Refactor app.py with improved model initialization and endpoint structure

- Rename HuggingFace client to 'model' for clarity
- Add docstring to call_model function
- Update generate endpoint route to '/api/generate'
- Remove commented-out test-token endpoint
- Enhance code readability and documentation

app.py

@@ -6,13 +6,22 @@ from langchain_core.messages import HumanMessage, AIMessage
 from langgraph.checkpoint.memory import MemorySaver
 from langgraph.graph import START, MessagesState, StateGraph
 
-# Initialize the HuggingFace client
-client = InferenceClient(
+# Initialize the HuggingFace model
+model = InferenceClient(
     model="HuggingFaceTB/SmolLM2-1.7B-Instruct",
 )
 
 # Define the function that calls the model
 def call_model(state: MessagesState):
+    """
+    Call the model with the given messages
+
+    Args:
+        state: MessagesState
+
+    Returns:
+        dict: A dictionary containing the generated text and the thread ID
+    """
     # Convert LangChain messages to HuggingFace format
     hf_messages = []
     for msg in state["messages"]:
@@ -22,7 +31,7 @@ def call_model(state: MessagesState):
             hf_messages.append({"role": "assistant", "content": msg.content})
     
     # Call the API
-    response = client.chat_completion(
+    response = model.chat_completion(
         messages=hf_messages,
         temperature=0.5,
         max_tokens=64,
@@ -52,13 +61,14 @@ class QueryRequest(BaseModel):
 # Create the FastAPI application
 app = FastAPI(title="LangChain FastAPI", description="API to generate text using LangChain and LangGraph")
 
+# Welcome endpoint
 @app.get("/")
 async def api_home():
     """Welcome endpoint"""
     return {"detail": "Welcome to FastAPI, Langchain, Docker tutorial"}
 
 # Generate endpoint
-@app.post("/generate")
+@app.post("/api/generate")
 async def generate(request: QueryRequest):
     """
     Endpoint to generate text using the language model
@@ -91,20 +101,6 @@ async def generate(request: QueryRequest):
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Error al generar texto: {str(e)}")
 
-# Add an endpoint to test the token directly
-# @app.get("/test-token")
-# async def test_token():
-#     """Endpoint to test the authentication with HuggingFace"""
-#     try:
-#         # Make a simple request to verify that the token works
-#         response = client.chat_completion(
-#             messages=[{"role": "user", "content": "Hello"}],
-#             max_tokens=10
-#         )
-#         return {"status": "success", "message": "Token is valid", "response": response.choices[0].message.content}
-#     except Exception as e:
-#         return {"status": "error", "message": str(e)}
-
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=8000)