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
```
54 lines
1.6 KiB
Python
54 lines
1.6 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.
|
|
|
|
from enum import Enum
|
|
|
|
from typing import Any, Dict, List, Optional, Protocol
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.inference import Message
|
|
|
|
|
|
class FilteringFunction(Enum):
|
|
"""The type of filtering function."""
|
|
|
|
none = "none"
|
|
random = "random"
|
|
top_k = "top_k"
|
|
top_p = "top_p"
|
|
top_k_top_p = "top_k_top_p"
|
|
sigmoid = "sigmoid"
|
|
|
|
|
|
@json_schema_type
|
|
class SyntheticDataGenerationRequest(BaseModel):
|
|
"""Request to generate synthetic data. A small batch of prompts and a filtering function"""
|
|
|
|
dialogs: List[Message]
|
|
filtering_function: FilteringFunction = FilteringFunction.none
|
|
model: Optional[str] = None
|
|
|
|
|
|
@json_schema_type
|
|
class SyntheticDataGenerationResponse(BaseModel):
|
|
"""Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."""
|
|
|
|
synthetic_data: List[Dict[str, Any]]
|
|
statistics: Optional[Dict[str, Any]] = None
|
|
|
|
|
|
class SyntheticDataGeneration(Protocol):
|
|
@webmethod(route="/synthetic-data-generation/generate")
|
|
def synthetic_data_generate(
|
|
self,
|
|
dialogs: List[Message],
|
|
filtering_function: FilteringFunction = FilteringFunction.none,
|
|
model: Optional[str] = None,
|
|
) -> Union[SyntheticDataGenerationResponse]: ...
|