phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 01:03:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

bedrock

Browse source
This commit is contained in:
Xi Yan 2024-12-26 18:10:23 -08:00
parent 28428c320a
commit d40e527471
2 changed files with 37 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -4,8 +4,8 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import * # noqa: F403
import json
from typing import AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
from botocore.client import BaseClient
from llama_models.datatypes import CoreModelId
@ -13,6 +13,24 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
from llama_stack.providers.utils.bedrock.client import create_bedrock_client
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,
ModelRegistryHelper,
@ -29,11 +47,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
interleaved_content_as_str,
)
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
from llama_stack.providers.utils.bedrock.client import create_bedrock_client
MODEL_ALIASES = [
build_model_alias(

22
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -4,17 +4,31 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import AsyncGenerator
from typing import AsyncGenerator, List, Optional, Union
from cerebras.cloud.sdk import AsyncCerebras
from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.inference import * # noqa: F403
from llama_models.datatypes import CoreModelId
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionRequest,
CompletionRequest,
CompletionResponse,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,