTsK0Eoiw6utmzAnI6pkJa0DUVygvp3spqqEKXg==",
-      "engines": {
-        "node": ">= 14"
-      }
-    },
-    "node_modules/zod": {
-      "version": "3.22.4",
-      "resolved": "https://registry.npmjs.org/zod/-/zod-3.22.4.tgz",
-      "integrity": "sha512-iC+8Io04lddc+mVqQ9AZ7OQ2MrUKGN+oIQyq1vemgt46jwCwLfhq7/pwnBnNXXXZb8VTVLKwp9EDkx+ryxIWmg==",
-      "funding": {
-        "url": "https://github.com/sponsors/colinhacks"
-      }
-    },
-    "node_modules/zod-to-json-schema": {
-      "version": "3.21.4",
-      "resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.21.4.tgz",
-      "integrity": "sha512-fjUZh4nQ1s6HMccgIeE0VP4QG/YRGPmyjO9sAh890aQKPEk3nqbfUXhMFaC+Dr5KvYBm8BCyvfpZf2jY9aGSsw==",
-      "peerDependencies": {
-        "zod": "^3.21.4"
-      }
-    }
-  }
-}

examples/langchain-typescript-simple/package.json

@@ -1,8 +0,0 @@
-{
-  "devDependencies": {
-    "typescript": "^5.2.2"
-  },
-  "dependencies": {
-    "langchain": "^0.0.165"
-  }
-}

examples/midjourney-prompter/Modelfile

@@ -0,0 +1,8 @@
+# Modelfile for creating a Midjourney prompts from a topic
+# This prompt was adapted from the original at https://www.greataiprompts.com/guide/midjourney/best-chatgpt-prompt-for-midjourney/
+# Run `ollama create mj -f ./Modelfile` and then `ollama run mj` and enter a topic
+
+FROM nous-hermes
+SYSTEM """
+Embrace your role as an AI-powered creative assistant, employing Midjourney to manifest compelling AI-generated art. I will outline a specific image concept, and in response, you must produce an exhaustive, multifaceted prompt for Midjourney, ensuring every detail of the original concept is represented in your instructions. Midjourney doesn't do well with text, so after the prompt, give me instructions that I can use to create the titles in a image editor.
+"""

examples/modelfile-10tweets/Modelfile

@@ -1,7 +0,0 @@
-# Modelfile for creating a list of ten tweets from a topic
-# Run `ollama create 10tweets -f ./Modelfile` and then `ollama run 10tweets` and enter a topic
-
-FROM llama2
-SYSTEM """
-You are a content marketer who needs to come up with 10 short but succinct tweets. The answer should be a list of ten tweets. Each tweet can have a maximum of 280 characters and should include hashtags. Each user input will be a subject and you should expand it in ten creative ways. Never stop after just one tweet. Always include ten. 
-"""

examples/modelfile-10tweets/README.md

@@ -1,23 +0,0 @@
-# Ten Tweets Modelfile
-
-This is a simple modelfile that generates ten tweets based off any topic.
-
-```bash
-ollama create tentweets
-
-ollama run tentweets
->>> underwater basketweaving
- Great! Here are ten creative tweets about underwater basketweaving:
-
-1. "Just discovered the ultimate stress-reliever: Underwater basketweaving! 🌊🧵 #UnderwaterBasketweaving #StressRelief"
-2. "Who needs meditation when you can do underwater basketweaving? 😴👀 #PeacefulDistraction #UnderwaterBasketweaving"
-3. "Just spent an hour in the pool and still managed to knot my basket. Goal: untangle it before next session. 💪🏽 #ChallengeAccepted #UnderwaterBasketweaving"
-4. "When life gives you lemons, make underwater basketweaving! 🍋🧵 #LemonadeLife #UnderwaterBasketweaving"
-5. "Just realized my underwater basketweaving skills could come in handy during a zombie apocalypse. 😂🧡 #SurvivalTips #UnderwaterBasketweaving"
-6. "I'm not lazy, I'm just conserving energy for my next underwater basketweaving session. 😴💤 #LazyDay #UnderwaterBasketweaving"
-7. "Just found my inner peace while doing underwater basketweaving. It's like meditation, but with knots! 🙏🧵 #Mindfulness #UnderwaterBasketweaving"
-8. "Why study for exams when you can do underwater basketweaving and forget all your worries? 😜🧵 #ProcrastinationStation #UnderwaterBasketweaving"
-9. "Just had to cut my underwater basketweaving session short due to a sudden urge to breathe. 🤯🌊 #AquaticAdventures #UnderwaterBasketweaving"
-10. "I'm not sure what's more impressive: my underwater basketweaving skills or the fact that I didn't drown trying to make this tweet. 😅🧵 #Accomplishment 
-#UnderwaterBasketweaving"
-```

