macapp: add error handling for symlink operations

Refactor the installer to do a better job handling errors when creating symlinks.
It checks if paths are valid before trying to use them, safely creates
directories if they don't exist, and clearly tells you what went wrong if
something fails. It also uses TypeScript to catch mistakes early and makes
sure paths work correctly in all cases.

README.md

@@ -346,6 +346,9 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [Web management](https://github.com/lemonit-eric-mao/ollama-web-management) (Web management page)
 - [Promptery](https://github.com/promptery/promptery) (desktop client for Ollama.)
 - [Ollama App](https://github.com/JHubi1/ollama-app) (Modern and easy-to-use multi-platform client for Ollama)
+- [SpaceLlama](https://github.com/tcsenpai/spacellama) (Firefox and Chrome extension to quickly summarize web pages with ollama in a sidebar)
+- [YouLama](https://github.com/tcsenpai/youlama) (Webapp to quickly summarize any YouTube video, supporting Invidious as well)
+- [DualMind](https://github.com/tcsenpai/dualmind) (Experimental app allowing two models to talk to each other in the terminal or in a web interface)
 - [ollamarama-matrix](https://github.com/h1ddenpr0cess20/ollamarama-matrix) (Ollama chatbot for the Matrix chat protocol)
 - [ollama-chat-app](https://github.com/anan1213095357/ollama-chat-app) (Flutter-based chat app)
 - [Perfect Memory AI](https://www.perfectmemory.ai/) (Productivity AI assists personalized by what you have seen on your screen, heard and said in the meetings)
@@ -356,6 +359,7 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [Nosia](https://github.com/nosia-ai/nosia) (Easy to install and use RAG platform based on Ollama)
 - [Witsy](https://github.com/nbonamy/witsy) (An AI Desktop application avaiable for Mac/Windows/Linux)
 - [Abbey](https://github.com/US-Artificial-Intelligence/abbey) (A configurable AI interface server with notebooks, document storage, and YouTube support)
+- [Minima](https://github.com/dmayboroda/minima) (RAG with on-premises or fully local workflow)
 
 ### Cloud
 

api/types.go

@@ -146,6 +146,7 @@ type ToolCall struct {
 }
 
 type ToolCallFunction struct {
+	Index     int                       `json:"index,omitempty"`
 	Name      string                    `json:"name"`
 	Arguments ToolCallFunctionArguments `json:"arguments"`
 }

cmd/cmd_test.go

@@ -8,7 +8,6 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"os"
-	"path/filepath"
 	"strings"
 	"testing"
 
@@ -180,18 +179,14 @@ Weigh anchor!
 
 	t.Run("license", func(t *testing.T) {
 		var b bytes.Buffer
-		license, err := os.ReadFile(filepath.Join("..", "LICENSE"))
-		if err != nil {
-			t.Fatal(err)
-		}
-
+		license := "MIT License\nCopyright (c) Ollama\n"
 		if err := showInfo(&api.ShowResponse{
 			Details: api.ModelDetails{
 				Family:            "test",
 				ParameterSize:     "7B",
 				QuantizationLevel: "FP16",
 			},
-			License: string(license),
+			License: license,
 		}, &b); err != nil {
 			t.Fatal(err)
 		}

docs/api.md

@@ -49,10 +49,10 @@ Advanced parameters (optional):
 - `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
 - `system`: system message to (overrides what is defined in the `Modelfile`)
 - `template`: the prompt template to use (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. You may choose to use the `raw` parameter if you are specifying a full templated prompt in your request to the API
 - `keep_alive`: controls how long the model will stay loaded into memory following the request (default: `5m`)
+- `context` (deprecated): the context parameter returned from a previous request to `/generate`, this can be used to keep a short conversational memory
 
 #### JSON mode
 

docs/modelfile.md

@@ -63,7 +63,7 @@ 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>'`
+2. `ollama create choose-a-model-name -f <location of the file e.g. ./Modelfile>`
 3. `ollama run choose-a-model-name`
 4. Start using the model!
 
