Skip to main content

No project description provided

Project description



DocChat is a Python application that allows users to interact with documents using natural language. It leverages LangChain, Gradio, and the OpenAI API to create a chat interface for document-based conversations.

Installation

To get started with DocChat, follow these steps:

  1. Clone the repository to your local machine:
    git clone https://github.com/BackyardML/DocChat.git
    
  2. Change the directory to the project folder:
    cd DocChat
    
  3. Install Poetry (if you haven't already):
    pip install poetry
    
  4. Install project dependencies using Poetry:
    poetry install
    
  5. Obtain an API key from OpenAI.

Usage

Running DocChat

You can run DocChat by executing the app.py script:

poetry run python app.py

This will start a Gradio web application with a chat interface that you can access through your web browser.

Interacting with DocChat

  1. Launch the Gradio application by running the app.py script.
  2. Set your OpenAI API key by entering it in the "OpenAI API Key" textbox.
  3. Upload the document you want to chat about using the file uploader.
  4. Click the "Run" button to create a chatbot for the document.
  5. Start chatting with the document! You can type messages in the "Message" textbox, and the chatbot will respond based on the content of the document.
  6. To clear the chat history, click the "Clear" button.

Contact

If you have any questions or need assistance, feel free to contact me at patrik@backyardml.se

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

docchat-0.1.2.tar.gz (3.1 kB view details)

Uploaded Source

Built Distribution

docchat-0.1.2-py3-none-any.whl (3.7 kB view details)

Uploaded Python 3

File details

Details for the file docchat-0.1.2.tar.gz.

File metadata

  • Download URL: docchat-0.1.2.tar.gz
  • Upload date:
  • Size: 3.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.18

File hashes

Hashes for docchat-0.1.2.tar.gz
Algorithm Hash digest
SHA256 1ea6848a17a4f18c0c4b661d1ed3a7984fd7cfe69b20071135262d9831cc7180
MD5 3bb1c5ba3c09b936cf34669622998b0b
BLAKE2b-256 83c702741da336b2f3bc7a9f209f0db52a997537391896b1b67e4bd16a86c224

See more details on using hashes here.

File details

Details for the file docchat-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: docchat-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 3.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.18

File hashes

Hashes for docchat-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 8c507cab9b1b31d1163e94956559f43fc77dd98664bbc3ea63c6028edd9e3ab6
MD5 1f5e54540175b5ea1a6fc9a89aca83b6
BLAKE2b-256 4f7dd6967aa619f2db070099d87f88b4efb0ca66bd8d439336e1ac426f10f9a5

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page