promptforge-gateway 0.1.0

PromptForge inference gateway: routes OpenAI-shaped chat completions to a backend
docs.rs failed to build promptforge-gateway-0.1.0
Please check the build logs for more information.
See Builds for ideas on how to fix a failed build, or Metadata for how to configure docs.rs builds.
If you believe this is docs.rs' fault, open an issue.

promptforge-gateway

Crates.io docs.rs License

The credential-holding inference gateway for PromptForge. It serves an OpenAI-compatible HTTP API that routes chat completions to configured backends, holds every credential, manages a model catalog, runs a built-in web search tool, and optionally spawns local llama-server processes for GGUF models. Nothing above it holds a vendor key. A key rotation touches one file on one host.

Installation

cargo install promptforge-gateway

Usage

promptforge-gateway serve gateway.toml

Configure endpoints, models, and credentials in a single TOML file. The gateway accepts POST /v1/chat/completions and serves a model catalog at GET /v1/models.

See the PromptForge User Guide for full documentation.

Minimum Rust Version

Rust 1.89 or later.

License

Licensed under the Boost Software License 1.0.