phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat(api): Add options for supporting various embedding models (#1192)

Browse source 
We need to support:
- asymmetric embedding models (#934)
- truncation policies (#933)
- varying dimensional output (#932) 

## 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
```
This commit is contained in:
Ashwin Bharambe 2025-02-20 22:27:12 -08:00 • committed by GitHub
parent 6f9d622340
commit 81ce39a607
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 202 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -28,12 +28,14 @@ from llama_stack.apis.inference import (
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
ResponseFormat,
ResponseFormatType,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -383,6 +385,9 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
self,
model_id: str,
contents: List[str] | List[InterleavedContentItem],
text_truncation: Optional[TextTruncation] = TextTruncation.none,
output_dimension: Optional[int] = None,
task_type: Optional[EmbeddingTaskType] = None,
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)