feat(embedding): add Ollama tests and multi-provider support#83
Merged
Siddhant-K-code merged 1 commit intoMay 9, 2026
Merged
Conversation
- Add 15 unit tests for the Ollama embedding client (mock HTTP server) - Add --embedding-provider flag to api, serve, and memory commands - Use the embedding registry instead of hardcoding OpenAI in all commands - Accept ollama and cohere as valid providers in config validation - Add base_url field to EmbeddingConfig for custom endpoints Closes #25 Co-authored-by: Ona <[email protected]>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds unit tests for the Ollama embedding client and wires all CLI commands through the embedding provider registry instead of hardcoding OpenAI.
Why
The Ollama client (
pkg/embedding/ollama) shipped without tests. The CLI commands (api,serve,memory) only accepted OpenAI, even though the registry already supported Ollama and Cohere.Changes
--embedding-providerflag added toapi,serve, andmemorycommands (acceptsopenai,ollama,cohere)--embedding-base-urlflag for custom endpoints (e.g.http://localhost:11434for Ollama)ollamaandcohereas valid providersEmbeddingConfig.BaseURLfield added for config file supportUsage
Closes #25