feat: add OrcaRouter as a named LLM provider adapter - #2243
Open
XiaoHuo888-hue wants to merge 2 commits into
Open
feat: add OrcaRouter as a named LLM provider adapter#2243XiaoHuo888-hue wants to merge 2 commits into
XiaoHuo888-hue wants to merge 2 commits into
Conversation
Adds OrcaRouter as a branded OpenAI-compatible LLM adapter, mirroring the existing NVIDIA Build adapter: users pick a model and supply an OrcaRouter API key, and the endpoint (https://api.orcarouter.ai/v1) is preconfigured and overridable. - base1.py: OrcaRouterLLMParameters reusing the shared branded OpenAI-compatible validation helper - llm1/orcarouter.py: OrcaRouterLLMAdapter + schema + icon - llm1/__init__.py: export the new adapter - tests: registration, model prefixing, api_base default/override, and schema checks for the OrcaRouter adapter Co-Authored-By: Claude <noreply@anthropic.com>
|
|
for more information, see https://pre-commit.ci
|
Contributor
|
| Filename | Overview |
|---|---|
| unstract/sdk1/src/unstract/sdk1/adapters/base1.py | Adds OrcaRouter parameters through the existing branded OpenAI-compatible validation path, preserving endpoint overrides and repeated-validation behavior. |
| unstract/sdk1/src/unstract/sdk1/adapters/llm1/init.py | Exports the new adapter while remaining compatible with the category's import-time registration mechanism. |
| unstract/sdk1/src/unstract/sdk1/adapters/llm1/orcarouter.py | Defines unique OrcaRouter metadata, provider identity, adapter type, and icon path following established LLM adapter conventions. |
| unstract/sdk1/src/unstract/sdk1/adapters/llm1/static/orcarouter.json | Adds a configuration schema consistent with the existing branded OpenAI-compatible adapter schema pattern. |
| unstract/sdk1/tests/test_branded_openai_adapters.py | Extends coverage for registration, model prefixing, endpoint fallback and override behavior, and schema defaults. |
Sequence Diagram
sequenceDiagram
participant User
participant UI as Adapter Settings
participant SDK as OrcaRouter Adapter
participant LiteLLM
participant OrcaRouter
User->>UI: Configure model and API key
UI->>SDK: Submit adapter metadata
SDK->>SDK: Apply default API base and custom_openai prefix
SDK->>LiteLLM: Send validated completion parameters
LiteLLM->>OrcaRouter: OpenAI-compatible request
OrcaRouter-->>LiteLLM: Completion response
LiteLLM-->>User: Return completion
Reviews (1): Last reviewed commit: "[pre-commit.ci] auto fixes from pre-comm..." | Re-trigger Greptile
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
2 participants
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
Adds OrcaRouter as a named LLM provider. OrcaRouter is an OpenAI-compatible model routing gateway that exposes 150+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, MiniMax, xAI and others behind a single endpoint and API key, with gateway-level security controls for AI agents.
I'm an engineer on the OrcaRouter team.
What this changes
unstract/sdk1/src/unstract/sdk1/adapters/llm1/orcarouter.py: theOrcaRouterLLMAdapteradapter class (provider idorcarouter, base URLhttps://api.orcarouter.ai/v1)unstract/sdk1/src/unstract/sdk1/adapters/base1.py:OrcaRouterLLMParameters, reusing the shared branded OpenAI-compatible validation helper so the endpoint is preconfigured but overridableunstract/sdk1/src/unstract/sdk1/adapters/llm1/static/orcarouter.json: the adapter form schema (model + API key, reasoning toggle)unstract/sdk1/src/unstract/sdk1/adapters/llm1/__init__.py: exports the new adapterfrontend/public/icons/adapter-icons/OrcaRouter.png: adapter logounstract/sdk1/tests/test_branded_openai_adapters.py: unit tests for registration, model prefixing, api_base default/override, and schemaWhy a separate provider rather than the OpenAI-compatible escape hatch
This mirrors how OpenRouter and NVIDIA Build are wired in this repo — branded adapters with the endpoint preconfigured, so the model picker, docs and config reference stay consistent. OrcaRouter routes through the same
custom_openai/path LiteLLM already uses for NVIDIA Build, with the OrcaRouter base URL pinned as the default.How to use it
sk-orca-).deepseek/deepseek-v4-flashoropenai/gpt-5.5.Verification
pytest unstract/sdk1/tests/test_branded_openai_adapters.py→ 59 passed (including the 5 new OrcaRouter cases; 9 deselected require the fullllama-indexstack not present in the local env)ruff checkon the changed files → no new findings (2 pre-existing import-sort notes on pristinemain)custom_openai/deepseek/deepseek-v4-flash+https://api.orcarouter.ai/v1) with a realsk-orca-key → HTTP 200, valid completion content returned