Update app.py

app.py

@@ -31,6 +31,85 @@ if "history" not in st.session_state:
 if "authenticated" not in st.session_state:
     st.session_state.authenticated = False
 
+# PDF processing logic
+def process_input(input_data):
+    # Initialize progress bar and status
+    progress_bar = st.progress(0)
+    status = st.empty()
+    
+    # Step 1: Read PDF file in memory
+    status.text("Reading PDF file...")
+    progress_bar.progress(0.25)
+    
+    pdf_reader = PdfReader(BytesIO(input_data.read()))
+    documents = "".join([page.extract_text() or "" for page in pdf_reader.pages])
+    
+    # Step 2: Split text
+    status.text("Splitting text into chunks...")
+    progress_bar.progress(0.50)
+    
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    texts = text_splitter.split_text(documents)
+    
+    # Step 3: Create embeddings
+    status.text("Creating embeddings...")
+    progress_bar.progress(0.75)
+    
+    hf_embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-mpnet-base-v2",
+        model_kwargs={'device': 'cpu'}
+    )
+    
+    # Step 4: Initialize FAISS vector store
+    status.text("Building vector store...")
+    progress_bar.progress(1.0)
+    
+    dimension = len(hf_embeddings.embed_query("test"))
+    index = faiss.IndexFlatL2(dimension)
+    vector_store = FAISS(
+        embedding_function=hf_embeddings,
+        index=index,
+        docstore=InMemoryDocstore({}),
+        index_to_docstore_id={}
+    )
+    
+    # Add texts to vector store
+    uuids = [str(uuid.uuid4()) for _ in texts]
+    vector_store.add_texts(texts, ids=uuids)
+    
+    # Complete processing
+    status.text("Processing complete!")
+    
+    return vector_store
+
+# Question-answering logic
+def answer_question(vectorstore, query):
+    if not HUGGINGFACEHUB_API_TOKEN:
+        raise RuntimeError("Missing Hugging Face API token. Please set it in your secrets.")
+    
+    llm = HuggingFaceHub(
+        repo_id="mistralai/Mistral-7B-Instruct-v0.1",
+        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 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",
+        retriever=retriever,
+        return_source_documents=False,
+        chain_type_kwargs={"prompt": prompt_template}
+    )
+    
+    result = qa_chain({"query": query})
+    return result["result"].split("Answer:")[-1].strip()
+
 # Sidebar with BSNL logo and authentication
 with st.sidebar:
     try:
@@ -152,84 +231,5 @@ def main():
             except Exception as e:
                 st.error(f"Error generating answer: {str(e)}")
 
-# PDF processing logic
-def process_input(input_data):
-    # Initialize progress bar and status
-    progress_bar = st.progress(0)
-    status = st.empty()
-    
-    # Step 1: Read PDF file in memory
-    status.text("Reading PDF file...")
-    progress_bar.progress(0.25)
-    
-    pdf_reader = PdfReader(BytesIO(input_data.read()))
-    documents = "".join([page.extract_text() or "" for page in pdf_reader.pages])
-    
-    # Step 2: Split text
-    status.text("Splitting text into chunks...")
-    progress_bar.progress(0.50)
-    
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-    texts = text_splitter.split_text(documents)
-    
-    # Step 3: Create embeddings
-    status.text("Creating embeddings...")
-    progress_bar.progress(0.75)
-    
-    hf_embeddings = HuggingFaceEmbeddings(
-        model_name="sentence-transformers/all-mpnet-base-v2",
-        model_kwargs={'device': 'cpu'}
-    )
-    
-    # Step 4: Initialize FAISS vector store
-    status.text("Building vector store...")
-    progress_bar.progress(1.0)
-    
-    dimension = len(hf_embeddings.embed_query("test"))
-    index = faiss.IndexFlatL2(dimension)
-    vector_store = FAISS(
-        embedding_function=hf_embeddings,
-        index=index,
-        docstore=InMemoryDocstore({}),
-        index_to_docstore_id={}
-    )
-    
-    # Add texts to vector store
-    uuids = [str(uuid.uuid4()) for _ in texts]
-    vector_store.add_texts(texts, ids=uuids)
-    
-    # Complete processing
-    status.text("Processing complete!")
-    
-    return vector_store
-
-# Question-answering logic
-def answer_question(vectorstore, query):
-    if not HUGGINGFACEHUB_API_TOKEN:
-        raise RuntimeError("Missing Hugging Face API token. Please set it in your secrets.")
-    
-    llm = HuggingFaceHub(
-        repo_id="mistralai/Mistral-7B-Instruct-v0.1",
-        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 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",
-        retriever=retriever,
-        return_source_documents=False,
-        chain_type_kwargs={"prompt": prompt_template}
-    )
-    
-    result = qa_chain({"query": query})
-    return result["result"].split("Answer:")[-1].strip()
-
 if __name__ == "__main__":
     main()