Update app.py

app.py

@@ -1,3 +1,4 @@
+# app.py
 import streamlit as st
 import os
 from io import BytesIO
@@ -28,175 +29,118 @@ if "authenticated" not in st.session_state:
 
 # Sidebar
 with st.sidebar:
-    # BSNL Logo (local file with error handling)
     try:
-        st.image(
-            "bsnl_logo.png",
-            width=200
-        )
+        st.image("bsnl_logo.png", width=200)
     except FileNotFoundError:
-        st.warning("BSNL logo not found. Please ensure 'bsnl_logo.png' exists in the project root.")
+        st.warning("Logo missing: 'bsnl_logo.png' not found.")
+
     st.header("RAG Control Panel")
     api_key_input = st.text_input("Enter RAG Access Key", type="password")
-    
-    # Authentication
+
     if st.button("Authenticate"):
         if api_key_input == RAG_ACCESS_KEY:
             st.session_state.authenticated = True
-            st.success("Authentication successful!")
+            st.success("Authenticated successfully!")
         else:
-            st.error("Invalid API key.")
-    
-    # File uploader
+            st.error("Invalid RAG Access Key.")
+
     if st.session_state.authenticated:
-        input_data = st.file_uploader("Upload a PDF file", type=["pdf"])
-        
-        if st.button("Process File") and input_data is not None:
-            try:
-                vector_store = process_input(input_data)
-                st.session_state.vectorstore = vector_store
-                st.success("File processed successfully. You can now ask questions.")
-            except (PermissionError, OSError) as e:
-                st.error(f"File upload failed (Permission or OS error): {str(e)}. Check server permissions or file system access.")
-            except Exception as e:
-                st.error(f"File upload failed (Unexpected error): {str(e)}. Please try again or check server logs.")
-    
-    # Display chat history
-    st.subheader("Chat History")
-    for i, (q, a) in enumerate(st.session_state.history):
-        st.write(f"**Q{i+1}:** {q}")
-        st.write(f"**A{i+1}:** {a}")
-        st.markdown("---")
-
-# Main app
+        input_data = st.file_uploader("Upload PDF file", type=["pdf"])
+
+        if input_data:
+            if input_data.type != "application/pdf":
+                st.error("Only PDF files are allowed.")
+            elif st.button("Process File"):
+                try:
+                    vector_store = process_input(input_data)
+                    st.session_state.vectorstore = vector_store
+                    st.success("File processed successfully. You can now ask questions.")
+                except (PermissionError, OSError) as e:
+                    st.error(f"File error: {str(e)}")
+                except Exception as e:
+                    if "403" in str(e):
+                        st.error("Access Denied (403): Check Hugging Face API token.")
+                    else:
+                        st.error(f"Unexpected error: {str(e)}")
+
+        # Chat History
+        st.subheader("Chat History")
+        for i, (q, a) in enumerate(st.session_state.history):
+            st.write(f"**Q{i+1}:** {q}")
+            st.write(f"**A{i+1}:** {a}")
+            st.markdown("---")
+
+# Main area
 def main():
-    # Inject CSS for simple color scheme and clean styling
-    st.markdown("""
-        <style>
-        @import url('https://fonts.googleapis.com/css2?family=Roboto:wght@400;700&display=swap');
-        .stApp {
-            background-color: #FFFFFF; /* White background */
-            font-family: 'Roboto', sans-serif;
-            color: #333333;
-        }
-        .stTextInput > div > div > input {
-            background-color: #FFFFFF;
-            color: #333333;
-            border-radius: 8px;
-            border: 1px solid #007BFF;
-            padding: 10px;
-            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
-        }
-        .stButton > button {
-            background-color: #007BFF;
-            color: white;
-            border-radius: 8px;
-            padding: 10px 20px;
-            border: none;
-            transition: all 0.3s ease;
-            box-shadow: 0 2px 4px rgba(0,0,0,0.2);
-        }
-        .stButton > button:hover {
-            background-color: #0056b3;
-            transform: scale(1.05);
-        }
-        .stSidebar {
-            background-color: #F5F5F5; /* Light gray */
-            padding: 20px;
-            border-right: 2px solid #007BFF;
-        }
-        h1, h2, h3 {
-            color: #333333;
-        }
-        .stSpinner > div > div {
-            border-color: #007BFF transparent transparent transparent;
-        }
-        </style>
-    """, unsafe_allow_html=True)
-    
     st.title("RAG Q&A App with Mistral AI")
-    st.markdown("Welcome to the BSNL RAG App! Upload your PDF files and ask questions with ease.", unsafe_allow_html=True)
-    
+    st.markdown("Welcome to the BSNL RAG App. Upload a PDF and ask questions!")
+
     if not st.session_state.authenticated:
-        st.warning("Please authenticate with your API key in the sidebar.")
+        st.warning("Please authenticate using your RAG Access Key in the sidebar.")
         return
-    
+
     if st.session_state.vectorstore is None:
         st.info("Please upload and process a PDF file in the sidebar.")
         return
-    
+
     query = st.text_input("Enter your question:")
     if st.button("Submit") and query:
         with st.spinner("Generating answer..."):
-            answer = answer_question(st.session_state.vectorstore, query)
-            st.session_state.history.append((query, answer))
-            st.write("**Answer:**", answer)
+            try:
+                answer = answer_question(st.session_state.vectorstore, query)
+                st.session_state.history.append((query, answer))
+                st.write("**Answer:**", answer)
+            except Exception as e:
+                st.error(f"Failed to generate answer: {str(e)}")
 
