Update app.py

app.py

@@ -1,157 +1,88 @@
 # app.py
 import os
-import warnings
 from dotenv import load_dotenv
-import gradio as gr
-from qdrant_search import QdrantSearch
-from langchain_groq import ChatGroq
-from nomic_embeddings import EmbeddingsModel
-
 from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
+from qdrant_search import QdrantSearch
+from langchain_groq import ChatGroq
+from nomic_embeddings import EmbeddingsModel
 
-# Load environment variables
 load_dotenv()
 
-# Suppress FutureWarnings
+import warnings
 warnings.filterwarnings("ignore", category=FutureWarning)
 
-# Disable tokenizers parallelism
 os.environ["TOKENIZERS_PARALLELISM"] = "FALSE"
 
+# Initialize FastAPI app
+app = FastAPI()
+
+# Allow CORS for frontend on Vercel
+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
-
-# Initialize the language model
 llm = ChatGroq(model="mixtral-8x7b-32768")
-
-# Initialize the embeddings model
 embeddings = EmbeddingsModel()
-
-# Initialize Qdrant search with necessary credentials
 search = QdrantSearch(
     qdrant_url=os.environ["QDRANT_CLOUD_URL"],
     api_key=os.environ["QDRANT_API_KEY"],
     embeddings=embeddings
 )
 
-def chat_function(question: str):
-    """
-    Handles the chat functionality by processing the user's question,
-    retrieving relevant documents, generating an answer, and returning sources.
+# Define request and response models
+class QueryRequest(BaseModel):
+    question: str
 
-    Args:
-        question (str): The user's question.
+class AnswerResponse(BaseModel):
+    answer: str
+    sources: list
 
-    Returns:
-        Tuple[str, str]: The generated answer and the sources used.
-    """
-    query = question.strip()
+# API endpoint to handle user queries
+@app.post("/api/chat", response_model=AnswerResponse)
+async def chat_endpoint(request: QueryRequest):
+    query = request.question.strip()
     if not query:
-        return "❌ **Error:** Query cannot be empty.", "No sources available."
+        raise HTTPException(status_code=400, detail="Query cannot be empty.")
 
     # Step 1: Retrieve relevant documents from Qdrant
     retrieved_docs = search.query_multiple_collections(query, collection_names, limit)
 
-    if not retrieved_docs:
-        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])
+    context = "\n".join([doc['text'] for doc in retrieved_docs])
 
     # Step 3: Construct the prompt with context and question
     prompt = (
         "You are LangAssist, a knowledgeable assistant for the LangChain Python Library. "
         "Given the following context from the documentation, provide a helpful answer to the user's question.\n\n"
-        "### Context:\n{context}\n\n"
-        "### Question:\n{question}\n\n"
-        "### Answer:"
+        "Context:\n{context}\n\n"
+        "Question: {question}\n\n"
+        "Answer:"
     ).format(context=context, question=query)
 
     # Step 4: Generate an answer using the language model
     try:
         answer = llm.invoke(prompt)
     except Exception as e:
-        return f"⚠️ **Error generating answer:** {str(e)}", "No sources available."
+        raise HTTPException(status_code=500, detail=str(e))
 
     # Prepare sources
-    sources = "\n\n".join([
-        f"**Source:** {doc['source']}\n**Excerpt:** {doc['text']}"
-        for doc in retrieved_docs
-    ])
-
-    return answer.content.strip(), sources
-
-# Define Pydantic model for request
-class ChatRequest(BaseModel):
-    question: str
-
-# Initialize FastAPI app
-app = FastAPI()
+    sources = [
+        {
+            "source": doc['source'],
+            "text": doc['text']
+        } for doc in retrieved_docs
+    ]
 
-# Define allowed origins
-origins = [
-    "*",  # Allow all origins; for production, specify your frontend domains
-    # Example:
-    # "http://localhost",
-    # "http://localhost:3000",
-    # "https://your-frontend-domain.com",
-]
-
-# Add CORS middleware
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,            # Allows all origins. Replace "*" with specific domains in production.
-    allow_credentials=True,
-    allow_methods=["*"],              # Allows all HTTP methods.
-    allow_headers=["*"],              # Allows all headers.
-)
-
-# Define API endpoint
-@app.post("/api/chat")
-async def api_chat(request: ChatRequest):
-    try:
-        answer, sources = chat_function(request.question)
-        return {"answer": answer, "sources": sources}
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+    # Step 5: Return the answer and sources
+    # return AnswerResponse(answer=answer.strip(), sources=sources)
+    return AnswerResponse(answer=answer.content.strip(), sources=sources)
 
-# Create Gradio Interface
-with gr.Blocks() as demo:
-    gr.Markdown("# 🗨️ LangAssist Chat")
-    gr.Markdown("Ask questions about the LangChain Python Library and get answers based on the latest documentation.")
-
-    with gr.Row():
-        with gr.Column(scale=2):
-            question_input = gr.Textbox(
-                lines=2,
-                placeholder="Type your question here...",
-                label="Your Question"
-            )
-            submit_button = gr.Button("💬 Submit")
-        with gr.Column(scale=3):
-            answer_output = gr.Markdown("### Answer will appear here...")
-            sources_output = gr.Markdown("### Sources will appear here...")
-
-    submit_button.click(
-        fn=chat_function,
-        inputs=question_input,
-        outputs=[answer_output, sources_output]
-    )
-
-    gr.Markdown("""
-    ---
-    ## 📡 API Endpoint
-
-    You can access the API endpoint at `/api/chat`. For example, send a POST request to `http://localhost:8000/api/chat` with JSON body `{"question": "Your question here"}`.
-    """)
-
-# Mount Gradio app on FastAPI
-app = gr.mount_gradio_app(app, demo, path="/gradio")
-
-# To run, use: uvicorn app:app --host 0.0.0.0 --port 8000
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=8000)