Update app3.py

app3.py

@@ -1,13 +1,12 @@
 import streamlit as st
 from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+import os
 from langchain_google_genai import GoogleGenerativeAIEmbeddings
-import google.generativeai as genai
-from langchain.vectorstores import FAISS
+from langchain_community.vectorstores import Chroma
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
-import os
 
 st.set_page_config(page_title="Document Genie", layout="wide")
 
@@ -20,35 +19,12 @@ This chatbot is built using the Retrieval-Augmented Generation (RAG) framework,
 
 Follow these simple steps to interact with the chatbot:
 
-1. **Enter Your API Key**: You'll need a Google API key for the chatbot to access Google's Generative AI models. Obtain your API key https://makersuite.google.com/app/apikey.
-
-2. **Upload Your Documents**: The system accepts multiple PDF files at once, analyzing the content to provide comprehensive insights.
+1. **Upload Your Documents**: The system accepts multiple PDF files at once, analyzing the content to provide comprehensive insights.
 
-3. **Ask a Question**: After processing the documents, ask any question related to the content of your uploaded documents for a precise answer.
+2. **Ask a Question**: After processing the documents, ask any question related to the content of your uploaded documents for a precise answer.
 """)
 
-
-
-# This is the first API key input; no need to repeat it in the main function.
-api_key = st.text_input("Enter your Google API Key:", type="password", key="api_key_input")
-
-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
-
-def get_text_chunks(text):
-    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):
-    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")
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
 
 def get_conversational_chain():
     prompt_template = """
@@ -64,31 +40,42 @@ def get_conversational_chain():
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
     return chain
 
-def user_input(user_question, api_key):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
-    new_db = FAISS.load_local("faiss_index", embeddings)
-    docs = new_db.similarity_search(user_question)
-    chain = get_conversational_chain()
-    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-    st.write("Reply: ", response["output_text"])
 
-def main():
-    st.header("AI clone chatbot💁")
+def get_pdf(pdf_docs,query):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
 
-    user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
+    text_splitter = RecursiveCharacterTextSplitter(
+    # Set a really small chunk size, just to show.
+    chunk_size=500,
+    chunk_overlap=20,
+    separators=["\n\n","\n"," ",".",","])
+    chunks=text_splitter.split_text(text)
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vector = Chroma.from_documents(chunk, embeddings)
+    docs = db3.similarity_search(query)
+  chain = get_conversational_chain()
+  response = chain({"input_documents": docs, "question": query}, return_only_outputs=True)
+  return response
+  #st.write("Reply: ", response["output_text"])
+
+def main():
+    st.header("Chat with your pdf💁")
 
-    if user_question and api_key:  # Ensure API key and user question are provided
-        user_input(user_question, api_key)
+    query = st.text_input("Ask a Question from the PDF Files", key="query")
 
     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") and api_key:  # Check if API key is provided before processing
+        if query and st.button("Submit & Process", key="process_button"):
             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)
+                response = get_pdf(pdf_docs,query)
                 st.success("Done")
+   st.write("Reply: ", response["output_text"])             
+    
 
 if __name__ == "__main__":
     main()