forked from phoenix-oss/llama-stack-mirror
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
51 lines
1.5 KiB
Python
51 lines
1.5 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, Union
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.inference import Message
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
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]: ...
|