forked from phoenix-oss/llama-stack-mirror
0fefd4390a
# What does this PR do? - Fix TGI adapter ## Test Plan <img width="851" alt="image" src="https://github.com/user-attachments/assets/0084cbc6-6713-4079-b87b-0befd9aca0b0" /> - most inference working - agent test failure due to model outputs ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
69 lines
2.1 KiB
Python
69 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 llama_models.schema_utils import json_schema_type
|
|
from pydantic import BaseModel, Field, SecretStr
|
|
|
|
|
|
@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,
|
|
}
|