examples/modelfile-devopsengineer/Modelfile

@@ -1,8 +0,0 @@
-# Modelfile for creating a devops engineer assistant
-# Run `ollama create devops-engineer -f ./Modelfile` and then `ollama run devops-engineer` and enter a topic
-
-FROM mistral
-PARAMETER temperature 1
-SYSTEM """
-You are a senior devops engineer, acting as an assistant. You offer help with cloud technologies like: Terraform, AWS, kubernetes, python. You answer with code examples when possible
-"""

examples/modelfile-devopsengineer/README.md

@@ -1,40 +0,0 @@
-# DevOps Engineer Modelfile
-
-This is a simple modelfile that takes will respond to any questions that a senior DevOps engineer should know how to solve.
-
-````text
-ollama create devopsengineer
-
-ollama run devopsengineer
->>> how can i proxy all connections from inside the office through a single server that caches large files. Provide a config file for nginx to achieve this?
-
-Here is an example configuration file for Nginx that can be used to proxy all connections from inside the office network to a centralized cache server:
-```perl
-http {
-    upstream cache_server {
-        server <cache_server_ip>;
-        server <cache_server_ip>;
-        server <cache_server_ip>;
-    }
-    
-    server {
-        listen 80;
-        server_name localhost;
-        
-        location / {
-            proxy_pass http://cache_server;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        }
-    }
-}
-```
-In this configuration, we define an `upstream` block that lists the IP addresses of the cache servers. We then define a server block that listens on port 80 and routes all 
-traffic to the `/` location to the cache servers using the `proxy_pass` directive. The `proxy_set_header` directives are used to preserve the source IP address of the client
-request when forwarding it to the cache server.
-
-To use this configuration, you would need to replace the placeholder `<cache_server_ip>` with the actual IP addresses of your cache servers. You would also need to make sure
-that the cache servers are configured to accept incoming connections from the Nginx server and handle requests for files.
-
-````

examples/modelfile-midjourney/Modelfile

@@ -1,11 +0,0 @@
-# Modelfile for creating a Midjourney prompts from a topic
-# This prompt was adapted from the original at https://www.greataiprompts.com/guide/midjourney/best-chatgpt-prompt-for-midjourney/
-# Run `ollama create mj -f ./Modelfile` and then `ollama run mj` and enter a topic
-
-FROM zephyr
-PARAMETER temperature 0.8
-PARAMETER top_k 500
-PARAMETER top_p 0.9
-SYSTEM """
-Embrace your role as a creative illustrator. Based on a concept provided, you must produce a single paragraph with a multifaceted description of an image, ensuring significant details of the concept and more is represented in your instructions. You do not need to write complete sentences but rather short concepts with the following information: the level of detail that should be represented, an artistic style and maybe a specific name of a painter or illustrator, the ideal color pallete, lighting, mood, perspective, the setting, time of day, weather, the season, the time period, location, materials, the textures, patterns, lines, brushstrokes, techniques, the medium, the genre, the rendering style. Don't include everything and keep the description length under 250 words. 
-"""

examples/modelfile-midjourney/README.md

@@ -1,11 +0,0 @@
-# Midjourney Prompt Generator Modelfile
-
-This simple modelfile will help create a prompt to feed to Midjourney.
-
-```text
-ollama create midjourney
-
-ollama run midjourney
->>> a sports car in the mountains. 
-A sleek, high-performance automobile cuts through a serpentine mountain landscape. The concept is a classic illustration of speed and power, depicted in the style of pop art by Andy Warhol. The color palette is dominated by bold, primary hues of red, blue, and yellow, with striking accent colors of white, black, and metallic shades. The lighting is bright and focused, casting sharp shadows on the rugged terrain. A sense of excitement and anticipation permeates throughout the scene, as the car navigates a treacherous course through the winding road. The perspective is low, allowing for a full view of the vehicle's sleek lines and intricate details. The setting takes place in the afternoon during a sunny day in autumn, as evidenced by the vibrant foliage on the mountainside. The time period is modern, with nods to classic car design. The materials are primarily digital, allowing for smooth curves and sharp contrasts. The textures are sleek and polished, with meticulously detailed lines and brushstrokes that accentuate the car's aerodynamic design. The patterns consist of geometric shapes and bold stripes, adding to the car's dynamic appeal. The genre is modern realism, with a focus on precision and detail. The rendering style is highly technical, capturing the nuances and subtleties of the vehicle and its surroundings in breathtaking detail.
-```

