forked from phoenix-oss/llama-stack-mirror
8de8eb03c8
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
49 lines
1.4 KiB
Python
49 lines
1.4 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import logging
|
|
from typing import List
|
|
|
|
from llama_stack.apis.inference import (
|
|
EmbeddingsResponse,
|
|
InterleavedContent,
|
|
ModelStore,
|
|
)
|
|
|
|
EMBEDDING_MODELS = {}
|
|
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
|
|
class SentenceTransformerEmbeddingMixin:
|
|
model_store: ModelStore
|
|
|
|
async def embeddings(
|
|
self,
|
|
model_id: str,
|
|
contents: List[InterleavedContent],
|
|
) -> EmbeddingsResponse:
|
|
model = await self.model_store.get_model(model_id)
|
|
embedding_model = self._load_sentence_transformer_model(
|
|
model.provider_resource_id
|
|
)
|
|
embeddings = embedding_model.encode(contents)
|
|
return EmbeddingsResponse(embeddings=embeddings)
|
|
|
|
def _load_sentence_transformer_model(self, model: str) -> "SentenceTransformer":
|
|
global EMBEDDING_MODELS
|
|
|
|
loaded_model = EMBEDDING_MODELS.get(model)
|
|
if loaded_model is not None:
|
|
return loaded_model
|
|
|
|
log.info(f"Loading sentence transformer for {model}...")
|
|
from sentence_transformers import SentenceTransformer
|
|
|
|
loaded_model = SentenceTransformer(model)
|
|
EMBEDDING_MODELS[model] = loaded_model
|
|
return loaded_model
|