@@ -156,7 +156,7 @@ PARAMETER <parameter> <parametervalue>
 | 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       |
+| num_predict    | Maximum number of tokens to predict when generating text. (Default: -1, infinite generation)                                                                                                                                   | 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            |
 | min_p          | Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter *p* represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with *p*=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0) | float      | min_p 0.05            |

llama/README.md

@@ -93,7 +93,7 @@ make -j
 
 ## Vendoring
 
-Ollama currently vendors [llama.cpp](https://github.com/ggerganov/llama.cpp/) and [ggml](https://github.com/ggerganov/ggml) through a vendoring model.  While we generally strive to contribute changes back upstream to avoid drift, we cary a small set of patches which are applied to the tracking commit.  A set of make targets are available to aid developers in updating to a newer tracking commit, or to work on changes.
+Ollama currently vendors [llama.cpp](https://github.com/ggerganov/llama.cpp/) and [ggml](https://github.com/ggerganov/ggml) through a vendoring model. While we generally strive to contribute changes back upstream to avoid drift, we cary a small set of patches which are applied to the tracking commit. A set of make targets are available to aid developers in updating to a newer tracking commit, or to work on changes.
 
 If you update the vendoring code, start by running the following command to establish the tracking llama.cpp repo in the `./vendor/` directory.
 
@@ -105,35 +105,35 @@ make apply-patches
 
 **Pin to new base commit**
 
-To update to a newer base commit, select the upstream git tag or commit and update `llama/vendoring.env`
+To update to a newer base commit, select the upstream git tag or commit and update `llama/vendoring`
 
 #### Applying patches
 
 When updating to a newer base commit, the existing patches may not apply cleanly and require manual merge resolution.
 
-Start by applying the patches.  If any of the patches have conflicts, the `git am` will stop at the first failure.
+Start by applying the patches. If any of the patches have conflicts, the `git am` will stop at the first failure.
 
 ```
 make apply-patches
 ```
 
-If you see an error message about a conflict, go into the `./vendor/` directory, and perform merge resolution using your preferred tool to the patch commit which failed.  Save the file(s) and continue the patch series with `git am --continue` .  If any additional patches fail, follow the same pattern until the full patch series is applied.  Once finished, run a final `create-patches` and `sync` target to ensure everything is updated.
+If you see an error message about a conflict, go into the `./vendor/` directory, and perform merge resolution using your preferred tool to the patch commit which failed. Save the file(s) and continue the patch series with `git am --continue` . If any additional patches fail, follow the same pattern until the full patch series is applied. Once finished, run a final `create-patches` and `sync` target to ensure everything is updated.
 
 ```
 make create-patches sync
 ```
 
-Build and test Ollama, and make any necessary changes to the Go code based on the new base commit.  Submit your PR to the Ollama repo.
+Build and test Ollama, and make any necessary changes to the Go code based on the new base commit. Submit your PR to the Ollama repo.
 
 ### Generating Patches
 
-When working on new fixes or features that impact vendored code, use the following model.  First get a clean tracking repo with all current patches applied:
+When working on new fixes or features that impact vendored code, use the following model. First get a clean tracking repo with all current patches applied:
 
 ```
 make apply-patches
 ```
 
-Now edit the upstream native code in the `./vendor/` directory.  You do not need to commit every change in order to build, a dirty working tree in the tracking repo is OK while developing.  Simply save in your editor, and run the following to refresh the vendored code with your changes, build the backend(s) and build ollama:
+Now edit the upstream native code in the `./vendor/` directory. You do not need to commit every change in order to build, a dirty working tree in the tracking repo is OK while developing. Simply save in your editor, and run the following to refresh the vendored code with your changes, build the backend(s) and build ollama:
 
 ```
 make sync
@@ -142,9 +142,9 @@ go build .
 ```
 
 > [!IMPORTANT]
-> Do **NOT** run `apply-patches` while you're iterating as that will reset the tracking repo.  It will detect a dirty tree and abort, but if your tree is clean and you accidentally ran this target, use `git reflog` to recover your commit(s).
+> Do **NOT** run `apply-patches` while you're iterating as that will reset the tracking repo. It will detect a dirty tree and abort, but if your tree is clean and you accidentally ran this target, use `git reflog` to recover your commit(s).
 