examples/modelfile-recipemaker/README.md

@@ -1,20 +0,0 @@
-# Recipe Maker Modelfile 
-
-Simple modelfile to generate a recipe from a short list of ingredients.
-
-```
-ollama create recipemaker
-
-ollama run recipemaker
->>> chilli pepper, white chocolate, kale
- Ingredients:
-- 1 small chili pepper
-- 4 squares of white chocolate
-- handful of kale leaves
-
-Instructions:
-1. In a blender or food processor, puree the chilies and white chocolate until smooth.
-2. Add the chopped kale leaves to the blender and pulse until well combined.
-3. Serve immediately as a dip for crackers or use it as an ingredient in your favorite recipe. The mixture of spicy chili pepper with sweet white chocolate and nutritious 
-kale will make your taste buds dance with delight!
-```

examples/modelfile-sentiments/Modelfile

@@ -1,28 +0,0 @@
-# Modelfile for creating a sentiment analyzer. 
-# Run `ollama create sentiments -f pathtofile` and then `ollama run sentiments` and enter a topic
-
-FROM orca
-TEMPLATE """
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
-### User: 
-I hate it when my phone dies
-### Response: 
-NEGATIVE
-### User: 
-He is awesome
-### Response: 
-POSITIVE
-### User: 
-This is the link to the article
-### Response: 
-NEUTRAL
-### User:
-{{ .Prompt }}
-
-### Response:
-"""
-
-SYSTEM """You are a sentiment analyzer. You will receive text and output only one word, either POSITIVE or NEGATIVE or NEUTRAL, depending on the sentiment of the text."""

examples/modelfile-sentiments/Readme.md

@@ -1,25 +0,0 @@
-# Sentiments Modelfile
-
-This is a simple sentiments analyzer using the Orca model. When you pull Orca from the registry, it has a Template already defined that looks like this:
-
-```Modelfile
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
-
-### User:
-{{ .Prompt }}
-
-### Response:
-```
-
-If we just wanted to have the text:
-
-```Plaintext
-You are a sentiment analyzer. You will receive text and output only one word, either POSITIVE or NEGATIVE or NEUTRAL, depending on the sentiment of the text.
-```
-
-then we could have put this in a SYSTEM block. But we want to provide examples which require updating the full Template. Any Modelfile you create will inherit all the settings from the source model. But in this example, we are overriding the Template.
-
-When providing examples for the input and output, you should include the way the model usually provides information. Since the Orca model expects a user prompt to appear after ### User: and the response is after ### Response, we should format our examples like that as well. If we were using the Llama 2 model, the format would be a bit different.

examples/python-dockerit/Modelfile

@@ -1,20 +0,0 @@
-FROM mistral
-SYSTEM """
-You are an experienced Devops engineer focused on docker. When given specifications for a particular need or application you know the best way to host that within a docker container. For instance if someone tells you they want an nginx server to host files located at /web you will answer as follows
-
----start
-FROM nginx:alpine
-COPY /myweb /usr/share/nginx/html
-EXPOSE 80
----end
-
-Notice that the answer you should give is just the contents of the dockerfile with no explanation and there are three dashes and the word start at the beginning and 3 dashes and the word end. The full output can be piped into a file and run as is. Here is another example. The user will ask to launch a Postgres server with a password of abc123. And the response should be
-
----start
-FROM postgres:latest
-ENV POSTGRES_PASSWORD=abc123
-EXPOSE 5432
----end
-
-Again it's just the contents of the dockerfile and nothing else.
-"""

examples/python-dockerit/README.md

@@ -1,15 +0,0 @@
-# DockerIt
-
-DockerIt is a tool to help you build and run your application in a Docker container. It consists of a model that defines the system prompt and model weights to use, along with a python script to then build the container and run the image automatically. 
-
-## Caveats
-
-This is an simple example. It's assuming the Dockerfile content generated is going to work. In many cases, even with simple web servers, it fails when trying to copy files that don't exist. It's simply an example of what you could possibly do.
-
-## Example Usage
-
-```bash
-> python3 ./dockerit.py "simple postgres server with admin password set to 123"
-Enter the name of the image: matttest
-Container named happy_keller  started with id:  7c201bb6c30f02b356ddbc8e2a5af9d7d7d7b8c228519c9a501d15c0bd9d6b3e
-```

