forked from phoenix-oss/llama-stack-mirror
21bedc1596
* TGI adapter and some refactoring of other inference adapters * Use the lower-level `generate_stream()` method for correct tool calling --------- Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
15 lines
461 B
Python
15 lines
461 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 llama_toolchain.core.datatypes import RemoteProviderConfig
|
|
|
|
|
|
async def get_adapter_impl(config: RemoteProviderConfig, _deps):
|
|
from .tgi import TGIInferenceAdapter
|
|
|
|
impl = TGIInferenceAdapter(config.url)
|
|
await impl.initialize()
|
|
return impl
|