 def process_input(input_data):
-    # Create vectorstore directory for FAISS index
-    try:
-        os.makedirs("vectorstore", exist_ok=True)
-        os.chmod("vectorstore", 0o777)  # Ensure write permissions
-    except PermissionError as e:
-        st.error(f"Failed to create vectorstore directory: {str(e)}")
-        raise
-    
-    # Initialize progress bar and status
+    os.makedirs("vectorstore", exist_ok=True)
+    os.chmod("vectorstore", 0o777)
+
     progress_bar = st.progress(0)
-    status = st.status("Processing PDF file...", expanded=True)
-    
-    # Step 1: Read PDF file in memory
+    status = st.status("Processing PDF...", expanded=True)
+
     status.update(label="Reading PDF file...")
-    progress_bar.progress(0.20)
-    
+    progress_bar.progress(0.2)
+
     pdf_reader = PdfReader(BytesIO(input_data.read()))
-    documents = ""
-    for page in pdf_reader.pages:
-        documents += page.extract_text() or ""
-    
-    # Step 2: Split text
-    status.update(label="Splitting text into chunks...")
-    progress_bar.progress(0.40)
-    
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-    texts = text_splitter.split_text(documents)
-    
-    # Step 3: Create embeddings
+    documents = "".join(page.extract_text() or "" for page in pdf_reader.pages)
+
+    status.update(label="Splitting text...")
+    progress_bar.progress(0.4)
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    texts = splitter.split_text(documents)
+
     status.update(label="Creating embeddings...")
-    progress_bar.progress(0.60)
-    
-    hf_embeddings = HuggingFaceEmbeddings(
+    progress_bar.progress(0.6)
+
+    embeddings = HuggingFaceEmbeddings(
         model_name="sentence-transformers/all-mpnet-base-v2",
-        model_kwargs={'device': 'cpu'}
+        model_kwargs={"device": "cpu"}
     )
-    
-    # Step 4: Initialize FAISS vector store
-    status.update(label="Building vector store...")
-    progress_bar.progress(0.80)
-    
-    dimension = len(hf_embeddings.embed_query("sample text"))
+
+    status.update(label="Building FAISS index...")
+    progress_bar.progress(0.8)
+
+    dimension = len(embeddings.embed_query("sample text"))
     index = faiss.IndexFlatL2(dimension)
     vector_store = FAISS(
-        embedding_function=hf_embeddings,
+        embedding_function=embeddings,
         index=index,
         docstore=InMemoryDocstore({}),
         index_to_docstore_id={}
     )
-    
-    # Add texts to vector store
-    uuids = [str(uuid.uuid4()) for _ in range(len(texts))]
+    uuids = [str(uuid.uuid4()) for _ in texts]
     vector_store.add_texts(texts, ids=uuids)
-    
-    # Save vector store locally
+
     status.update(label="Saving vector store...")
-    progress_bar.progress(0.90)
-    
+    progress_bar.progress(0.9)
     vector_store.save_local("vectorstore/faiss_index")
-    
-    # Complete processing
-    status.update(label="Processing complete!", state="complete")
+
+    status.update(label="Done!", state="complete")
     progress_bar.progress(1.0)
-    
+
     return vector_store
 
 def answer_question(vectorstore, query):
@@ -205,14 +149,14 @@ def answer_question(vectorstore, query):
         model_kwargs={"temperature": 0.7, "max_length": 512},
         huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN
     )
-    
+
     retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
-    
+
     prompt_template = PromptTemplate(
         template="Use the provided context to answer the question concisely:\n\nContext: {context}\n\nQuestion: {question}\n\nAnswer:",
         input_variables=["context", "question"]
     )
-    
+
     qa_chain = RetrievalQA.from_chain_type(
         llm=llm,
         chain_type="stuff",
@@ -220,7 +164,7 @@ def answer_question(vectorstore, query):
         return_source_documents=False,
         chain_type_kwargs={"prompt": prompt_template}
     )
-    
+
     result = qa_chain({"query": query})
     return result["result"].split("Answer:")[-1].strip()