litellm/litellm-rust
yujonglee 83ab0113f0
feat(ocr): add Vertex DeepSeek adapter and remove legacy OCR pipeline (#40509)
* feat(ocr): add Vertex DeepSeek adapter

* fix(ocr): restore stacked CI coverage

* style(ocr): apply workspace rustfmt

* fix(ocr): deduplicate stacked gateway error mapping

* test(ocr): keep response format checks at dispatch

* fix(ocr): initialize gateway input provenance

* refactor(ocr): preserve DeepSeek extra params

* refactor(ocr): align Vertex DeepSeek preparation

* fix(gateway): drop removed OCR credential error variant

* fix(ocr): fail closed for deferred hooks and Vertex destinations

* fix(ocr): preserve DeepSeek credential provenance
2026-09-11 16:22:57 -07:00
..
crates feat(ocr): add Vertex DeepSeek adapter and remove legacy OCR pipeline (#40509) 2026-09-11 16:22:57 -07:00
.gitignore feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033) 2026-06-23 13:16:47 -07:00
ADDING_A_PROVIDER.md docs(litellm-rust): fix the gateway run commands and point ADDING_A_PROVIDER at the one checks runbook 2026-09-03 00:07:19 -07:00
AGENTS.md feat(rust_bridge): count budget-check input tokens in Rust on all LLM routes (#40381) 2026-09-10 13:56:30 -07:00
Cargo.lock feat(ocr): add Vertex Mistral adapter (#40507) 2026-09-11 16:22:56 -07:00
Cargo.toml feat(ocr): add Vertex Mistral adapter (#40507) 2026-09-11 16:22:56 -07:00
CLAUDE.md refactor(rust): extract config crate (#39706) 2026-09-04 08:17:07 -07:00
README.md refactor(rust): extract config crate (#39706) 2026-09-04 08:17:07 -07:00

LiteLLM Rust

This workspace contains the staged Rust implementation for LiteLLM.

litellm-core is the LiteLLM SDK in Rust: one entrypoint per top-level call that makes the LLM call and hands back a typed response, the same shape as litellm.messages() in Python.

let response = litellm_core::messages::messages(MessagesRequest {
    model: "claude-sonnet-4-5",
    body,
    api_key: Some(key),
    ..
})
.await?;

Python continues to own configuration, retries, routing policy, logging, callbacks, spend tracking, and customer plugins until each Rust path has parity coverage and production evidence.

Crates

Crate Role
litellm-core The SDK. Per-route entrypoints (messages::messages()), types, provider transforms (modules under providers/), provider resolution, auth, the provider HTTP call, and the router.
litellm-config Config-loading boundary. Returns resolved deployments and optionally delegates loading to Python.
litellm-ai-gateway The axum server (behind the server feature) and WebSocket hosts. Translates HTTP/WS to core entrypoints; no provider handlers.
litellm-python-interop Domain-neutral PyO3 foundation for GIL handling and typed Python/Serde conversion.
litellm-python-bridge PyO3 cdylib exposing LiteLLM Rust APIs to the Python SDK. Owns API registration, domain wiring, and Python exception mapping.

Dependency direction is acyclic: config depends on core, the gateway depends on config and core, and the Python bridge depends on the domain layers and Python interop.

Layout

crates/
  core/           The SDK: route modules + provider transforms.
    src/messages/   mod.rs (entrypoint), types, transformation, prepare, handler, client
    src/providers/anthropic/messages/transformation.rs
  config/         Config loading and resolved deployments.
  ai-gateway/     Axum server + WebSocket hosts; calls core entrypoints.
  python-interop/ Domain-neutral PyO3 conversion and GIL primitives.
  python-bridge/  PyO3 API adapter for Python LiteLLM.

The folder shape follows the Python provider tree: core/src/providers/<provider>/<route>/transformation.rs. The bridge exposes one function per top-level route, mirroring the core entrypoints.

Checks

Run the commands under "Checks" in CLAUDE.md before pushing Rust changes. That list is the single source of truth and matches what GitHub Actions runs for changes under litellm-rust/.