-Iterate until you're ready to submit PRs.  Once your code is ready, commit a change in the `./vendor/` directory, then generate the patches for ollama with
+Iterate until you're ready to submit PRs. Once your code is ready, commit a change in the `./vendor/` directory, then generate the patches for ollama with
 
 ```
 make create-patches
@@ -157,4 +157,4 @@ In your `./vendor/` directory, create a branch, and cherry-pick the new commit t
 
 Commit the changes in the ollama repo and submit a PR to Ollama, which will include the vendored code update with your change, along with the patches.
 
-After your PR upstream is merged, follow the **Updating Base Commit** instructions above, however first remove your patch before running `apply-patches` since the new base commit contains your change already.
+After your PR upstream is merged, follow the **Updating Base Commit** instructions above, however first remove your patch before running `apply-patches` since the new base commit contains your change already.

macapp/src/install.ts

@@ -1,21 +1,35 @@
 import * as fs from 'fs'
-import { exec as cbExec } from 'child_process'
+import { spawn } from 'child_process'
 import * as path from 'path'
-import { promisify } from 'util'
 
 const app = process && process.type === 'renderer' ? require('@electron/remote').app : require('electron').app
 const ollama = app.isPackaged ? path.join(process.resourcesPath, 'ollama') : path.resolve(process.cwd(), '..', 'ollama')
-const exec = promisify(cbExec)
 const symlinkPath = '/usr/local/bin/ollama'
 
-export function installed() {
+export function installed(): boolean {
   return fs.existsSync(symlinkPath) && fs.readlinkSync(symlinkPath) === ollama
 }
 
-export async function install() {
-  const command = `do shell script "mkdir -p ${path.dirname(
-    symlinkPath
-  )} && ln -F -s \\"${ollama}\\" \\"${symlinkPath}\\"" with administrator privileges`
-
-  await exec(`osascript -e '${command}'`)
+function validPath(targetPath: string): boolean {
+  const normalized = path.normalize(targetPath)
+  return !(/[;&|`$(){}[\]<>]/.test(normalized) || normalized.includes('..'))
+}
+
+export async function install(): Promise<void> {
+  if (!validPath(ollama) || !validPath(symlinkPath)) {
+    throw new Error('Invalid path format')
+  }
+
+  await fs.promises.mkdir(path.dirname(symlinkPath), { recursive: true })
+    .catch(err => err.code === 'EEXIST' ? null : Promise.reject(err))
+
+  const process = spawn('osascript', [
+    '-e',
+    `do shell script "ln -F -s '${path.normalize(ollama)}' '${path.normalize(symlinkPath)}'" with administrator privileges`
+  ])
+
+  await new Promise<void>((resolve, reject) => {
+    process.on('error', reject)
+    process.on('close', code => code === 0 ? resolve() : reject(new Error(`Failed with code ${code}`)))
+  })
 }

openai/openai.go

@@ -140,6 +140,7 @@ type CompletionChunk struct {
 
 type ToolCall struct {
 	ID       string `json:"id"`
+	Index    int    `json:"index"`
 	Type     string `json:"type"`
 	Function struct {
 		Name      string `json:"name"`
@@ -206,6 +207,7 @@ func toToolCalls(tc []api.ToolCall) []ToolCall {
 		toolCalls[i].ID = toolCallId()
 		toolCalls[i].Type = "function"
 		toolCalls[i].Function.Name = tc.Function.Name
+		toolCalls[i].Index = tc.Function.Index
 
 		args, err := json.Marshal(tc.Function.Arguments)
 		if err != nil {

openai/openai_test.go

@@ -195,7 +195,86 @@ func TestChatMiddleware(t *testing.T) {
 				Stream: &False,