examples/python-dockerit/dockerit.py

@@ -1,17 +0,0 @@
-import requests, json, docker, io, sys
-inputDescription = " ".join(sys.argv[1:])
-imageName = input("Enter the name of the image: ")
-client = docker.from_env()
-s = requests.Session()
-output=""
-with s.post('http://localhost:11434/api/generate', json={'model': 'dockerit', 'prompt': inputDescription}, stream=True) as r:
-  for line in r.iter_lines():
-    if line:
-      j = json.loads(line)
-      if "response" in j:
-        output = output +j["response"]
-output = output[output.find("---start")+9:output.find("---end")-1]
-f = io.BytesIO(bytes(output, 'utf-8'))
-client.images.build(fileobj=f, tag=imageName)
-container = client.containers.run(imageName, detach=True)
-print("Container named", container.name, " started with id: ",container.id)

examples/python-dockerit/requirements.txt

@@ -1 +0,0 @@
-docker

examples/python-json-datagenerator/predefinedschema.py

@@ -1,31 +0,0 @@
-import requests
-import json
-import random
-
-model = "llama2"
-template = {
-  "firstName": "", 
-  "lastName": "", 
-  "address": {
-    "street": "", 
-    "city": "", 
-    "state": "", 
-    "zipCode": ""
-  }, 
-  "phoneNumber": ""
-}
-
-prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in the US, and  phone number. \nUse the following template: {json.dumps(template)}."
-
-data = {
-    "prompt": prompt,
-    "model": model,
-    "format": "json",
-    "stream": False,
-    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
-}
-
-print(f"Generating a sample user")
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
-json_data = json.loads(response.text)
-print(json.dumps(json.loads(json_data["response"]), indent=2))

examples/python-json-datagenerator/randomaddresses.py

@@ -1,31 +0,0 @@
-import requests
-import json
-import random
-
-countries = [
-    "United States",
-    "United Kingdom",
-    "the Netherlands",
-    "Germany",
-    "Mexico",
-    "Canada",
-    "France",
-]
-country = random.choice(countries)
-model = "llama2"
-
-prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and phone number. Do not use common names. Respond using JSON. Key names should have no backslashes, values should use plain ascii with no special characters."
-
-data = {
-    "prompt": prompt,
-    "model": model,
-    "format": "json",
-    "stream": False,
-    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
-}
-
-print(f"Generating a sample user in {country}")
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
-json_data = json.loads(response.text)
-
-print(json.dumps(json.loads(json_data["response"]), indent=2))

examples/python-json-datagenerator/readme.md

@@ -1,34 +0,0 @@
-# JSON Output Example
-
-![llmjson 2023-11-10 15_31_31](https://github.com/jmorganca/ollama/assets/633681/e599d986-9b4a-4118-81a4-4cfe7e22da25)
-
-There are two python scripts in this example. `randomaddresses.py` generates random addresses from different countries. `predefinedschema.py` sets a template for the model to fill in.
-
-## Review the Code
-
-Both programs are basically the same, with a different prompt for each, demonstrating two different ideas. The key part of getting JSON out of a model is to state in the prompt or system prompt that it should respond using JSON, and specifying the `format` as `json` in the data body.
-
-```python
-prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and  phone number. Do not use common names. Respond using JSON. Key names should with no backslashes, values should use plain ascii with no special characters."
-
-data = {
-    "prompt": prompt,
-    "model": model,
-    "format": "json",
-    "stream": False,
-    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
-}
-```
-
-When running `randomaddresses.py` you will see that the schema changes and adapts to the chosen country.
-
-In `predefinedschema.py`, a template has been specified in the prompt as well. It's been defined as JSON and then dumped into the prompt string to make it easier to work with.
-
-Both examples turn streaming off so that we end up with the completed JSON all at once. We need to convert the `response.text` to JSON so that when we output it as a string we can set the indent spacing to make the output easy to read.
-
-```python
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
-json_data = json.loads(response.text)
-
-print(json.dumps(json.loads(json_data["response"]), indent=2))
-```

examples/python-json-datagenerator/requirements.txt

@@ -1 +0,0 @@
-Requests==2.31.0

examples/python-loganalysis/Modelfile

@@ -1,8 +0,0 @@
-FROM codebooga:latest
-
-SYSTEM """
-You are a log file analyzer. You will receive a set of lines from a log file for some software application, find the errors and other interesting aspects of the logs, and explain them so a new user can understand what they mean. If there are any steps they can do to resolve them, list the steps in your answer.
-"""
-
-PARAMETER TEMPERATURE 0.3
-

