DOCUMENT Q&A APP

DESCRIPTION

This Q&A application leverages Langchain, Groq, Hugging Face, and Streamlit to provide intelligent document-based question answering. Users can upload PDF files, and the application uses RAG to answer the user queries based on the attachment.

TOOLS AND MODELS

• LANGCHAIN
• GROQ : (llama-3.1-70b-versatile LLM)
• HUGGING-FACE
• FAISS (VectorDB)
• STREAMLIT

INSTALLING REQUIREMENTS:

pip install -r requirements.txt

GENERATING API KEYS

Generate API keys for

• Groq for inferencing hosted LLM models here.
• Hugging-face embeddings for embedding the documents here.

RUNNING THE APPLICATION

streamlit run app.py

Once the application is running, navigate to localhost to interact with the Document Q&A system.

FUNCTIONALITY

1. Upload a PDF file: Select a PDF document using the file uploader in the sidebar. The app will split the document into manageable chunks for efficient search and retrieval.
2. Ask a question: Once the PDF is processed, type your query in the chat input field. The app will generate a response based on the document's content and chat history.

INTERFACE

HOME:

INPUT:

RESPONSE: