From 8ff78b40f2c45c343ee43b9f94f74d06a38fd8a1 Mon Sep 17 00:00:00 2001
From: JJ Asghar <awesome@ibm.com>
Date: Sat, 15 Feb 2025 16:41:48 -0600
Subject: [PATCH] Added python chat completion example

Added a `python` chat completion example like you have for RAG.
---
 docs/getting-started/api-endpoints.md | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/docs/getting-started/api-endpoints.md b/docs/getting-started/api-endpoints.md
index a342e40..022b09b 100644
--- a/docs/getting-started/api-endpoints.md
+++ b/docs/getting-started/api-endpoints.md
@@ -25,7 +25,8 @@ To ensure secure access to the API, authentication is required 🛡️. You can
 
 - **Endpoint**: `POST /api/chat/completions`
 - **Description**: Serves as an OpenAI API compatible chat completion endpoint for models on Open WebUI including Ollama models, OpenAI models, and Open WebUI Function models.
-- **Example**:
+
+- **Curl Example**:
 
   ```bash
   curl -X POST http://localhost:3000/api/chat/completions \
@@ -41,6 +42,29 @@ To ensure secure access to the API, authentication is required 🛡️. You can
         ]
       }'
   ```
+  
+- **Python Example**:
+  ```python
+  import requests
+  
+  def chat_with_model(token):
+      url = 'http://localhost:3000/api/chat/completions'
+      headers = {
+          'Authorization': f'Bearer {token}',
+          'Content-Type': 'application/json'
+      }
+      data = {
+        "model": "granite3.1-dense:8b",
+        "messages": [
+          {
+            "role": "user",
+            "content": "Why is the sky blue?"
+          }
+        ]
+      }
+      response = requests.post(url, headers=headers, data=data)
+      return response.json()
+  ```
 
 ### 🧩 Retrieval Augmented Generation (RAG)