# 🐾 Tabby
[](https://opensource.org/licenses/Apache-2.0)
[](https://github.com/psf/black)
Self-hosted AI coding assistant. An opensource / on-prem alternative to GitHub Copilot.
> **Warning**
> Tabby is still in the alpha phase
## Features
* Self-contained, with no need for a DBMS or cloud service
* Web UI for visualizing and configuration models and MLOps.
* OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
* Consumer level GPU supports (FP-16 weight loading with various optimization).
## Demo
## Get started
### Docker
The easiest way of getting started is using the docker image:
```bash
# Create data dir and grant owner to 1000 (Tabby run as uid 1000 in container)
mkdir -p data/hf_cache && chown -R 1000 data
docker run \
-it --rm \
-v ./data:/data \
-v ./data/hf_cache:/home/app/.cache/huggingface \
-p 5000:5000 \
-e MODEL_NAME=TabbyML/J-350M \
tabbyml/tabby
```
To use the GPU backend (triton) for a faster inference speed:
```bash
docker run \
--gpus all \
-it --rm \
-v ./data:/data \
-v ./data/hf_cache:/home/app/.cache/huggingface \
-p 5000:5000 \
-e MODEL_NAME=TabbyML/J-350M \
-e MODEL_BACKEND=triton \
tabbyml/tabby
```
Note: To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.
You can then query the server using `/v1/completions` endpoint:
```bash
curl -X POST http://localhost:5000/v1/completions -H 'Content-Type: application/json' --data '{
"prompt": "def binarySearch(arr, left, right, x):\n mid = (left +"
}'
```
We also provides an interactive playground in admin panel [localhost:5000/_admin](http://localhost:5000/_admin)
### Skypilot
See [deployment/skypilot/README.md](./deployment/skypilot/README.md)
## API documentation
Tabby opens an FastAPI server at [localhost:5000](https://localhost:5000), which embeds an OpenAPI documentation of the HTTP API.
## Development
Go to `development` directory.
```bash
make dev
```
or
```bash
make dev-triton # Turn on triton backend (for cuda env developers)
```