llama-stack/llama_stack/providers/utils/inference
Ashwin Bharambe 6f9d622340
fix(api): update embeddings signature so inputs and outputs list align (#1161)
See Issue #922 

The change is slightly backwards incompatible but no callsite (in our
client codebases or stack-apps) every passes a depth-2
`List[List[InterleavedContentItem]]` (which is now disallowed.)

## Test Plan

```bash
$ cd llama_stack/providers/tests/inference
$ pytest -s -v -k fireworks test_embeddings.py \
   --inference-model nomic-ai/nomic-embed-text-v1.5 --env EMBEDDING_DIMENSION=784
$  pytest -s -v -k together test_embeddings.py \
   --inference-model togethercomputer/m2-bert-80M-8k-retrieval --env EMBEDDING_DIMENSION=784
$ pytest -s -v -k ollama test_embeddings.py \
   --inference-model all-minilm:latest --env EMBEDDING_DIMENSION=784
```

Also ran `tests/client-sdk/inference/test_embeddings.py`
2025-02-20 21:43:13 -08:00
..
__init__.py chore: move all Llama Stack types from llama-models to llama-stack (#1098) 2025-02-14 09:10:59 -08:00
embedding_mixin.py fix(api): update embeddings signature so inputs and outputs list align (#1161) 2025-02-20 21:43:13 -08:00
model_registry.py feat: register embedding models for ollama, together, fireworks (#1190) 2025-02-20 15:39:08 -08:00
openai_compat.py chore: remove llama_models.llama3.api imports from providers (#1107) 2025-02-19 19:01:29 -08:00
prompt_adapter.py fix: pass tool_prompt_format to chat_formatter (#1198) 2025-02-20 21:38:35 -08:00