Upload 2 files

app.py

@@ -0,0 +1,99 @@
+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_community.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 not google_api_key:
+    st.error("Google API Key is not set. Please set the GOOGLE_API_KEY in the .env file.")
+else:
+    genai.configure(api_key=google_api_key)
+
+
+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):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    os.makedirs("faiss_index", exist_ok=True)
+    vector_store.save_local("faiss_index")
+    st.write("FAISS index saved successfully!")
+
+
+def get_conversational_chain():
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context. If the answer is not in the provided context, just say, 
+    'Answer is not available in the context.' Do not provide a wrong answer.
+
+    Context: {context}
+    Question: {question}
+    Answer:
+    """
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
+    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):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    try:
+        new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    except Exception as e:
+        st.error(f"Error loading FAISS index: {e}")
+        return
+    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.set_page_config(page_title="Chat with PDF using Gemini💁", layout="wide")
+    st.header("Chat with your PDF using Gemini 💁")
+    
+    with st.sidebar:
+        st.title("Menu:")
+        pdf_docs = st.file_uploader("Upload your PDF files", 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("Processing Done")
+            else:
+                st.error("Please upload PDF files.")
+
+    st.subheader("Ask a question about your PDFs")
+    user_question = st.text_input("Type your question here:")
+    if user_question:
+        with st.spinner("Getting your answer..."):
+            user_input(user_question)
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+PyPDF2
+langchain-community
+langchain-google-genai
+google-generativeai
+faiss-cpu
+python-dotenv