Update app.py

app.py

@@ -2,37 +2,20 @@
 import os
 import warnings
 from dotenv import load_dotenv
-from fastapi import FastAPI, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-from pydantic import BaseModel
+import gradio as gr
 from qdrant_search import QdrantSearch
 from langchain_groq import ChatGroq
 from nomic_embeddings import EmbeddingsModel
-import gradio as gr
-from starlette.middleware.wsgi import WSGIMiddleware
-from starlette.responses import RedirectResponse
 
-# Load environment variables from Hugging Face Secrets
-# No need to use load_dotenv() as Hugging Face handles env vars
+# Load environment variables from .env file
+load_dotenv()
 
 # Suppress FutureWarnings
 warnings.filterwarnings("ignore", category=FutureWarning)
 
-# Disable tokenizers parallelism
+# Disable tokenizers parallelism to avoid potential issues
 os.environ["TOKENIZERS_PARALLELISM"] = "FALSE"
 
-# Initialize FastAPI app
-app = FastAPI()
-
-# Allow CORS for frontend on Vercel or any other frontend
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  # Replace "*" with your frontend URL for better security
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
 # Initialize global variables
 collection_names = ["docs_v1_2", "docs_v2_2", "docs_v3_2"]
 limit = 5
@@ -50,29 +33,26 @@ search = QdrantSearch(
     embeddings=embeddings
 )
 
-# Define request and response models
-class QueryRequest(BaseModel):
-    question: str
+def chat_endpoint(question: str):
+    """
+    Handles the chat functionality by processing the user's question,
+    retrieving relevant documents, generating an answer, and returning sources.
 
-class AnswerResponse(BaseModel):
-    answer: str
-    sources: list
+    Args:
+        question (str): The user's question.
 
-# API endpoint to handle user queries
-@app.post("/api/chat", response_model=AnswerResponse)
-async def chat_endpoint(request: QueryRequest):
-    query = request.question.strip()
+    Returns:
+        Tuple[str, str]: The generated answer and the sources used.
+    """
+    query = question.strip()
     if not query:
-        raise HTTPException(status_code=400, detail="Query cannot be empty.")
+        return "❌ **Error:** Query cannot be empty.", "No sources available."
 
     # Step 1: Retrieve relevant documents from Qdrant
     retrieved_docs = search.query_multiple_collections(query, collection_names, limit)
 
     if not retrieved_docs:
-        return AnswerResponse(
-            answer="⚠️ **No relevant documents found** for your query.",
-            sources=[]
-        )
+        return "⚠️ **No relevant documents found** for your query.", "No sources available."
 
     # Step 2: Prepare the context from retrieved documents
     context = "\n\n".join([doc['text'] for doc in retrieved_docs])
@@ -90,43 +70,19 @@ async def chat_endpoint(request: QueryRequest):
     try:
         answer = llm.invoke(prompt)
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+        return f"⚠️ **Error generating answer:** {str(e)}", "No sources available."
 
     # Prepare sources
-    sources = [
-        {
-            "source": doc['source'],
-            "text": doc['text']
-        } for doc in retrieved_docs
-    ]
-
-    # Return the answer and sources
-    return AnswerResponse(answer=answer.content.strip(), sources=sources)
-
-# Gradio function to wrap around the chat endpoint
-def gradio_chat(question: str):
-    request = QueryRequest(question=question)
-    try:
-        response = chat_endpoint(request)
-        if hasattr(response, '__await__'):
-            import asyncio
-            response = asyncio.run(response)
-        answer = response.answer
-        sources = response.sources
-        # Prepare sources for display
-        sources_md = "\n\n".join([
-            f"**Source:** {src['source']}\n**Excerpt:** {src['text']}"
-            for src in sources
-        ])
-        return answer, sources_md
-    except HTTPException as http_exc:
-        return f"❌ **Error {http_exc.status_code}:** {http_exc.detail}", "No sources available."
-    except Exception as e:
-        return f"⚠️ **Error:** {str(e)}", "No sources available."
+    sources_md = "\n\n".join([
+        f"**Source:** {src['source']}\n**Excerpt:** {src['text']}"
+        for src in retrieved_docs
+    ])
+
+    return answer.content.strip(), sources_md
 
 # Create Gradio Interface
-gradio_app = gr.Interface(
-    fn=gradio_chat,
+interface = gr.Interface(
+    fn=chat_endpoint,
     inputs=gr.Textbox(
         lines=2,
         placeholder="Type your question here...",
@@ -140,16 +96,6 @@ gradio_app = gr.Interface(
     description="Ask questions about the LangChain Python Library and get answers based on the latest documentation."
 )
 
-# Mount Gradio app to FastAPI
-app.mount("/gradio", WSGIMiddleware(gradio_app))
-
-# Redirect root to Gradio interface
-@app.get("/")
-async def root():
-    return RedirectResponse(url="/gradio")
-
-# Only necessary when running locally
-# Remove or comment out when deploying on Hugging Face
+# If running locally, uncomment the following lines:
 # if __name__ == "__main__":
-#     import uvicorn
-#     uvicorn.run("app:app", host="0.0.0.0", port=8000)
+#     interface.launch()