Upload 5 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY="AIzaSyADEPJi8dJy685LZdjmpsYuUEa8VnyxaxY"

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.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()
+api_key = os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=api_key)
+
+def get_pdf_text(pdf_docs):
+    """Extract text from uploaded PDF files."""
+    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):
+    """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):
+    """Create a FAISS vector store from 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():
+    """Create a conversational chain with a custom prompt template."""
+    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 answers.
+
+    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):
+    """Process user input, search FAISS index, and generate a response."""
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+
+    # Load FAISS index with deserialization flag
+    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+
+    # Perform similarity search
+    docs = new_db.similarity_search(user_question)
+
+    # Generate response using the conversational chain
+    chain = get_conversational_chain()
+    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+
+    # Display the response
+    st.write("Reply:", response["output_text"])
+
+def main():
+    """Main function to run the Streamlit app."""
+    st.set_page_config("Chat With Multiple PDF")
+    st.header("Chat with Multiple PDF using Gemini💁")
+
+    # User input for questions
+    user_question = st.text_input("Ask a Question from the PDF Files")
+
+    if user_question:
+        user_input(user_question)
+
+    # Sidebar for uploading and processing PDFs
+    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()

index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a9c2684d79fc931ff028b0e1286333e39b05dd146d57d6cbd237ae27eea1d7
+size 346011

requirements.txt

@@ -0,0 +1,51 @@
+streamlit
+google-generativeai
+python-dotenv
+langchain
+PyPDF2
+chromadb
+faiss-cpu
+langchain_google_genai
+langchain
+python-dotenv
+ipykernel
+langchain-community
+bs4
+arxiv
+pymupdf
+wikipedia
+langchain-text-splitters
+langchain-openai
+chromadb
+sentence_transformers
+langchain_huggingface
+faiss-cpu
+langchain_chroma
+streamlit
+langchain_groq
+fastapi
+uvicorn
+langserve[all]
+sse_starlette
+streamlit
+google.generativeai
+arxiv
+wikipedia
+streamlit-pydantic
+validators
+youtube_transcript_api
+pytube
+Unstructured
+yt-dlp
+numexpr
+langchain_huggingface
+huggingface_hub
+duckduckgo-search
+langchain_nvidia_ai_endpoints
+crewai
+crewai_tools
+pinecone
+pinecone-client
+neo4j==5.14
+langchain-google-genai
+