From 02169f3e605a1ba57ce3711e74f241614dc11ab1 Mon Sep 17 00:00:00 2001
From: Roy Han <royjhan02@gmail.com>
Date: Wed, 26 Jun 2024 14:30:28 -0700
Subject: [PATCH 1/4] Update docs

---
 docs/openai.md | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/docs/openai.md b/docs/openai.md
index 59e7d6405..ca56f8aa3 100644
--- a/docs/openai.md
+++ b/docs/openai.md
@@ -27,6 +27,11 @@ chat_completion = client.chat.completions.create(
     ],
     model='llama3',
 )
+
+completion = client.completions.create(
+    model="llama3",
+    prompt="Say this is a test"
+)
 ```
 
 ### OpenAI JavaScript library
@@ -45,6 +50,11 @@ const chatCompletion = await openai.chat.completions.create({
   messages: [{ role: 'user', content: 'Say this is a test' }],
   model: 'llama3',
 })
+
+const completion = await openai.completions.create({
+    model: "llama3",
+    prompt: "Say this is a test.",
+})
 ```
 
 ### `curl`
@@ -65,6 +75,13 @@ curl http://localhost:11434/v1/chat/completions \
             }
         ]
     }'
+
+curl https://api.openai.com/v1/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "llama3",
+        "prompt": "Say this is a test"
+    }'
 ```
 
 ## Endpoints
@@ -107,6 +124,40 @@ curl http://localhost:11434/v1/chat/completions \
 - `finish_reason` will always be `stop`
 - `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached
 
+### `/v1/completions`
+
+#### Supported features
+
+- [x] Completions
+- [x] Streaming
+- [x] JSON mode
+- [x] Reproducible outputs
+- [ ] Logprobs
+
+#### Supported request fields
+
+- [x] `model`
+- [x] `prompt`
+- [x] `frequency_penalty`
+- [x] `presence_penalty`
+- [x] `seed`
+- [x] `stop`
+- [x] `stream`
+- [x] `temperature`
+- [x] `top_p`
+- [x] `max_tokens`
+- [ ] `best_of`
+- [ ] `echo`
+- [ ] `suffix`
+- [ ] `logit_bias`
+- [ ] `user`
+- [ ] `n`
+
+#### Notes
+
+- `prompt` currently only accepts a string
+- `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached
+
 ## Models
 
 Before using a model, pull it locally `ollama pull`:

From 105e36765d2b56a4c6ad4901e9a56adb61b7f0ac Mon Sep 17 00:00:00 2001
From: Roy Han <royjhan02@gmail.com>
Date: Wed, 3 Jul 2024 15:03:54 -0700
Subject: [PATCH 2/4] token bug corrected

---
 docs/openai.md | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/docs/openai.md b/docs/openai.md
index 318ed71be..11e10e4c7 100644
--- a/docs/openai.md
+++ b/docs/openai.md
@@ -119,10 +119,6 @@ curl https://api.openai.com/v1/completions \
 - [ ] `user`
 - [ ] `n`
 
-#### Notes
-
-- `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached
-
 ### `/v1/completions`
 
 #### Supported features
@@ -155,7 +151,6 @@ curl https://api.openai.com/v1/completions \
 #### Notes
 
 - `prompt` currently only accepts a string
-- `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached
 
 ## Models
 

From 04cde43b2a1bfab26d3543981bb58318dac3a72e Mon Sep 17 00:00:00 2001
From: royjhan <65097070+royjhan@users.noreply.github.com>
Date: Mon, 8 Jul 2024 14:44:16 -0700
Subject: [PATCH 3/4] Update docs/openai.md

---
 docs/openai.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/openai.md b/docs/openai.md
index 11e10e4c7..0dd835f14 100644
--- a/docs/openai.md
+++ b/docs/openai.md
@@ -76,7 +76,7 @@ curl http://localhost:11434/v1/chat/completions \
         ]
     }'
 
-curl https://api.openai.com/v1/completions \
+curl https://localhost:11434/v1/completions \
     -H "Content-Type: application/json" \
     -d '{
         "model": "llama3",

From 2644c4e682978be7731fd4528a1eba018c3bff6b Mon Sep 17 00:00:00 2001
From: royjhan <65097070+royjhan@users.noreply.github.com>
Date: Mon, 8 Jul 2024 14:46:05 -0700
Subject: [PATCH 4/4] Update docs/openai.md

---
 docs/openai.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/openai.md b/docs/openai.md
index 0dd835f14..d9265c6b3 100644
--- a/docs/openai.md
+++ b/docs/openai.md
@@ -76,7 +76,7 @@ curl http://localhost:11434/v1/chat/completions \
         ]
     }'
 
-curl https://localhost:11434/v1/completions \
+curl http://localhost:11434/v1/completions \
     -H "Content-Type: application/json" \
     -d '{
         "model": "llama3",