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 ```
70 lines
2.1 KiB
Python
70 lines
2.1 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 typing import Optional
|
|
|
|
from pydantic import BaseModel, Field, SecretStr
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class TGIImplConfig(BaseModel):
|
|
url: str = Field(
|
|
description="The URL for the TGI serving endpoint",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, url: str = "${env.TGI_URL}", **kwargs):
|
|
return {
|
|
"url": url,
|
|
}
|
|
|
|
|
|
@json_schema_type
|
|
class InferenceEndpointImplConfig(BaseModel):
|
|
endpoint_name: str = Field(
|
|
description="The name of the Hugging Face Inference Endpoint in the format of '{namespace}/{endpoint_name}' (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided.",
|
|
)
|
|
api_token: Optional[SecretStr] = Field(
|
|
default=None,
|
|
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
endpoint_name: str = "${env.INFERENCE_ENDPOINT_NAME}",
|
|
api_token: str = "${env.HF_API_TOKEN}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"endpoint_name": endpoint_name,
|
|
"api_token": api_token,
|
|
}
|
|
|
|
|
|
@json_schema_type
|
|
class InferenceAPIImplConfig(BaseModel):
|
|
huggingface_repo: str = Field(
|
|
description="The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct')",
|
|
)
|
|
api_token: Optional[SecretStr] = Field(
|
|
default=None,
|
|
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
repo: str = "${env.INFERENCE_MODEL}",
|
|
api_token: str = "${env.HF_API_TOKEN}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"huggingface_repo": repo,
|
|
"api_token": api_token,
|
|
}
|