ReMe/example.env
XiaoHuo888-hue e631a7a547 feat(as_llm): add named OrcaRouter provider
Add an OrcaRouter chat-model provider alongside the existing OpenAI-compatible
wrappers. OrcaRouter is an OpenAI-compatible gateway at
https://api.orcarouter.ai/v1; users can now select it with
LLM_BACKEND=orcarouter instead of pointing an OpenAI wrapper at a custom
base_url.

- OrcaRouterCredential: subclass of OpenAICredential with a default base_url
  of https://api.orcarouter.ai/v1 and an empty-string fallback for the shared
  ${LLM_BASE_URL:-} config key
- OrcaRouterAsLLM: registered as backend "orcarouter" in the as_llm registry
- docs: README (en/zh), quick start (en/zh), example.env
- tests: unit coverage for registration, defaults, and fallback behavior

Live-verified against the OrcaRouter chat/completions endpoint with model
orcarouter/auto.

Signed-off-by: XiaoHuo888-hue <jinhao.song@myflashcloud.com>
2026-08-19 13:05:42 +00:00

14 lines
574 B
Bash

EMBEDDING_API_KEY=sk-xxx
EMBEDDING_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
LLM_API_KEY=sk-xxx
LLM_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
# OpenAI-compatible gateway: LLM_BACKEND=orcarouter
# LLM_API_KEY=sk-orca-...
# LLM_MODEL_NAME=orcarouter/auto
# LLM_BASE_URL is optional and defaults to https://api.orcarouter.ai/v1
# Optional data-source mirrors. Unset variables use the official services.
# HF_MIRROR_URL=https://hf-mirror.com
# ARXIV_MIRROR_URL=https://export.arxiv.org
# TUSHARE_MIRROR_URL=http://112.124.63.173:4000/tushare