Update app.py

app.py

@@ -8,81 +8,98 @@ from langchain.prompts import PromptTemplate
 from langchain_community.llms import HuggingFaceEndpoint
 from langchain.chains import RetrievalQA
 
-# PDF processing
+# Helper function to process PDF and build the QA chain
 def process_file(file_path):
-    loader = PyPDFLoader(file_path)
-    documents = loader.load()
-
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    texts = text_splitter.split_documents(documents)
-
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vectorstore = FAISS.from_documents(texts, embeddings)
-
-    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 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
-    )
-
-    return qa
-
-# Chat start
+    try:
+        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)
+
+        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")
+        )
+
+        cl.run_sync(cl.Message("⚙️ Building RetrievalQA chain...").send())
+
+        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.run_sync(cl.Message("✅ QA chain is ready. You can ask your question now.").send())
+
+        return qa
+
+    except Exception as e:
+        cl.run_sync(cl.Message(f"❌ Error processing file: {e}").send())
+        return None
+
+# On chat start — ask user for PDF
 @cl.on_chat_start
 async def start():
     await cl.Message("👋 Welcome! Please upload a PDF to get started.").send()
 
-    msg = await cl.AskFileMessage(
-        content="📄 Upload your PDF file here:",
+    file_message = await cl.AskFileMessage(
+        content="📄 Upload a PDF file below:",
         accept=["application/pdf"],
         max_size_mb=20,
         timeout=180
     ).send()
 
-    if msg and msg.files:
-        file = msg.files[0]
-        qa_chain = process_file(file.path)
+    if file_message.files:
+        file = file_message.files[0]
+        file_path = file.path
+
+        await cl.Message(f"📂 Received file: `{file.name}`. Now processing...").send()
+        qa_chain = 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. You can now ask your questions.").send()
+        if qa_chain:
+            cl.user_session.set("qa_chain", qa_chain)
+            cl.user_session.set("ready", True)
+        else:
+            await cl.Message("⚠️ File could not be processed. Please try again.").send()
     else:
-        await cl.Message("❌ No file was uploaded. Please try again.").send()
+        await cl.Message("⚠️ No file uploaded. Please upload a PDF file to proceed.").send()
 
-# On user message
+# On message — handle question
 @cl.on_message
 async def handle_message(message: cl.Message):
     if not cl.user_session.get("ready"):
-        await cl.Message("⚠️ Please upload a PDF first.").send()
+        await cl.Message("⚠️ Please upload a PDF file first.").send()
         return
 
     qa_chain = cl.user_session.get("qa_chain")
     try:
+        await cl.Message("💬 Thinking...").send()
         response = qa_chain(message.content)
         answer = response["result"]
-        await cl.Message(content=answer).send()
+        await cl.Message(content=f"🧠 Answer: {answer}").send()
     except Exception as e:
-        await cl.Message(content=f"❌ An error occurred while generating a response: {str(e)}").send()
+        await cl.Message(f"❌ Error during question answering: {e}").send()