From 210de0a1c65bce57cd3b29cf22ead402386a01ea Mon Sep 17 00:00:00 2001
From: JMARyA <jmarya@hydrar.de>
Date: Mon, 18 Mar 2024 10:18:06 +0100
Subject: [PATCH] update ollama

---
 technology/applications/utilities/Ollama.md | 86 ++++++++++++++++++++-
 1 file changed, 85 insertions(+), 1 deletion(-)

diff --git a/technology/applications/utilities/Ollama.md b/technology/applications/utilities/Ollama.md
index a046e38..006307e 100644
--- a/technology/applications/utilities/Ollama.md
+++ b/technology/applications/utilities/Ollama.md
@@ -2,7 +2,7 @@
 obj: application
 repo: https://github.com/ollama/ollama
 website: https://ollama.ai
-rev: 2024-02-19
+rev: 2024-03-18
 ---
 
 # Ollama
@@ -1047,6 +1047,90 @@ MESSAGE user Is Ontario in Canada?
 MESSAGE assistant yes
 ```
 
+## OpenAI Compatability
+Ollama now has built-in compatibility with the OpenAI Chat Completions API, making it possible to use more tooling and applications with Ollama locally.
+
+### Usage
+#### OpenAI [Python](../../dev/programming/languages/Python.md) library
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url='http://localhost:11434/v1/',
+
+    # required but ignored
+    api_key='ollama',
+)
+
+chat_completion = client.chat.completions.create(
+    messages=[
+        {
+            'role': 'user',
+            'content': 'Say this is a test',
+        }
+    ],
+    model='llama2',
+)
+```
+
+#### OpenAI JavaScript library
+```js
+import OpenAI from 'openai'
+
+const openai = new OpenAI({
+  baseURL: 'http://localhost:11434/v1/',
+
+  // required but ignored
+  apiKey: 'ollama',
+})
+
+const chatCompletion = await openai.chat.completions.create({
+  messages: [{ role: 'user', content: 'Say this is a test' }],
+  model: 'llama2',
+})
+```
+
+#### [curl](../cli/network/curl.md)
+```sh
+curl http://localhost:11434/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "llama2",
+        "messages": [
+            {
+                "role": "system",
+                "content": "You are a helpful assistant."
+            },
+            {
+                "role": "user",
+                "content": "Hello!"
+            }
+        ]
+    }'
+```
+
+### Model names
+For tooling that relies on default OpenAI model names such as `gpt-3.5-turbo`, use `ollama cp` to copy an existing model name to a temporary name:
+
+```sh
+ollama cp llama2 gpt-3.5-turbo
+```
+
+Afterwards, this new model name can be specified the `model` field:
+```shell
+curl http://localhost:11434/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "gpt-3.5-turbo",
+        "messages": [
+            {
+                "role": "user",
+                "content": "Hello!"
+            }
+        ]
+    }'
+```
+
 ## Libraries & Applications
 - [ollama-rs](https://github.com/pepperoni21/ollama-rs)
 - [ollama-webui](https://github.com/ollama-webui/ollama-webui)