feat: add OrcaRouter embedding encoder - #4455
Open
bangla24bdrang-lab wants to merge 1 commit into
Open
Conversation
Adds an OpenAI-compatible embedding encoder backed by OrcaRouter (https://www.orcarouter.ai). Like the existing OctoAI embedder it uses the OpenAI SDK against a custom base URL (https://api.orcarouter.ai/v1) and is registered in EMBEDDING_PROVIDER_TO_CLASS_MAP as the "orcarouter" provider. Includes unit tests for embed_documents and embed_query. Co-Authored-By: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The
unstructuredlibrary pre-processes documents for downstream LLM workflows, and itsunstructured.embedmodule exposes embedding encoders so those pipelines can attach vector embeddings to partitioned elements. This PR adds OrcaRouter as a first-class embedding provider, mirroring the existing OctoAI embedder.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
orcarouteras 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.Changes
unstructured/embed/orcarouter.py— newOrcaRouterEmbeddingConfig+OrcaRouterEmbeddingEncoder. It uses the OpenAI SDK directly againsthttps://api.orcarouter.ai/v1(same pattern as the existing OctoAI embedder), with a default model ofopenai/text-embedding-3-small.unstructured/embed/__init__.py— registerorcarouterinEMBEDDING_PROVIDER_TO_CLASS_MAP, next tooctoai.test_unstructured/embed/test_orcarouter.py— unit tests forembed_documentsandembed_query, following the existingtest_octoai.pyshape.CHANGELOG.md/unstructured/__version__.py— bumped to0.27.3.Testing
python3 -m pytest test_unstructured/embed/— 18 passed (including the 2 new tests).ruff checkandruff format --checkon all changed files — clean.embed_queryreturned a 1536-dim vector andembed_documentsembedded 2 elements, both viahttps://api.orcarouter.ai/v1/embeddings.I'm an engineer on the OrcaRouter team.
Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter