Skip to content

feat: add Requesty LLM provider#671

Open
Thibaultjaigu wants to merge 1 commit into
aurelio-labs:mainfrom
Thibaultjaigu:feat/requesty-llm
Open

feat: add Requesty LLM provider#671
Thibaultjaigu wants to merge 1 commit into
aurelio-labs:mainfrom
Thibaultjaigu:feat/requesty-llm

Conversation

@Thibaultjaigu

Copy link
Copy Markdown

Description

Adds a RequestyLLM provider, mirroring the existing OpenRouterLLM implementation. Requesty exposes an OpenAI-compatible router endpoint (https://router.requesty.ai/v1), so the integration reuses the same openai client pattern already used for OpenRouter — only the base URL, env var, and default model differ.

Changes

  • semantic_router/llms/requesty.py — new RequestyLLM class (same shape as OpenRouterLLM)
  • semantic_router/llms/__init__.py — export RequestyLLM
  • tests/unit/llms/test_llm_requesty.py — unit tests mirroring the OpenRouter test suite

Usage

from semantic_router.llms import RequestyLLM

llm = RequestyLLM(name="openai/gpt-4o-mini")  # reads REQUESTY_API_KEY

Checks

  • make lint clean (black, ruff, mypy all pass on the new files)
  • New unit tests pass (pytest tests/unit/llms/test_llm_requesty.py)

Disclosure

I work at Requesty. Happy to adjust naming, scope, or the default model to match your conventions — or close this if out of scope. Docs: https://docs.requesty.ai

Add RequestyLLM mirroring the existing OpenRouterLLM, using Requesty's
OpenAI-compatible router endpoint (https://router.requesty.ai/v1).

- New semantic_router/llms/requesty.py with RequestyLLM
- Export RequestyLLM from semantic_router.llms
- Unit tests in tests/unit/llms/test_llm_requesty.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant