mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
Bump version to 0.0.24 (#94)
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
poegej
GitHub
parent
ed8d10775a
commit
95abbf576b
7 changed files with 998 additions and 0 deletions
|
|
@ -0,0 +1,10 @@
|
|||
name: local-bedrock-conda-example
|
||||
distribution_spec:
|
||||
description: Use Amazon Bedrock APIs.
|
||||
providers:
|
||||
inference: remote::bedrock
|
||||
memory: meta-reference
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
image_type: conda
|
||||
17
llama_stack/providers/adapters/inference/bedrock/__init__.py
Normal file
17
llama_stack/providers/adapters/inference/bedrock/__init__.py
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
# 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 .bedrock import BedrockInferenceAdapter
|
||||
from .config import BedrockConfig
|
||||
|
||||
|
||||
async def get_adapter_impl(config: BedrockConfig, _deps):
|
||||
assert isinstance(config, BedrockConfig), f"Unexpected config type: {type(config)}"
|
||||
|
||||
impl = BedrockInferenceAdapter(config)
|
||||
|
||||
await impl.initialize()
|
||||
|
||||
return impl
|
||||
457
llama_stack/providers/adapters/inference/bedrock/bedrock.py
Normal file
457
llama_stack/providers/adapters/inference/bedrock/bedrock.py
Normal file
|
|
@ -0,0 +1,457 @@
|
|||
# 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 * # noqa: F403
|
||||
|
||||
import boto3
|
||||
from botocore.client import BaseClient
|
||||
from botocore.config import Config
|
||||
|
||||
from llama_models.llama3.api.chat_format import ChatFormat
|
||||
from llama_models.llama3.api.tokenizer import Tokenizer
|
||||
from llama_models.sku_list import resolve_model
|
||||
|
||||
from llama_stack.apis.inference import * # noqa: F403
|
||||
from llama_stack.providers.adapters.inference.bedrock.config import BedrockConfig
|
||||
|
||||
# mapping of Model SKUs to ollama models
|
||||
BEDROCK_SUPPORTED_MODELS = {
|
||||
"Meta-Llama3.1-8B-Instruct": "meta.llama3-1-8b-instruct-v1:0",
|
||||
"Meta-Llama3.1-70B-Instruct": "meta.llama3-1-70b-instruct-v1:0",
|
||||
"Meta-Llama3.1-405B-Instruct": "meta.llama3-1-405b-instruct-v1:0",
|
||||
}
|
||||
|
||||
|
||||
class BedrockInferenceAdapter(Inference):
|
||||
|
||||
@staticmethod
|
||||
def _create_bedrock_client(config: BedrockConfig) -> BaseClient:
|
||||
retries_config = {
|
||||
k: v
|
||||
for k, v in dict(
|
||||
total_max_attempts=config.total_max_attempts,
|
||||
mode=config.retry_mode,
|
||||
).items()
|
||||
if v is not None
|
||||
}
|
||||
|
||||
config_args = {
|
||||
k: v
|
||||
for k, v in dict(
|
||||
region_name=config.region_name,
|
||||
retries=retries_config if retries_config else None,
|
||||
connect_timeout=config.connect_timeout,
|
||||
read_timeout=config.read_timeout,
|
||||
).items()
|
||||
if v is not None
|
||||
}
|
||||
|
||||
boto3_config = Config(**config_args)
|
||||
|
||||
session_args = {
|
||||
k: v
|
||||
for k, v in dict(
|
||||
aws_access_key_id=config.aws_access_key_id,
|
||||
aws_secret_access_key=config.aws_secret_access_key,
|
||||
aws_session_token=config.aws_session_token,
|
||||
region_name=config.region_name,
|
||||
profile_name=config.profile_name,
|
||||
).items()
|
||||
if v is not None
|
||||
}
|
||||
|
||||
boto3_session = boto3.session.Session(**session_args)
|
||||
|
||||
return boto3_session.client("bedrock-runtime", config=boto3_config)
|
||||
|
||||
def __init__(self, config: BedrockConfig) -> None:
|
||||
self._config = config
|
||||
|
||||
self._client = BedrockInferenceAdapter._create_bedrock_client(config)
|
||||
tokenizer = Tokenizer.get_instance()
|
||||
self.formatter = ChatFormat(tokenizer)
|
||||
|
||||
@property
|
||||
def client(self) -> BaseClient:
|
||||
return self._client
|
||||
|
||||
async def initialize(self) -> None:
|
||||
pass
|
||||
|
||||
async def shutdown(self) -> None:
|
||||
self.client.close()
|
||||
|
||||
async def completion(
