Update app.py

app.py

@@ -1,115 +1,113 @@
-import streamlit as st
-from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-import os
-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
-
-# Load environment variables
-load_dotenv()
-google_api_key = os.getenv("GOOGLE_API_KEY")
-if google_api_key is None:
-    st.error("GOOGLE_API_KEY is not set. Please set it in the .env file.")
-else:
-    genai.configure(api_key=google_api_key)
-
-# Global variable to store chat history
-if 'chat_history' not in st.session_state:
-    st.session_state.chat_history = []
-
-# Function to extract text from PDF files
-def get_pdf_text(pdf_docs):
-    text = ""
-    for pdf in pdf_docs:
-        pdf_reader = PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text += page.extract_text()
-    return text
-
-# Function to split text into chunks
-def get_text_chunks(text):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
-    chunks = text_splitter.split_text(text)
-    return chunks
-
-# Function to create and save a vector store from text chunks
-def get_vector_store(text_chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
-
-# Function to load a question-answering chain
-def get_conversational_chain():
-    prompt_template = """
-    Answer the question as detailed as possible from the provided context, make sure to provide all the details. If the answer is not in
-    provided context, just say, "Answer is not available in the context." Don't provide the wrong answer.\n\n
-    Context:\n{context}\n
-    Question:\n{question}\n
-    Answer:
-    """
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.5)
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-    return chain
-
-# Function to handle user input and generate a response
-def user_input(user_question):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    
-    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
-    docs = new_db.similarity_search(user_question)
-
-    chain = get_conversational_chain()
-
-    response = chain(
-        {"input_documents": docs, "question": user_question},
-        return_only_outputs=True
-    )
-
-    response_text = response["output_text"]
-    
-    # Update chat history
-    st.session_state.chat_history.append({"question": user_question, "answer": response_text})
-    
-    st.write("Reply: ", response_text)
-
-# Function to download chat history as a .txt file
-def download_chat_history_txt():
-    chat_lines = [f"Question: {entry['question']}\nAnswer: {entry['answer']}\n" for entry in st.session_state.chat_history]
-    chat_text = "\n".join(chat_lines)
-    return chat_text
-
-# Main function to run the Streamlit app
-def main():
-    st.set_page_config(page_title="Chat PDF", layout="wide")
-    st.header("Chat with PDF")
-
-    user_question = st.text_input("Ask a Question from the PDF Files")
-
-    if user_question:
-        user_input(user_question)
-
-    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)
-        if st.button("Submit & Process"):
-            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)
-                    st.success("Done")
-            else:
-                st.error("Please upload at least one PDF file.")
-        
-        # Only one download button
-        chat_txt = download_chat_history_txt()
-        st.download_button("Download Chat History (TXT)", chat_txt, file_name="chat_history.txt", mime="text/plain")
-
-if __name__ == "__main__":
-    main()
+import os
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
+from langchain.prompts import PromptTemplate
+from langchain.chains.question_answering import load_qa_chain
+from dotenv import load_dotenv
+from fuzzywuzzy import process
+
+# Load environment variables
+load_dotenv()
+google_api_key = os.getenv("GOOGLE_API_KEY")
+if google_api_key is None:
+    st.error("GOOGLE_API_KEY is not set. Please set it in the .env file.")
+else:
+    from google.generativeai import configure
+    configure(api_key=google_api_key)
+
+# Global variable to store chat history
+if 'chat_history' not in st.session_state:
+    st.session_state.chat_history = []
+
+# Function to extract text from uploaded PDF files
+def extract_text_from_pdfs(files):
+    text = ""
+    for pdf in files:
+        reader = PdfReader(pdf)
+        for page in reader.pages:
+            text += page.extract_text()
+    return text
+
+# Function to split text into manageable chunks
+def split_text_into_chunks(text):
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    return splitter.split_text(text)
+
+# Create and store embeddings
+def create_vector_store(chunks):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vector_store = FAISS.from_texts(chunks, embedding=embeddings)
+    vector_store.save_local("faiss_index")
+    return vector_store
+
+# Load a previously created vector store
+def load_vector_store():
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    return FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+
+# Generate a response using Gemini
+def generate_response(question, vector_store):
+    docs = vector_store.similarity_search(question)
+    chain = get_qa_chain()
+    response = chain({"input_documents": docs, "question": question}, return_only_outputs=True)
+    return response["output_text"]
+
+# Load the question-answering chain
+def get_qa_chain():
+    prompt = PromptTemplate(
+        template="""
+        Use the provided context to answer the question in detail. If the answer is unavailable, respond with "Answer not found in the provided context."
+        Context:\n{context}\n
+        Question:\n{question}\n
+        Answer:""",
+        input_variables=["context", "question"]
+    )
+    llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.5)
+    return load_qa_chain(llm, chain_type="stuff", prompt=prompt)
+
+# Suggest questions or keywords dynamically
+def suggest_keywords(query, all_texts):
+    return process.extract(query, all_texts, limit=5)
+
+# Main app function
+def main():
+    st.set_page_config(page_title="Virtual Agent App", layout="wide")
+    st.title("Virtual Agent Powered by Gemini")
+
+    # Sidebar for uploading files
+    with st.sidebar:
+        st.header("Upload Documents")
+        uploaded_files = st.file_uploader("Upload PDFs", type=["pdf"], accept_multiple_files=True)
+        if st.button("Process Files"):
+            if uploaded_files:
+                raw_text = extract_text_from_pdfs(uploaded_files)
+                text_chunks = split_text_into_chunks(raw_text)
+                create_vector_store(text_chunks)
+                st.success("Documents processed successfully!")
+            else:
+                st.error("Please upload at least one PDF.")
+
+    # Main interface for questions and suggestions
+    user_question = st.text_input("Ask your question here (suggestions below):")
+    if user_question:
+        # Load vector store and generate suggestions
+        vector_store = load_vector_store()
+        suggestions = suggest_keywords(user_question, vector_store.similarity_search(user_question, k=10))
+        st.write("Suggestions:", [s[0] for s in suggestions])
+
+        # Generate and display response
+        if st.button("Submit Question"):
+            response = generate_response(user_question, vector_store)
+            st.write("Answer:", response)
+            st.session_state.chat_history.append({"question": user_question, "answer": response})
+
+    # Chat history download
+    if st.sidebar.button("Download Chat History"):
+        chat_history = "\n".join([f"Q: {item['question']}\nA: {item['answer']}" for item in st.session_state.chat_history])
+        st.sidebar.download_button("Download History", chat_history, file_name="chat_history.txt", mime="text/plain")
+
+if __name__ == "__main__":
+    main()