docs: document OrcaRouter as an embedding provider - #280
Open
martinzudergaming-a11y wants to merge 1 commit into
Open
docs: document OrcaRouter as an embedding provider#280martinzudergaming-a11y wants to merge 1 commit into
martinzudergaming-a11y wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This adds OrcaRouter as a documented embedding provider, mirroring how the README already documents named providers like Ollama, OpenAI, Gemini, Voyage, and Nebius.
OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Adding orcarouter as a first-class provider means this project's users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL.
It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.
Why this change
cocoindex-codelets users choose any LiteLLM embedding backend. OrcaRouter serves many embedding models (openai/text-embedding-3-small,google/gemini-embedding-001, …) behind a single OpenAI-compatible endpoint with automatic failover and adaptive routing. It plugs into the existing LiteLLM bridge with a normalopenai/route — no custom code required.What changed
README.md— added an "OrcaRouter" block under "Embedding Models", in the same<details>format as the existing named providers. It explains theopenai/openai/<model-id>model string (LiteLLM strips oneopenai/and OrcaRouter resolves the remaining provider-qualified id) and setsOPENAI_BASE_URLtohttps://api.orcarouter.ai/v1.EMBEDDINGS.md— added an "OrcaRouter (aggregated cloud gateway)" section under "LiteLLM Remote (Cloud Providers)" with a working YAML example.Verification
I verified the documented config against a live OrcaRouter endpoint using the same LiteLLM call path the daemon uses for
ccc init/ccc doctor(litellm.aembeddingwithmodel: openai/openai/text-embedding-3-smallandOPENAI_BASE_URL: https://api.orcarouter.ai/v1). It returned HTTP 200 with 2 embeddings of dimension 1536.All pre-commit hooks that apply to Markdown (trailing-whitespace, end-of-file-fixer) pass on the changed files.
I'm an engineer on the OrcaRouter team.
Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter