Update app.py

app.py

@@ -4,76 +4,81 @@ from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.chat_models import ChatGroq
 from langchain.prompts import PromptTemplate
-from langchain_community.llms import HuggingFaceEndpoint
 from langchain.chains import RetrievalQA
 
+# PDF to QA chain processor
+def process_file(file_path):
+    loader = PyPDFLoader(file_path)
+    documents = loader.load()
+    cl.run_sync(cl.Message("📄 PDF loaded successfully. Splitting text...").send())
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+
+    cl.run_sync(cl.Message("🔍 Creating embeddings and FAISS vector store...").send())
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    vectorstore = FAISS.from_documents(texts, embeddings)
+
+    cl.run_sync(cl.Message("⚙️ Building RetrievalQA chain...").send())
+
+    prompt_template = """
+    Use the following pieces of context to answer the question at the end.
+    If you don't know the answer, just say you don't know — don't try to make up an answer.
+    
+    {context}
+    
+    Question: {question}
+    Helpful Answer:
+    """
+
+    prompt = PromptTemplate(
+        template=prompt_template,
+        input_variables=["context", "question"]
+    )
+
+    llm = ChatGroq(
+        api_key=os.environ.get("GROQ_API_KEY"),
+        model_name="llama3-8b-8192"
+    )
+
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=vectorstore.as_retriever(search_kwargs={"k": 3}),
+        chain_type_kwargs={"prompt": prompt},
+        return_source_documents=True
+    )
+
+    return qa_chain
+
+# On Chat Start
 @cl.on_chat_start
 async def start():
-    await cl.Message("👋 Welcome! Please upload a PDF to get started.").send()
+    await cl.Message("👋 Welcome! Upload a PDF to begin.").send()
 
     await cl.AskFileMessage(
-        content="📄 Upload a PDF file below:",
+        content="📄 Upload a PDF file below (Max 20 MB):",
         accept=["application/pdf"],
         max_size_mb=20,
         timeout=180
     ).send()
 
+# On User Message
 @cl.on_message
 async def handle_message(message: cl.Message):
     if files := await cl.user_session.get("files"):
         file = files[0]
         file_path = file.path
-        await cl.Message(f"📂 Received file: {file.name}").send()
-
-        try:
-            await cl.Message("📄 PDF loaded successfully. Splitting text...").send()
-            loader = PyPDFLoader(file_path)
-            documents = loader.load()
-
-            text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-            texts = text_splitter.split_documents(documents)
-
-            await cl.Message("🔍 Creating embeddings and FAISS vector store...").send()
-            embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-            vectorstore = FAISS.from_documents(texts, embeddings)
-
-            await cl.Message("⚙️ Building RetrievalQA chain...").send()
-            custom_prompt_template = """
-            Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know.
-            {context}
-            Question: {question}
-            Helpful Answer:
-            """
-            prompt = PromptTemplate(
-                template=custom_prompt_template,
-                input_variables=["context", "question"]
-            )
-
-            llm = HuggingFaceEndpoint(
-                repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
-                temperature=0.5,
-                max_new_tokens=500,
-                top_k=50,
-                huggingfacehub_api_token=os.environ.get("HUGGINGFACEHUB_API_TOKEN")
-            )
-
-            qa = RetrievalQA.from_chain_type(
-                llm=llm,
-                chain_type="stuff",
-                retriever=vectorstore.as_retriever(search_kwargs={"k": 3}),
-                chain_type_kwargs={"prompt": prompt},
-                return_source_documents=True
-            )
-
-            cl.user_session.set("qa_chain", qa)
-            cl.user_session.set("ready", True)
-            await cl.Message("✅ QA chain is ready. You can ask your question now.").send()
-            cl.user_session.set("files", None)
-
-        except Exception as e:
-            await cl.Message(f"❌ Error during processing: {str(e)}").send()
 
+        # Build RAG pipeline
+        qa_chain = await cl.make_async(process_file)(file_path)
+        cl.user_session.set("qa_chain", qa_chain)
+        cl.user_session.set("ready", True)
+
+        await cl.Message(f"✅ File `{file.name}` processed. QA chain is ready. You can now ask your question!").send()
+        cl.user_session.set("files", None)
         return
 
     if not cl.user_session.get("ready"):
@@ -82,9 +87,7 @@ async def handle_message(message: cl.Message):
 
     qa_chain = cl.user_session.get("qa_chain")
     await cl.Message("💬 Thinking...").send()
-    try:
-        response = qa_chain(message.content)
-        answer = response["result"]
-        await cl.Message(f"🧠 Answer: {answer}").send()
-    except Exception as e:
-        await cl.Message(f"❌ Error during QA: {str(e)}").send()
+
+    response = qa_chain(message.content)
+    answer = response["result"]
+    await cl.Message(content=f"🧠 Answer: {answer}").send()