|
||||
self,
|
||||
model: str,
|
||||
content: InterleavedTextMedia,
|
||||
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
||||
stream: Optional[bool] = False,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
) -> Union[CompletionResponse, CompletionResponseStreamChunk]:
|
||||
raise NotImplementedError()
|
||||
|
||||
@staticmethod
|
||||
def resolve_bedrock_model(model_name: str) -> str:
|
||||
model = resolve_model(model_name)
|
||||
assert (
|
||||
model is not None
|
||||
and model.descriptor(shorten_default_variant=True)
|
||||
in BEDROCK_SUPPORTED_MODELS
|
||||
), (
|
||||
f"Unsupported model: {model_name}, use one of the supported models: "
|
||||
f"{','.join(BEDROCK_SUPPORTED_MODELS.keys())}"
|
||||
)
|
||||
|
||||
return BEDROCK_SUPPORTED_MODELS.get(
|
||||
model.descriptor(shorten_default_variant=True)
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _bedrock_stop_reason_to_stop_reason(bedrock_stop_reason: str) -> StopReason:
|
||||
if bedrock_stop_reason == "max_tokens":
|
||||
return StopReason.out_of_tokens
|
||||
return StopReason.end_of_turn
|
||||
|
||||
@staticmethod
|
||||
def _builtin_tool_name_to_enum(tool_name_str: str) -> Union[BuiltinTool, str]:
|
||||
for builtin_tool in BuiltinTool:
|
||||
if builtin_tool.value == tool_name_str:
|
||||
return builtin_tool
|
||||
else:
|
||||
return tool_name_str
|
||||
|
||||
@staticmethod
|
||||
def _bedrock_message_to_message(converse_api_res: Dict) -> Message:
|
||||
stop_reason = BedrockInferenceAdapter._bedrock_stop_reason_to_stop_reason(
|
||||
converse_api_res["stopReason"]
|
||||
)
|
||||
|
||||
bedrock_message = converse_api_res["output"]["message"]
|
||||
|
||||
role = bedrock_message["role"]
|
||||
contents = bedrock_message["content"]
|
||||
|
||||
tool_calls = []
|
||||
text_content = []
|
||||
for content in contents:
|
||||
if "toolUse" in content:
|
||||
tool_use = content["toolUse"]
|
||||
tool_calls.append(
|
||||
ToolCall(
|
||||
tool_name=BedrockInferenceAdapter._builtin_tool_name_to_enum(
|
||||
tool_use["name"]
|
||||
),
|
||||
arguments=tool_use["input"] if "input" in tool_use else None,
|
||||
call_id=tool_use["toolUseId"],
|
||||
)
|
||||
)
|
||||
elif "text" in content:
|
||||
text_content.append(content["text"])
|
||||
|
||||
return CompletionMessage(
|
||||
role=role,
|
||||
content=text_content,
|
||||
stop_reason=stop_reason,
|
||||
tool_calls=tool_calls,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _messages_to_bedrock_messages(
|
||||
messages: List[Message],
|
||||
) -> Tuple[List[Dict], Optional[List[Dict]]]:
|
||||
bedrock_messages = []
|
||||
system_bedrock_messages = []
|
||||
|
||||
user_contents = []
|
||||
assistant_contents = None
|
||||
for message in messages:
|
||||
role = message.role
|
||||
content_list = (
|
||||
message.content
|
||||
if isinstance(message.content, list)
|
||||
else [message.content]
|
||||
)
|
||||
if role == "ipython" or role == "user":
|
||||
if not user_contents:
|
||||
user_contents = []
|
||||
|
||||
if role == "ipython":
|
||||
user_contents.extend(
|
||||
[
|
||||
{
|
||||
"toolResult": {
|
||||
"toolUseId": message.call_id,
|
||||
"content": [
|
||||
{"text": content} for content in content_list
|
||||
],
|
||||
}
|
||||
}
|
||||
]
|
||||
)
|
||||
else:
|
||||
user_contents.extend(
|
||||
[{"text": content} for content in content_list]
|
||||
)
|
||||
|
||||
if assistant_contents:
|
||||
bedrock_messages.append(
|
||||
{"role": "assistant", "content": assistant_contents}
|
||||
)
|
||||
assistant_contents = None
|
||||
elif role == "system":
|
||||
system_bedrock_messages.extend(
|
||||
[{"text": content} for content in content_list]
|
||||
)
|
||||
elif role == "assistant":
|
||||
if not assistant_contents:
|
||||
assistant_contents = []
|
||||
|
||||
assistant_contents.extend(
|
||||
[
|
||||
{
|
||||
"text": content,
|
||||
}
|
||||
for content in content_list
|
||||
]
|
||||
+ [
|
||||
{
|
