https://github.com/bhavik-jikadara/multi-files-querybot

The Multi-Files QueryBot is a Python-based tool that allows users to interact with multiple document types, including PDFs, .docx, and .json files, through natural language queries.
https://github.com/bhavik-jikadara/multi-files-querybot

chatbot chatbot-application multiple-pdfs-querybot streamlit-webapp webapplication

Last synced: 6 days ago
JSON representation

The Multi-Files QueryBot is a Python-based tool that allows users to interact with multiple document types, including PDFs, .docx, and .json files, through natural language queries.

• Host: GitHub
• URL: https://github.com/bhavik-jikadara/multi-files-querybot
• Owner: Bhavik-Jikadara
• Created: 2024-06-07T07:58:33.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-10-22T11:46:45.000Z (23 days ago)
• Last Synced: 2024-11-09T04:15:47.136Z (6 days ago)
• Topics: chatbot, chatbot-application, multiple-pdfs-querybot, streamlit-webapp, webapplication
• Language: Jupyter Notebook
• Homepage: https://multi-files-querybot.streamlit.app/
• Size: 240 KB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Multiple PDFs QueryBot

The **Multi-Files QueryBot** is a Python-based tool that allows users to interact with multiple document types, including `PDFs`, `.docx`, and `.json` files, through natural language queries. Users can ask questions based on the content of these documents, and the app provides accurate, context-aware responses.\n* It’s designed to help users efficiently navigate and extract insights from large sets of documents, training them to ask more effective and precise questions.

## How it works?

The application follows these steps to respond to your questions:

- **Files Loading**: The app reads multiple documents and extracts their text content.

- **Text Chunking**: The extracted text is divided into smaller, manageable chunks for efficient processing.

- **Language Model**: The application employs a language model to create vector representations (embeddings) of the text chunks.

- **Similarity Matching**: When a question is asked, the app compares it to the text chunks and identifies those with the highest semantic similarity.

- **Response Generation**: The selected chunks are input into the language model, which generates a response based on the relevant content from the PDFs.

## Dependencies and Installation

To install the MultiPDF Chat App, please follow these steps:

### Step 1: Clone the repository

    | git clone https://github.com/Bhavik-Jikadara/multiple-pdfs-querybot.git

    | cd multiple-pdfs-querybot/

### Step 2: Create a virtualenv (windows user)

    | pip install virtualenv

    | virtualenv venv

    | source venv/Scripts/activate

### Step 3: Install the requirements libraries using pip

    | pip install -r requirements.txt

### Step 4: Type this command and run the project

    | streamlit run app.py

## License

The Multiple PDFs QueryBot is released under the [Apache License 2.0](https://github.com/Bhavik-Jikadara/multiple-pdfs-querybot/blob/main/LICENSE).