Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

#35: Updated README #36

Merged
merged 5 commits into from
Dec 25, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .go-version
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
1.21
84 changes: 71 additions & 13 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,22 +1,80 @@
# Glide - An LLM Routing Engine
Achieve 100% uptime for your Generative AI applications. Glide sits between your applications and your API endpoint. Pass your model preferences to the API endpoint and your call will be routed to the correct model based on model availability.
# Glide
<div style="text-align: center;">
<img src="docs/images/glide.png" width="400px" alt="Glide GH Header" />
</div>

[![LICENSE](https://img.shields.io/github/license/modelgateway/glide.svg?style=flat-square&color=%2362d0c6)](https://github.com/modelgateway/glide/blob/main/LICENSE)

Glide is a cloud-native open source high-performant model gateway. All LLMOps you needed is packed in one lightweight service.

We take all problems and toll of managing and communicating with external providers out of your applications,
so you could focus solving your core problems.

Glide sits between your application and model providers that you use to seamlessly handle various LLMOps tasks like
model failover, caching, etc.

> [!Warning]
> Glide is under active development right now. Give us a star to support the project ✨

## Features

- **Unified REST API** across providers. Avoid vendor lock-ins and changes in your applications when you adopt new providers.
- **High availability** and **resiliency** working with external model providers. Automatic **fallbacks** on provider failures, rate limits, transient errors. Smart retries to reduce communication latency.
- Support **popular LLM providers**.
- **High performance**. Performance is our priority. We want to keep Glide "invisible" for your latency-wise, while providing rich functionality.
- **Production-ready observability** via OpenTelemetry, emit metrics on models health, allows whitebox monitoring.
- Straightforward and simple maintenance and configuration, API key rotation, etc.

## Supported Providers

|| Provider | Support Status
|---|---|---|
| <img src="docs/images/openai.png" width=18 />| OpenAI | 🏗️ Coming Soon |
| <img src="docs/images/azure.png" width=18>| Azure OpenAI | 🏗️ Coming Soon |
| <img src="docs/images/anthropic.png" width=18>| Anthropic | 🏗️ Coming Soon |
| <img src="docs/images/cohere.png" width=18>| Cohere | 🏗️ Coming Soon|
| <img src="docs/images/bard.png" width=18>| Google Gemini | 🏗️ Coming Soon | |
| <img src="docs/images/localai.png" width=18>| LocalAI | 🏗️ Coming Soon | |
### Large Language Models

<br />
| | Provider | Support Status |
|-----------------------------------------------------|---------------|-----------------|
| <img src="docs/images/openai.svg" width="18" /> | OpenAI | 🏗️ Coming Soon |
| <img src="docs/images/azure.svg" width="18" /> | Azure OpenAI | 🏗️ Coming Soon |
| <img src="docs/images/anthropic.svg" width="18" /> | Anthropic | 🏗️ Coming Soon |
| <img src="docs/images/cohere.png" width="18" /> | Cohere | 🏗️ Coming Soon |
| <img src="docs/images/bard.svg" width="18" /> | Google Gemini | 🏗️ Coming Soon |
| <img src="docs/images/localai.webp" width="18" /> | LocalAI | 🏗️ Coming Soon |


## Get Started

TBU

## Roadmap

- REST API to set primary and secondary models based on LLM API status
- Open an issue if there is a feature you'd like to see
### MVP (Coming soon)

- Unified LLM Chat REST API
- Support for most popular LLM providers
- Seamless model fallbacking
- The Main Load Balancing: Priority, Round Robin, Weighted Round Robin, Latency

### Future

- Exact & Semantic Caching
- Cost Management & Budgeting
- and many more!

Open [an issue](https://github.com/modelgateway/glide/issues) or start [a discussion](https://github.com/modelgateway/glide/discussions)
if there is a feature or an enhancement you'd like to see in Glide.

## Community

- Join Discord for real-time discussions

## Contribute

- Maintainers

- [Roman Hlushko](https://github.com/roma-glushko), Software Engineer, Distributed Systems & MLOps
- [Max Krueger](https://github.com/mkrueger12), Data Engineer, Data Scientist

Thanks everyone for already put their effort to make Glide better and more feature-rich:

<a href="https://github.com/modelgateway/glide/graphs/contributors">
<img src="https://contributors-img.web.app/image?repo=modelgateway/glide" />
</a>

8 changes: 8 additions & 0 deletions docs/images/anthropic.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
1 change: 1 addition & 0 deletions docs/images/azure.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
22 changes: 22 additions & 0 deletions docs/images/bard.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/cohere.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/glide.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/localai.webp
Binary file not shown.
1 change: 1 addition & 0 deletions docs/images/openai.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading