Update app.py

app.py

@@ -23,51 +23,55 @@ if api_key:
 
     if uploaded_file:
         # Load and process the document
-        with st.spinner("Processing document..."):
-            # Save the uploaded file temporarily
-            with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
-                tmp_file.write(uploaded_file.getvalue())
-                tmp_file_path = tmp_file.name
+        try:
+            with st.spinner("Processing document..."):
+                # Save the uploaded file temporarily
+                with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+                    tmp_file.write(uploaded_file.getvalue())
+                    tmp_file_path = tmp_file.name
 
-            # Use the temporary file path with PyPDFLoader
-            loader = PyPDFLoader(tmp_file_path)
-            documents = loader.load()
+                # Use the temporary file path with PyPDFLoader
+                loader = PyPDFLoader(tmp_file_path)
+                documents = loader.load()
 
-            # Remove the temporary file
-            os.unlink(tmp_file_path)
+                # Remove the temporary file
+                os.unlink(tmp_file_path)
 
-            # Split the document into chunks
-            text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-            chunks = text_splitter.split_documents(documents)
+                # Split the document into chunks
+                text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+                chunks = text_splitter.split_documents(documents)
 
-            # Generate embeddings and store them in a vector database
-            embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-            vector_store = FAISS.from_documents(chunks, embeddings)
+                # Generate embeddings and store them in a vector database
+                embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+                vector_store = FAISS.from_documents(chunks, embeddings)
 
-        st.success("Document processed successfully!")
+            st.success("Document processed successfully!")
+        except Exception as e:
+            st.error(f"Error processing document: {e}")
+            st.stop()
 
         # Step 3: Ask Questions About the Document
         st.subheader("💬 Chat with Your Document")
         user_query = st.text_input("Ask a question:")
 
         if user_query:
-            # Set up the RAG pipeline with DeepSeek LLM
-            retriever = vector_store.as_retriever()
-            llm = ChatOpenAI(
-                model="deepseek-chat",
-                openai_api_key=api_key,
-                openai_api_base="https://api.deepseek.com/v1",
-                temperature=0.85,
-                max_tokens=4000  # Ensure compliance with DeepSeek's token limit
-            )
-            qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+            try:
+                # Set up the RAG pipeline with DeepSeek LLM
+                retriever = vector_store.as_retriever()
+                llm = ChatOpenAI(
+                    model="deepseek-chat",
+                    openai_api_key=api_key,
+                    openai_api_base="https://api.deepseek.com/v1",
+                    temperature=0.85,
+                    max_tokens=1000  # Adjust token limit for safety
+                )
+                qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
 
-            # Generate response
-            with st.spinner("Generating response..."):
-                try:
+                # Generate response
+                with st.spinner("Generating response..."):
                     response = qa_chain.run(user_query)
                     st.write(f"**Answer:** {response}")
-                except Exception as e:
-                    st.error(f"Error: {e}")
+            except Exception as e:
+                st.error(f"Error generating response: {e}")
 else:
     st.warning("Please enter your DeepSeek API key to proceed.")