Create app.py

app.py

@@ -0,0 +1,61 @@
+# app.py
+import os
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from huggingface_hub import InferenceClient
+from typing import Optional
+
+# Initialize FastAPI app
+app = FastAPI(
+    title="LLM Chat API",
+    description="API for getting chat responses from Llama model",
+    version="1.0.0"
+)
+
+class ChatRequest(BaseModel):
+    text: str
+
+class ChatResponse(BaseModel):
+    response: str
+
+def llm_chat_response(text: str) -> str:
+    try:
+        HF_TOKEN = os.getenv("HF_TOKEN")
+        if not HF_TOKEN:
+            raise HTTPException(status_code=500, detail="HF_TOKEN not configured")
+        
+        client = InferenceClient(api_key=HF_TOKEN)
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": text + str('describe in one line only')
+                    }
+                ]
+            }
+        ]
+        
+        response_from_llama = client.chat.completions.create(
+            model="meta-llama/Llama-3.2-11B-Vision-Instruct",
+            messages=messages,
+            max_tokens=500
+        )
+        return response_from_llama.choices[0].message['content']
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/chat", response_model=ChatResponse)
+async def chat(request: ChatRequest):
+    try:
+        response = llm_chat_response(request.text)
+        return ChatResponse(response=response)
+    except HTTPException as he:
+        raise he
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/")
+async def root():
+    return {"message": "Welcome to the LLM Chat API. Use POST /chat endpoint to get responses."}