forked from phoenix-oss/llama-stack-mirror
# What does this PR do? Create a distribution template using Groq as inference provider. Link to issue: https://github.com/meta-llama/llama-stack/issues/958 ## Test Plan Run `python llama_stack/scripts/distro_codegen.py` to generate run.yaml and build.yaml Test the newly created template by running `llama stack build --template <template-name>` `llama stack run <template-name>`
32 lines
893 B
Python
32 lines
893 B
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 Any, Dict, Optional
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class GroqConfig(BaseModel):
|
|
api_key: Optional[str] = Field(
|
|
# The Groq client library loads the GROQ_API_KEY environment variable by default
|
|
default=None,
|
|
description="The Groq API key",
|
|
)
|
|
|
|
url: str = Field(
|
|
default="https://api.groq.com",
|
|
description="The URL for the Groq AI server",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
|
|
return {
|
|
"url": "https://api.groq.com",
|
|
"api_key": "${env.GROQ_API_KEY}",
|
|
}
|