Update app.py

app.py

@@ -6,6 +6,7 @@ from fastapi.responses import HTMLResponse
 from llama_cpp import Llama
 from pydantic import BaseModel
 import uvicorn
+import json
 
 # Configuration
 MODEL_URL = "https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M.gguf"
@@ -132,17 +133,25 @@ class ChatCompletionResponse(BaseModel):
     choices: list[dict]
     usage: dict
 
-@app.post("/v1/chat/completions")
-async def chat_completion(request: ChatCompletionRequest):
+@app.get("/v1/chat/completions")
+async def chat_completion(
+    messages: str,
+    max_tokens: int = 128,
+    temperature: float = 0.7,
+    top_p: float = 0.9,
+    stream: bool = False
+):
     try:
-        prompt = "\n".join([f"{msg['role']}: {msg['content']}" for msg in request.messages])
+        messages_list = json.loads(messages)
+        
+        prompt = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages_list])
         prompt += "\nassistant:"
 
         response = llm(
             prompt=prompt,
-            max_tokens=request.max_tokens,
-            temperature=request.temperature,
-            top_p=request.top_p,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
             stop=["</s>"]
         )