- About DocsGPT
- Features
- Installation
- Usage
- API Documentation
- Contribution Guidelines
- Community and Support
- Roadmap
- Acknowledgments
DocsGPT is a cutting-edge open-source solution that streamlines the process of finding information in project documentation. With its integration of the powerful GPT models, developers can easily ask questions about a project and receive accurate answers.
Say goodbye to time-consuming manual searches, and let DocsGPT help you quickly find the information you need. Try it out and see how it revolutionizes your project documentation experience. Contribute to its development and be a part of the future of AI-powered assistance.
To install DocsGPT, follow the installation instructions based on your platform and environment.
Learn how to use DocsGPT in our usage guide.
For developers, explore the API documentation to integrate DocsGPT into your applications.
We welcome contributions! Read our contribution guidelines to get started.
-
Join our community on Discord.
-
Get personalized support for deploying DocsGPT in a live environment: Support.
-
Email us at contact@arc53.com for assistance or inquiries.
Check our roadmap for upcoming features and milestones. Contribute or create issues to help us improve DocsGPT!
Name | Base Model | Requirements (or similar) |
---|---|---|
Docsgpt-7b-falcon | Falcon-7b | 1xA10G gpu |
Docsgpt-14b | llama-2-14b | 2xA10 gpu's |
Docsgpt-40b-falcon | falcon-40b | 8xA10G gpu's |
If you don't have enough resources to run it, you can use bitsnbytes to quantize.
How to use any other documentation
How to host it locally (so all data will stay on-premises)
-
Application - Flask app (main application).
-
Extensions - Chrome extension.
-
Scripts - Script that creates similarity search index and stores for other libraries.
-
Frontend - Frontend uses Vite and React.
Note: Make sure you have Docker installed
On Mac OS or Linux, write:
./setup.sh
It will install all the dependencies and allow you to download the local model or use OpenAI.
Otherwise, refer to this Guide:
-
Download and open this repository with
git clone https://github.com/arc53/DocsGPT.git
-
Create a
.env
file in your root directory and set the env variableOPENAI_API_KEY
with your OpenAI API key andVITE_API_STREAMING
to true or false, depending on if you want streaming answers or not. It should look like this inside:API_KEY=Yourkey VITE_API_STREAMING=true
You can create this file manually using a text editor or use a command-line text editor like echo
in Windows Command Prompt:
echo API_KEY=Yourkey > .env
echo VITE_API_STREAMING=true >> .env
See optional environment variables in the /.env-template
and/application/.env_sample
files.
-
Run the following command to set up the project and start the application:
./run-with-docker-compose.sh
-
Open your web browser and navigate to http://localhost:5173/.
To stop the application, press Ctrl + C
in your terminal or Command Prompt.
For development, only two containers are used from docker-compose.yaml
(by deleting all services except for Redis and Mongo).
See file docker-compose-dev.yaml.
Run the following commands:
docker compose -f docker-compose-dev.yaml build
docker compose -f docker-compose-dev.yaml up -d
Make sure you have Python 3.10 or 3.11 installed.
-
Export required environment variables or prepare a
.env
file in the/application
folder. You can create a.env
file using Windows Command Prompt like this:echo API_KEY=Yourkey > .env echo EMBEDDINGS_KEY=YourEmbeddingsKey >> .env
Replace Yourkey
and YourEmbeddingsKey
with your actual API keys.
(check out application/core/settings.py
if you want to see more config options.)
- (optional) Create a Python virtual environment:
python -m venv venv
. venv/bin/activate # On linux
venv\Scripts\activate # On Windows
- Change to the
application/
subdir and install dependencies for the backend:
pip install -r application/requirements.txt
-
Run the app using the following command:
flask run --host=0.0.0.0 --port=7091
-
Start the worker with the following command:
celery -A application.app.celery worker -l INFO
Make sure you have Node version 16 or higher.
-
Navigate to the
/frontend
folder. -
Install dependencies by running:
npm install
-
Run the app using:
npm run dev
Built with 🦜️🔗 LangChain