Practical overview
When it fits
Use the repository when assessing its documented gateway interface or working with an existing deployment that depends on it; account for its deprecated status before adopting it for new infrastructure.
Who it is for
- Developers evaluating or maintaining a gateway layer for AI application inference.
- Teams that need to compare a shared chat-completion interface with direct provider integrations.
Documented uses
- Send chat-completion requests to a provider through a common server endpoint.
- Use REST or gRPC to submit inference requests.
- Review documented routing, load balancing and retry capabilities for model-provider requests.
Requirements & limits
The repository is public and identifies the project as Apache-2.0 licensed. README installation instructions include binaries, platform package managers and Docker.
- The README lists chat-completion support for five providers, while its introductory provider list is broader than the detailed endpoint table.
- The README explicitly marks image, audio, file, fine-tuning and moderation endpoints as unsupported.
- The repository description labels the project deprecated, and the README warns that the early-stage project may break.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Send an OpenAI chat-completion request through the gateway
Use the README's local REST example to submit a chat-completion request to OpenAI via the gateway.
Before you start
- Gateway running at http://localhost:8080.
- An OpenAI API key.
- curl.
Steps
Set the request content type to application/json.
Set the x-ms-provider header to openai and provide the key as a Bearer token in the Authorization header.
POST a JSON body containing a model and messages to http://localhost:8080/v1/chat/completions.
Expected outcome
A chat-completion request is sent to OpenAI through the local gateway endpoint.
Guide limitations
- The README example documents a request but does not establish a successful response.
- The project is explicitly described as deprecated and its README warns that things may break.
Compare options for Model inference and serving
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Gateway — pyadav | Send chat-completion requests to a provider through a common server endpoint. | Server | The repository is public and identifies the project as Apache-2.0 licensed. README installation instructions include binaries, platform package managers and Docker. |
| Morphingdb | Import a libtorch model and create predictions from values in a PostgreSQL table. | Docker, Linux, Self-hosted, Server | The README documents a Docker image and a build-from-repository option, followed by connecting to PostgreSQL and enabling the pgdl extension. |
| Stable Diffusion Tritonserver | Build a Docker image containing the Triton serving setup. | Docker, Linux, Self-hosted, Server | The repository is public and lists an Apache-2.0 license. The documented deployment is self-hosted and uses Docker; no hosted service is described. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 18 October 2026
- Original website title
- pyadav/gateway · Official homepage title · retained in its source language