||||
"toolUse": {
|
||||
"input": tool_call.arguments,
|
||||
"name": (
|
||||
tool_call.tool_name
|
||||
if isinstance(tool_call.tool_name, str)
|
||||
else tool_call.tool_name.value
|
||||
),
|
||||
"toolUseId": tool_call.call_id,
|
||||
}
|
||||
}
|
||||
for tool_call in message.tool_calls
|
||||
]
|
||||
)
|
||||
|
||||
if user_contents:
|
||||
bedrock_messages.append({"role": "user", "content": user_contents})
|
||||
user_contents = None
|
||||
else:
|
||||
# Unknown role
|
||||
pass
|
||||
|
||||
if user_contents:
|
||||
bedrock_messages.append({"role": "user", "content": user_contents})
|
||||
if assistant_contents:
|
||||
bedrock_messages.append(
|
||||
{"role": "assistant", "content": assistant_contents}
|
||||
)
|
||||
|
||||
if system_bedrock_messages:
|
||||
return bedrock_messages, system_bedrock_messages
|
||||
|
||||
return bedrock_messages, None
|
||||
|
||||
@staticmethod
|
||||
def get_bedrock_inference_config(sampling_params: Optional[SamplingParams]) -> Dict:
|
||||
inference_config = {}
|
||||
if sampling_params:
|
||||
param_mapping = {
|
||||
"max_tokens": "maxTokens",
|
||||
"temperature": "temperature",
|
||||
"top_p": "topP",
|
||||
}
|
||||
|
||||
for k, v in param_mapping.items():
|
||||
if getattr(sampling_params, k):
|
||||
inference_config[v] = getattr(sampling_params, k)
|
||||
|
||||
return inference_config
|
||||
|
||||
@staticmethod
|
||||
def _tool_parameters_to_input_schema(
|
||||
tool_parameters: Optional[Dict[str, ToolParamDefinition]]
|
||||
) -> Dict:
|
||||
input_schema = {"type": "object"}
|
||||
if not tool_parameters:
|
||||
return input_schema
|
||||
|
||||
json_properties = {}
|
||||
required = []
|
||||
for name, param in tool_parameters.items():
|
||||
json_property = {
|
||||
"type": param.param_type,
|
||||
}
|
||||
|
||||
if param.description:
|
||||
json_property["description"] = param.description
|
||||
if param.required:
|
||||
required.append(name)
|
||||
json_properties[name] = json_property
|
||||
|
||||
input_schema["properties"] = json_properties
|
||||
if required:
|
||||
input_schema["required"] = required
|
||||
return input_schema
|
||||
|
||||
@staticmethod
|
||||
def _tools_to_tool_config(
|
||||
tools: Optional[List[ToolDefinition]], tool_choice: Optional[ToolChoice]
|
||||
) -> Optional[Dict]:
|
||||
if not tools:
|
||||
return None
|
||||
|
||||
bedrock_tools = []
|
||||
for tool in tools:
|
||||
tool_name = (
|
||||
tool.tool_name
|
||||
if isinstance(tool.tool_name, str)
|
||||
else tool.tool_name.value
|
||||
)
|
||||
|
||||
tool_spec = {
|
||||
"toolSpec": {
|
||||
"name": tool_name,
|
||||
"inputSchema": {
|
||||
"json": BedrockInferenceAdapter._tool_parameters_to_input_schema(
|
||||
tool.parameters
|
||||
),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
if tool.description:
|
||||
tool_spec["toolSpec"]["description"] = tool.description
|
||||
|
||||
bedrock_tools.append(tool_spec)
|
||||
tool_config = {
|
||||
"tools": bedrock_tools,
|
||||
}
|
||||
|
||||
if tool_choice:
|
||||
tool_config["toolChoice"] = (
|
||||
{"any": {}}
|
||||
if tool_choice.value == ToolChoice.required
|
||||
else {"auto": {}}
|
||||
)
|
||||
return tool_config
|
||||
|
||||
async def chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[Message],
|
||||
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
||||
# zero-shot tool definitions as input to the model
|
||||
tools: Optional[List[ToolDefinition]] = None,
|
||||
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
|
||||
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
|
||||
stream: Optional[bool] = False,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
) -> (
|
||||
AsyncGenerator
|
||||
): # Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]:
|
||||
bedrock_model = BedrockInferenceAdapter.resolve_bedrock_model(model)
|
||||
inference_config = BedrockInferenceAdapter.get_bedrock_inference_config(
|
||||
sampling_params
|
||||
)
