forked from phoenix-oss/llama-stack-mirror
96e158eaac
This PR does the following: 1) adds the ability to generate embeddings in all supported inference providers. 2) Moves all the memory providers to use the inference API and improved the memory tests to setup the inference stack correctly and use the embedding models This is a merge from #589 and #598
29 lines
851 B
Python
29 lines
851 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 llama_models.schema_utils import json_schema_type
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
@json_schema_type
|
|
class FireworksImplConfig(BaseModel):
|
|
url: str = Field(
|
|
default="https://api.fireworks.ai/inference/v1",
|
|
description="The URL for the Fireworks server",
|
|
)
|
|
api_key: Optional[str] = Field(
|
|
default=None,
|
|
description="The Fireworks.ai API Key",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls) -> Dict[str, Any]:
|
|
return {
|
|
"url": "https://api.fireworks.ai/inference/v1",
|
|
"api_key": "${env.FIREWORKS_API_KEY}",
|
|
}
|