llama-stack-mirror/tests
Francisco Arceo 554ada57b0
chore: Add OpenAI compatibility for Ollama embeddings (#2440)
# What does this PR do?
This PR adds OpenAI compatibility for Ollama embeddings. Closes
https://github.com/meta-llama/llama-stack/issues/2428

Summary of changes:
- `llama_stack/providers/remote/inference/ollama/ollama.py`
- Implements the OpenAI embeddings endpoint for Ollama, replacing the
NotImplementedError with a full function that validates the model,
prepares parameters, calls the client, encodes embedding data
(optionally in base64), and returns a correctly structured response.
- Updates import statements to include the new embedding response
utilities.

- `llama_stack/providers/utils/inference/litellm_openai_mixin.py`
- Refactors the embedding data encoding logic to use a new shared
utility (`b64_encode_openai_embeddings_response`) instead of inline
base64 encoding and packing logic.
   - Cleans up imports accordingly.

- `llama_stack/providers/utils/inference/openai_compat.py`
- Adds `b64_encode_openai_embeddings_response` to handle encoding OpenAI
embedding outputs (including base64 support) in a reusable way.
- Adds `prepare_openai_embeddings_params` utility for standardizing
embedding parameter preparation.
   - Updates imports to include the new embedding data class.

- `tests/integration/inference/test_openai_embeddings.py`
- Removes `"remote::ollama"` from the list of providers that skip OpenAI
embeddings tests, since support is now implemented.

## Note

There was one minor issue, which required me to override the
`OpenAIEmbeddingsResponse.model` name with
`self._get_model(model).identifier` name, which is very unsatisfying.

## Test Plan
Unit Tests and integration tests

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
2025-06-13 14:28:51 -04:00
..
client-sdk/post_training feat: Add nemo customizer (#1448) 2025-03-25 11:01:10 -07:00
common feat(responses): implement full multi-turn support (#2295) 2025-06-02 15:35:49 -07:00
external-provider/llama-stack-provider-ollama chore: mark blobpath as optional (#2271) 2025-05-27 10:55:24 +02:00
integration chore: Add OpenAI compatibility for Ollama embeddings (#2440) 2025-06-13 14:28:51 -04:00
unit feat(auth): allow token to be provided for use against jwks endpoint (#2394) 2025-06-13 10:13:41 +02:00
verifications feat: Structured output for Responses API (#2324) 2025-06-03 14:43:00 -07:00
__init__.py refactor(test): introduce --stack-config and simplify options (#1404) 2025-03-05 17:02:02 -08:00
Containerfile ci: use ollama container image with loaded models (#2410) 2025-06-06 12:08:20 +02:00
README.md docs: revamp testing documentation (#2155) 2025-05-13 11:28:29 -07:00

Llama Stack Tests

Llama Stack has multiple layers of testing done to ensure continuous functionality and prevent regressions to the codebase.

Testing Type Details
Unit unit/README.md
Integration integration/README.md
Verification verifications/README.md