Upload 3 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY = "AIzaSyCaBo8rVhFgVFpy57oHL3xs-8QXKEOqXIE"

app.py

@@ -0,0 +1,105 @@
+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_dotenv()
+os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=os.getenv("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)
+    vector_store.save_local("faiss_index")
+
+
+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
+    the provided context, just say, "Answer is not available in the context." Don't provide the wrong answer.
+
+    Context:\n {context}?\n
+    Question: \n{question}\n
+
+    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")
+    
+    # Allow dangerous deserialization
+    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
+    )
+
+    print(response)
+    st.write("Reply: ", response.get("output_text", "No output generated"))
+
+
+def main():
+    st.set_page_config("Chat PDF")
+    st.header("Chat with PDF using Gemini💁")
+
+    user_question = st.text_input("Ask a Question from the PDF Files")
+    
+    # Add a Submit button for the user input
+    if st.button("Submit Question"):
+        if user_question:  # Ensure the input is not empty
+            user_input(user_question)
+        else:
+            st.warning("Please enter a question before submitting!")
+
+    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"):
+            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")
+
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+PyPDF2
+langchain
+langchain-google-genai
+langchain-community
+google-generativeai
+python-dotenv
+faiss-cpu