Update app.py

app.py

@@ -8,7 +8,8 @@ from groq import Groq
 
 # Set up Groq client
 client = Groq(
-    api_key="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")
+    api_key="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"
+)
 
 # Streamlit app
 st.title("RAG-based PDF QA Application")
@@ -18,42 +19,55 @@ uploaded_file = st.file_uploader("Upload a PDF document", type="pdf")
 
 if uploaded_file:
     # Step 2: Extract text from PDF
-    pdf_reader = PdfReader(uploaded_file)
-    text = "\n".join(page.extract_text() for page in pdf_reader.pages if page.extract_text())
-
-    # Step 3: Split text into chunks
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=1000, chunk_overlap=200
-    )
-    chunks = text_splitter.split_text(text)
-
-    # Step 4: Generate embeddings
-    st.text("Generating embeddings...")
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vector_db = FAISS.from_texts(chunks, embeddings)
-
-    st.success("Embeddings generated and stored in vector database.")
-
-    # Step 5: User interaction
-    query = st.text_input("Ask a question based on the uploaded document:")
-    if query:
-        # Retrieve relevant chunks from vector DB
-        docs = vector_db.similarity_search(query, k=3)
-        context = "\n".join(doc.page_content for doc in docs)
-
-        # Use Groq API for response generation
-        chat_completion = client.chat.completions.create(
-            messages=[
-                {"role": "system", "content": "You are a helpful assistant."},
-                {"role": "user", "content": query},
-                {"role": "assistant", "content": context},
-            ],
-            model="llama3-8b-8192",
-            stream=False,
+    try:
+        pdf_reader = PdfReader(uploaded_file)
+        text = "\n".join(
+            page.extract_text() for page in pdf_reader.pages if page.extract_text()
         )
+    except Exception as e:
+        st.error(f"Failed to read PDF: {e}")
+        text = ""
 
-        answer = chat_completion.choices[0].message.content
-        st.text_area("Answer:", value=answer, height=200)
+    if text:
+        # Step 3: Split text into chunks
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=1000, chunk_overlap=200
+        )
+        chunks = text_splitter.split_text(text)
+
+        # Step 4: Generate embeddings
+        st.text("Generating embeddings...")
+        try:
+            embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+            vector_db = FAISS.from_texts(chunks, embeddings)
+            st.success("Embeddings generated and stored in vector database.")
+        except Exception as e:
+            st.error(f"Error generating embeddings: {e}")
+
+        # Step 5: User interaction
+        query = st.text_input("Ask a question based on the uploaded document:")
+        if query:
+            try:
+                # Retrieve relevant chunks from vector DB
+                docs = vector_db.similarity_search(query, k=3)
+                context = "\n".join(doc.page_content for doc in docs)
+
+                # Use Groq API for response generation
+                chat_completion = client.chat.completions.create(
+                    messages=[
+                        {"role": "system", "content": "You are a helpful assistant."},
+                        {"role": "user", "content": query},
+                        {"role": "assistant", "content": context},
+                    ],
+                    model="llama3-8b-8192",
+                    stream=False,
+                )
+
+                answer = chat_completion.choices[0].message.content
+                st.text_area("Answer:", value=answer, height=200)
+            except Exception as e:
+                st.error(f"Error processing query: {e}")
 
 # Footer
 st.caption("Powered by Open Source Models and Groq API.")
+