 			},
 		},
-
+		{
+			name: "chat handler with streaming tools",
+			body: `{
+				"model": "test-model",
+				"messages": [
+					{"role": "user", "content": "What's the weather like in Paris?"}
+				],
+				"stream": true,
+				"tools": [{
+					"type": "function",
+					"function": {
+						"name": "get_weather",
+						"description": "Get the current weather",
+						"parameters": {
+							"type": "object",
+							"required": ["location"],
+							"properties": {
+								"location": {
+									"type": "string",
+									"description": "The city and state"
+								},
+								"unit": {
+									"type": "string",
+									"enum": ["celsius", "fahrenheit"]
+								}
+							}
+						}
+					}
+				}]
+			}`,
+			req: api.ChatRequest{
+				Model: "test-model",
+				Messages: []api.Message{
+					{
+						Role:    "user",
+						Content: "What's the weather like in Paris?",
+					},
+				},
+				Tools: []api.Tool{
+					{
+						Type: "function",
+						Function: api.ToolFunction{
+							Name:        "get_weather",
+							Description: "Get the current weather",
+							Parameters: struct {
+								Type       string   `json:"type"`
+								Required   []string `json:"required"`
+								Properties map[string]struct {
+									Type        string   `json:"type"`
+									Description string   `json:"description"`
+									Enum        []string `json:"enum,omitempty"`
+								} `json:"properties"`
+							}{
+								Type:     "object",
+								Required: []string{"location"},
+								Properties: map[string]struct {
+									Type        string   `json:"type"`
+									Description string   `json:"description"`
+									Enum        []string `json:"enum,omitempty"`
+								}{
+									"location": {
+										Type:        "string",
+										Description: "The city and state",
+									},
+									"unit": {
+										Type: "string",
+										Enum: []string{"celsius", "fahrenheit"},
+									},
+								},
+							},
+						},
+					},
+				},
+				Options: map[string]any{
+					"temperature": 1.0,
+					"top_p":       1.0,
+				},
+				Stream: &True,
+			},
+		},
 		{
 			name: "chat handler error forwarding",
 			body: `{

server/routes.go

@@ -251,6 +251,7 @@ func (s *Server) GenerateHandler(c *gin.Context) {
 
 		var b bytes.Buffer
 		if req.Context != nil {
+			slog.Warn("the context field is deprecated and will be removed in a future version of Ollama")
 			s, err := r.Detokenize(c.Request.Context(), req.Context)
 			if err != nil {
 				c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
@@ -1469,7 +1470,7 @@ func (s *Server) ChatHandler(c *gin.Context) {
 	go func() {
 		defer close(ch)
 		var sb strings.Builder
-		var hasToolCalls bool
+		var toolCallIndex int = 0
 		if err := r.Completion(c.Request.Context(), llm.CompletionRequest{
 			Prompt:  prompt,
 			Images:  images,
@@ -1509,16 +1510,19 @@ func (s *Server) ChatHandler(c *gin.Context) {
 			sb.WriteString(r.Content)
 			if toolCalls, ok := m.parseToolCalls(sb.String()); ok {
 				res.Message.ToolCalls = toolCalls
+				for i := range toolCalls {
+					toolCalls[i].Function.Index = toolCallIndex
+					toolCallIndex++
+				}
 				res.Message.Content = ""
 				sb.Reset()
-				hasToolCalls = true
 				ch <- res
 				return
 			}
 
 			if r.Done {
 				// Send any remaining content if no tool calls were detected
-				if !hasToolCalls {
+				if toolCallIndex == 0 {
 					res.Message.Content = sb.String()
 				}
 				ch <- res