Add environment variable loading for HuggingFace token

- Load HuggingFace token from .env file
- Pass token to InferenceClient initialization
- Update generate endpoint route to remove '/api' prefix
- Print token for debugging purposes

app.py

@@ -6,9 +6,17 @@ from langchain_core.messages import HumanMessage, AIMessage
 from langgraph.checkpoint.memory import MemorySaver
 from langgraph.graph import START, MessagesState, StateGraph
 
+import os
+from dotenv import load_dotenv
+load_dotenv()
+
+HUGGINGFACE_TOKEN = os.environ.get("HUGGINGFACE_TOKEN", os.getenv("HUGGINGFACE_TOKEN"))
+print(HUGGINGFACE_TOKEN)
+
 # Initialize the HuggingFace model
 model = InferenceClient(
     model="HuggingFaceTB/SmolLM2-1.7B-Instruct",
+    api_key=os.getenv("HUGGINGFACE_TOKEN")
 )
 
 # Define the function that calls the model
@@ -68,7 +76,7 @@ async def api_home():
     return {"detail": "Welcome to FastAPI, Langchain, Docker tutorial"}
 
 # Generate endpoint
-@app.post("/api/generate")
+@app.post("/generate")
 async def generate(request: QueryRequest):
     """
     Endpoint to generate text using the language model