Update app.py

app.py

@@ -1,128 +1,130 @@
-import streamlit as st
-from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_google_genai import GoogleGenerativeAIEmbeddings
-import google.generativeai as genai
-from langchain.vectorstores import FAISS
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain.chains.question_answering import load_qa_chain
-from langchain.prompts import PromptTemplate
-from dotenv import load_dotenv
-import os
-
-# Load environment variables from .env file
-load_dotenv()
-
-# Fetch the Google API key from the .env file
-api_key = os.getenv("GOOGLE_API_KEY")
-
-# Set the page configuration for the Streamlit app
-st.set_page_config(page_title="Document Genie", layout="wide")
-
-# Header and Instructions
-st.markdown("""
-## Document Genie: Get Instant Insights from Your Documents
-
-This chatbot utilizes the Retrieval-Augmented Generation (RAG) framework with Google's Generative AI model Gemini-PRO. It processes uploaded PDF documents by segmenting them into chunks, creating a searchable vector store, and generating precise answers to your questions. This method ensures high-quality, contextually relevant responses for an efficient user experience.
-
-### How It Works
-
-1. **Upload Your Documents**: You can upload multiple PDF files simultaneously for comprehensive analysis.
-2. **Ask a Question**: After processing the documents, type your question related to the content of your uploaded documents for a detailed answer.
-""")
-
-def get_pdf_text(pdf_docs):
-    """
-    Extract text from uploaded PDF documents.
-    """
-    text = ""
-    for pdf in pdf_docs:
-        pdf_reader = PdfReader(pdf)
-        for page in pdf_reader.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text
-    return text
-
-def get_text_chunks(text):
-    """
-    Split text into manageable chunks for processing.
-    """
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
-    chunks = text_splitter.split_text(text)
-    return chunks
-
-def get_vector_store(text_chunks, api_key):
-    """
-    Create and save a FAISS vector store from text chunks.
-    """
-    try:
-        embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
-        vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-        vector_store.save_local("faiss_index")
-        st.success("FAISS index created and saved successfully.")
-    except Exception as e:
-        st.error(f"Error creating FAISS index: {e}")
-
-def get_conversational_chain(api_key):
-    """
-    Set up the conversational chain using the Gemini-PRO model.
-    """
-    prompt_template = """
-    Answer the question as detailed as possible from the provided context. If the answer is not in the provided context, 
-    say "Answer is not available in the context". Do not provide incorrect information.\n\n
-    Context:\n{context}\n
-    Question:\n{question}\n
-    Answer:
-    """
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, google_api_key=api_key)
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-    return chain
-
-def user_input(user_question, api_key):
-    """
-    Handle user input and generate a response from the chatbot.
-    """
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
-    
-    try:
-        new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
-        docs = new_db.similarity_search(user_question)
-        chain = get_conversational_chain(api_key)
-        response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-        st.write("Reply:", response["output_text"])
-    except ValueError as e:
-        st.error(f"Error loading FAISS index or generating response: {e}")
-
-def main():
-    """
-    Main function to run the Streamlit app.
-    """
-    st.header("AI Chatbot 💁")
-
-    user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
-
-    if user_question:  # Trigger user input function only if there's a question
-        user_input(user_question, api_key)
-
-    with st.sidebar:
-        st.title("Menu:")
-        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True, key="pdf_uploader")
-        
-        if st.button("Submit & Process", key="process_button"):
-            if not api_key:
-                st.error("Google API key is missing. Please add it to the .env file.")
-                return
-            
-            if pdf_docs:
-                with st.spinner("Processing..."):
-                    raw_text = get_pdf_text(pdf_docs)
-                    text_chunks = get_text_chunks(raw_text)
-                    get_vector_store(text_chunks, api_key)
-                    st.success("Processing complete. You can now ask questions based on the uploaded documents.")
-            else:
-                st.error("No PDF files uploaded. Please upload at least one PDF file to proceed.")
-
-if __name__ == "__main__":
-    main()
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+import google.generativeai as genai
+from langchain.vectorstores import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from dotenv import load_dotenv
+import os
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Fetch the Google API key from the .env file
+api_key = os.getenv("GOOGLE_API_KEY")
+
+# Set the page configuration for the Streamlit app
+st.set_page_config(page_title="DocWizard Instant Insights and Analysis", layout="wide")
+
+# Header and Instructions
+st.markdown("""
+## Document Intelligence Explorer: Real-Time Insights and Analysis
+
+This chatbot utilizes the Retrieval-Augmented Generation (RAG) framework with Google's Generative AI model Gemini-PRO. It processes uploaded PDF documents by segmenting them into chunks, creating a searchable vector store, and generating precise answers to your questions. This method ensures high-quality, contextually relevant responses for an efficient user experience.
+
+### How It Works
+
+1. **Upload Your Documents**: You can upload multiple PDF files simultaneously for comprehensive analysis.
+2. **Ask a Question**: After processing the documents, type your question related to the content of your uploaded documents for a detailed answer.
+""")
+
+def get_pdf_text(pdf_docs):
+    """
+    Extract text from uploaded PDF documents.
+    """
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text
+    return text
+
+def get_text_chunks(text):
+    """
+    Split text into manageable chunks for processing.
+    """
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def get_vector_store(text_chunks, api_key):
+    """
+    Create and save a FAISS vector store from text chunks.
+    """
+    try:
+        embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+        vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+        vector_store.save_local("faiss_index")
+        st.success("FAISS index created and saved successfully.")
+    except Exception as e:
+        st.error(f"Error creating FAISS index: {e}")
+
+def get_conversational_chain(api_key):
+    """
+    Set up the conversational chain using the Gemini-PRO model.
+    """
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context. If the answer is not in the provided context, 
+    say "Answer is not available in the context". Do not provide incorrect information.\n\n
+    Context:\n{context}\n
+    Question:\n{question}\n
+    Answer:
+    """
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, google_api_key=api_key)
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+def user_input(user_question, api_key):
+    """
+    Handle user input and generate a response from the chatbot.
+    """
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+    
+    try:
+        new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+        docs = new_db.similarity_search(user_question)
+        chain = get_conversational_chain(api_key)
+        response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+        st.write("Reply:", response["output_text"])
+    except ValueError as e:
+        st.error(f"Error loading FAISS index or generating response: {e}")
+
+def main():
+    """
+    Main function to run the Streamlit app.
+    """
+    st.header("AI Chatbot 💁")
+
+    user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
+
+    if st.button("Generate Text", key="generate_button"):  # Add a button to generate text
+        if user_question:  # Trigger user input function only if there's a question
+            with st.spinner("Generating result..."):  # Display spinner while generating
+                user_input(user_question, api_key)
+
+    with st.sidebar:
+        st.title("Menu:")
+        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True, key="pdf_uploader")
+        
+        if st.button("Submit & Process", key="process_button"):
+            if not api_key:
+                st.error("Google API key is missing. Please add it to the .env file.")
+                return
+            
+            if pdf_docs:
+                with st.spinner("Processing..."):
+                    raw_text = get_pdf_text(pdf_docs)
+                    text_chunks = get_text_chunks(raw_text)
+                    get_vector_store(text_chunks, api_key)
+                    st.success("Processing complete. You can now ask questions based on the uploaded documents.")
+            else:
+                st.error("No PDF files uploaded. Please upload at least one PDF file to proceed.")
+
+if __name__ == "__main__":
+    main()