├── .gitignore
├── .env.example
├── gitpush.bat
├── requirements.txt
├── faiss_index
    ├── index.pkl
    └── index.faiss
├── README.md
├── .devcontainer
    └── devcontainer.json
└── app.py


/.gitignore:
--------------------------------------------------------------------------------
1 | env
2 | .env


--------------------------------------------------------------------------------
/.env.example:
--------------------------------------------------------------------------------
1 | GOOGLE_API_KEY=


--------------------------------------------------------------------------------
/gitpush.bat:
--------------------------------------------------------------------------------
1 | git add .
2 | git commit -m %1
3 | git push -u origin main


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kanugurajesh/Document-QA/HEAD/requirements.txt


--------------------------------------------------------------------------------
/faiss_index/index.pkl:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kanugurajesh/Document-QA/HEAD/faiss_index/index.pkl


--------------------------------------------------------------------------------
/faiss_index/index.faiss:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kanugurajesh/Document-QA/HEAD/faiss_index/index.faiss


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Document QA
 2 | 
 3 | <div align=center>
 4 |   <img src="https://github.com/kanugurajesh/Document-QA/assets/77529419/da7d4c4d-3155-4f3a-bfe9-5e85919f59fa" alt="" width=150 height=150>
 5 | </div>
 6 | 
 7 | A document Question Answering application using Gemini Pro vision. This project provides good user interface to interact with gemini pro vision
 8 | 
 9 | ## Screenshots
10 | 
11 | ![Screenshot 2024-01-18 215141](https://github.com/kanugurajesh/Document-QA/assets/77529419/0e4e29db-e862-4cc6-8bbf-ca3da288349e)
12 | 
13 | ![Screenshot 2024-01-18 215207](https://github.com/kanugurajesh/Document-QA/assets/77529419/43247e8e-4f1a-42f2-a9b1-4d3667b20ce1)
14 | 
15 | ## Demo
16 | 
17 | [![Document QA](https://img.youtube.com/vi/mQNUb9Mh2TE/0.jpg)](https://youtu.be/mQNUb9Mh2TE)
18 | 
19 | 


--------------------------------------------------------------------------------
/.devcontainer/devcontainer.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "Python 3",
 3 |   // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
 4 |   "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
 5 |   "customizations": {
 6 |     "codespaces": {
 7 |       "openFiles": [
 8 |         "README.md",
 9 |         "app.py"
10 |       ]
11 |     },
12 |     "vscode": {
13 |       "settings": {},
14 |       "extensions": [
15 |         "ms-python.python",
16 |         "ms-python.vscode-pylance"
17 |       ]
18 |     }
19 |   },
20 |   "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
21 |   "postAttachCommand": {
22 |     "server": "streamlit run app.py --server.enableCORS false --server.enableXsrfProtection false"
23 |   },
24 |   "portsAttributes": {
25 |     "8501": {
26 |       "label": "Application",
27 |       "onAutoForward": "openPreview"
28 |     }
29 |   },
30 |   "forwardPorts": [
31 |     8501
32 |   ]
33 | }


--------------------------------------------------------------------------------
/app.py:
--------------------------------------------------------------------------------
 1 | import streamlit as st
 2 | from PyPDF2 import PdfReader
 3 | from langchain.text_splitter import RecursiveCharacterTextSplitter
 4 | import os
 5 | from langchain_google_genai import GoogleGenerativeAIEmbeddings
 6 | import google.generativeai as genai
 7 | from langchain.vectorstores import FAISS
 8 | from langchain_google_genai import ChatGoogleGenerativeAI
 9 | from langchain.chains.question_answering import load_qa_chain
10 | from langchain.prompts import PromptTemplate
11 | from dotenv import load_dotenv
12 | 
13 | load_dotenv()
14 | os.getenv("GOOGLE_API_KEY")
15 | genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
16 | 
17 | 
18 | def get_pdf_text(pdf_docs):
19 |     text=""
20 |     for pdf in pdf_docs:
21 |         pdf_reader= PdfReader(pdf)
22 |         for page in pdf_reader.pages:
23 |             text+= page.extract_text()
24 |     return  text
25 | 
26 | def get_text_chunks(text):
27 |     text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
28 |     chunks = text_splitter.split_text(text)
29 |     return chunks
30 | 
31 | def get_vector_store(text_chunks):
32 |     embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
33 |     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
34 |     vector_store.save_local("faiss_index")
35 | 
36 | def get_conversational_chain():
37 | 
38 |     prompt_template = """
39 |     Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
40 |     provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
41 |     Context:\n {context}?\n
42 |     Question: \n{question}\n
43 | 
44 |     Answer:
45 |     """
46 | 
47 |     model = ChatGoogleGenerativeAI(model="gemini-pro",
48 |                              temperature=0.3)
49 | 
50 |     prompt = PromptTemplate(template = prompt_template, input_variables = ["context", "question"])
51 |     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
52 | 
53 |     return chain
54 | 
55 | def user_input(user_question):
56 |     embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
57 |     
58 |     new_db = FAISS.load_local("faiss_index", embeddings)
59 |     docs = new_db.similarity_search(user_question)
60 | 
61 |     chain = get_conversational_chain()
62 | 
63 |     
64 |     response = chain(
65 |         {"input_documents":docs, "question": user_question}
66 |         , return_only_outputs=True)
67 | 
68 |     print(response)
69 |     st.write("Reply: ", response["output_text"])
70 | 
71 | def main():
72 |     st.set_page_config("Chat PDF")
73 |     st.header("Upload your pdf files and start asking questions")
74 | 
75 |     user_question = st.text_input("Ask a Question from the PDF Files")
76 | 
77 |     if user_question:
78 |         user_input(user_question)
79 | 
80 |     with st.sidebar:
81 |         st.title("Menu:")
82 |         pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
83 |         if st.button("Submit & Process"):
84 |             with st.spinner("Processing..."):
85 |                 raw_text = get_pdf_text(pdf_docs)
86 |                 text_chunks = get_text_chunks(raw_text)
87 |                 get_vector_store(text_chunks)
88 |                 st.success("Done")
89 | 
90 | if __name__ == "__main__":
91 |     main()


--------------------------------------------------------------------------------