examples/python-loganalysis/loganalysis.py

@@ -1,42 +0,0 @@
-import sys
-import re
-import requests
-import json
-
-# prelines and postlines represent the number of lines of context to include in the output around the error
-prelines = 10
-postlines = 10
-
-def find_errors_in_log_file():
-  if len(sys.argv) < 2:
-    print("Usage: python loganalysis.py <filename>")
-    return
-
-  log_file_path = sys.argv[1]
-  with open(log_file_path, 'r') as log_file:
-    log_lines = log_file.readlines()
-
-error_logs = []
-    for i, line in enumerate(log_lines):
-        if "error" in line.lower():
-            start_index = max(0, i - prelines)
-            end_index = min(len(log_lines), i + postlines + 1)
-            error_logs.extend(log_lines[start_index:end_index])
-
-  return error_logs
-
-error_logs = find_errors_in_log_file()
-
-data = {
-  "prompt": "\n".join(error_logs), 
-  "model": "mattw/loganalyzer"
-}
-
-
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=True)
-for line in response.iter_lines():
-  if line:
-    json_data = json.loads(line)
-    if json_data['done'] == False:
-      print(json_data['response'], end='', flush=True)
-

examples/python-loganalysis/logtest.logfile

@@ -1,32 +0,0 @@
-2023-11-10 07:17:40 /docker-entrypoint.sh: /docker-entrypoint.d/ is not empty, will attempt to perform configuration
-2023-11-10 07:17:40 /docker-entrypoint.sh: Looking for shell scripts in /docker-entrypoint.d/
-2023-11-10 07:17:40 /docker-entrypoint.sh: Launching /docker-entrypoint.d/10-listen-on-ipv6-by-default.sh
-2023-11-10 07:17:40 10-listen-on-ipv6-by-default.sh: info: Getting the checksum of /etc/nginx/conf.d/default.conf
-2023-11-10 07:17:40 10-listen-on-ipv6-by-default.sh: info: Enabled listen on IPv6 in /etc/nginx/conf.d/default.conf
-2023-11-10 07:17:40 /docker-entrypoint.sh: Sourcing /docker-entrypoint.d/15-local-resolvers.envsh
-2023-11-10 07:17:40 /docker-entrypoint.sh: Launching /docker-entrypoint.d/20-envsubst-on-templates.sh
-2023-11-10 07:17:40 /docker-entrypoint.sh: Launching /docker-entrypoint.d/30-tune-worker-processes.sh
-2023-11-10 07:17:40 /docker-entrypoint.sh: Configuration complete; ready for start up
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: using the "epoll" event method
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: nginx/1.25.3
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: built by gcc 12.2.0 (Debian 12.2.0-14) 
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: OS: Linux 6.4.16-linuxkit
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: getrlimit(RLIMIT_NOFILE): 1048576:1048576
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker processes
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 29
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 30
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 31
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 32
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 33
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 34
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 35
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 36
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 37
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 38
-2023-11-10 07:17:44 192.168.65.1 - - [10/Nov/2023:13:17:43 +0000] "GET / HTTP/1.1" 200 615 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"
-2023-11-10 07:17:44 2023/11/10 13:17:44 [error] 29#29: *1 open() "/usr/share/nginx/html/favicon.ico" failed (2: No such file or directory), client: 192.168.65.1, server: localhost, request: "GET /favicon.ico HTTP/1.1", host: "localhost:8080", referrer: "http://localhost:8080/"
-2023-11-10 07:17:44 192.168.65.1 - - [10/Nov/2023:13:17:44 +0000] "GET /favicon.ico HTTP/1.1" 404 555 "http://localhost:8080/" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"
-2023-11-10 07:17:50 2023/11/10 13:17:50 [error] 29#29: *1 open() "/usr/share/nginx/html/ahstat" failed (2: No such file or directory), client: 192.168.65.1, server: localhost, request: "GET /ahstat HTTP/1.1", host: "localhost:8080"
-2023-11-10 07:17:50 192.168.65.1 - - [10/Nov/2023:13:17:50 +0000] "GET /ahstat HTTP/1.1" 404 555 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"
-2023-11-10 07:18:53 2023/11/10 13:18:53 [error] 29#29: *1 open() "/usr/share/nginx/html/ahstat" failed (2: No such file or directory), client: 192.168.65.1, server: localhost, request: "GET /ahstat HTTP/1.1", host: "localhost:8080"
-2023-11-10 07:18:53 192.168.65.1 - - [10/Nov/2023:13:18:53 +0000] "GET /ahstat HTTP/1.1" 404 555 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"