Abiram965/AIML

Intelligent Query System

This project is an intelligent query system that can answer questions based on the content of a PDF document. It uses a combination of natural language processing models and a vector database to provide accurate and relevant answers.

Features

• —PDF Text Extraction: Extracts text from PDF documents.
• —Text Chunking: Splits the extracted text into smaller, manageable chunks.
• —Vector Embeddings: Converts the text chunks into vector embeddings using Hugging Face's sentence-transformers.
• —Vector Storage: Stores the vector embeddings in a Qdrant vector database.
• —Question Answering: Uses Google's Gemini model to answer questions based on the document's content.
• —FastAPI Backend: Exposes the functionality through a FastAPI backend.

Setup

1. 1.Clone the repository:

    git clone https://github.com/abiram965/intelligent-query-system.git
    cd intelligent-query-system

1. 1.Create a virtual environment and activate it:

    python -m venv venv
    source venv/bin/activate  # On Windows, use `venv\Scripts\activate`

1. 1.Install the dependencies:

    pip install -r requirements.txt

1. 1.Create a `.env` file and add your API keys:

    QDRANT_URL="your_qdrant_url"
    QDRANT_API_KEY="your_qdrant_api_key"
    GEMINI_API_KEY="your_gemini_api_key"

1. 1.Run the FastAPI server:

    uvicorn main:app --reload

API Endpoint

POST /hackrx/run

This endpoint takes a PDF document and a list of questions as input and returns a list of answers.

• —Request Body:

    {
      "documents": "url_to_your_pdf_document",
      "questions": ["Your first question", "Your second question"]
    }

• —Headers:

• —Authorization: Bearer your_auth_token

• —Response:

    {
      "answers": ["Answer to the first question", "Answer to the second question"]
    }

Dependencies

• —fastapi
• —uvicorn
• —pydantic
• —requests
• —pdfplumber
• —python-dotenv
• —langchain-core
• —langchain-huggingface
• —langchain-qdrant
• —qdrant-client
• —google-generativeai
• —sentence-transformers