|
||||
|
||||
tool_config = BedrockInferenceAdapter._tools_to_tool_config(tools, tool_choice)
|
||||
bedrock_messages, system_bedrock_messages = (
|
||||
BedrockInferenceAdapter._messages_to_bedrock_messages(messages)
|
||||
)
|
||||
|
||||
converse_api_params = {
|
||||
"modelId": bedrock_model,
|
||||
"messages": bedrock_messages,
|
||||
}
|
||||
if inference_config:
|
||||
converse_api_params["inferenceConfig"] = inference_config
|
||||
|
||||
# Tool use is not supported in streaming mode
|
||||
if tool_config and not stream:
|
||||
converse_api_params["toolConfig"] = tool_config
|
||||
if system_bedrock_messages:
|
||||
converse_api_params["system"] = system_bedrock_messages
|
||||
|
||||
if not stream:
|
||||
converse_api_res = self.client.converse(**converse_api_params)
|
||||
|
||||
output_message = BedrockInferenceAdapter._bedrock_message_to_message(
|
||||
converse_api_res
|
||||
)
|
||||
|
||||
yield ChatCompletionResponse(
|
||||
completion_message=output_message,
|
||||
logprobs=None,
|
||||
)
|
||||
else:
|
||||
converse_stream_api_res = self.client.converse_stream(**converse_api_params)
|
||||
event_stream = converse_stream_api_res["stream"]
|
||||
|
||||
for chunk in event_stream:
|
||||
if "messageStart" in chunk:
|
||||
yield ChatCompletionResponseStreamChunk(
|
||||
event=ChatCompletionResponseEvent(
|
||||
event_type=ChatCompletionResponseEventType.start,
|
||||
delta="",
|
||||
)
|
||||
)
|
||||
elif "contentBlockStart" in chunk:
|
||||
yield ChatCompletionResponseStreamChunk(
|
||||
event=ChatCompletionResponseEvent(
|
||||
event_type=ChatCompletionResponseEventType.progress,
|
||||
delta=ToolCallDelta(
|
||||
content=ToolCall(
|
||||
tool_name=chunk["contentBlockStart"]["toolUse"][
|
||||
"name"
|
||||
],
|
||||
call_id=chunk["contentBlockStart"]["toolUse"][
|
||||
"toolUseId"
|
||||
],
|
||||
),
|
||||
parse_status=ToolCallParseStatus.started,
|
||||
),
|
||||
)
|
||||
)
|
||||
elif "contentBlockDelta" in chunk:
|
||||
if "text" in chunk["contentBlockDelta"]["delta"]:
|
||||
delta = chunk["contentBlockDelta"]["delta"]["text"]
|
||||
else:
|
||||
delta = ToolCallDelta(
|
||||
content=ToolCall(
|
||||
arguments=chunk["contentBlockDelta"]["delta"][
|
||||
"toolUse"
|
||||
]["input"]
|
||||
),
|
||||
parse_status=ToolCallParseStatus.success,
|
||||
)
|
||||
|
||||
yield ChatCompletionResponseStreamChunk(
|
||||
event=ChatCompletionResponseEvent(
|
||||
event_type=ChatCompletionResponseEventType.progress,
|
||||
delta=delta,
|
||||
)
|
||||
)
|
||||
elif "contentBlockStop" in chunk:
|
||||
# Ignored
|
||||
pass
|
||||
elif "messageStop" in chunk:
|
||||
stop_reason = (
|
||||
BedrockInferenceAdapter._bedrock_stop_reason_to_stop_reason(
|
||||
chunk["messageStop"]["stopReason"]
|
||||
)
|
||||
)
|
||||
|
||||
yield ChatCompletionResponseStreamChunk(
|
||||
event=ChatCompletionResponseEvent(
|
||||
event_type=ChatCompletionResponseEventType.complete,
|
||||
delta="",
|
||||
stop_reason=stop_reason,
|
||||
)
|
||||
)
|
||||
elif "metadata" in chunk:
|
||||
# Ignored
|
||||
pass
|
||||
else:
|
||||
# Ignored
|
||||
pass
|
||||
55
llama_stack/providers/adapters/inference/bedrock/config.py
Normal file
55
llama_stack/providers/adapters/inference/bedrock/config.py
Normal file
|
|
@ -0,0 +1,55 @@
|
|||
# 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 * # noqa: F403
|
||||
|
||||
from llama_models.schema_utils import json_schema_type
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class BedrockConfig(BaseModel):
|
||||
aws_access_key_id: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The AWS access key to use. Default use environment variable: AWS_ACCESS_KEY_ID",
|
||||
)
|
||||
aws_secret_access_key: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The AWS secret access key to use. Default use environment variable: AWS_SECRET_ACCESS_KEY",
|
||||
)
|
||||
aws_session_token: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The AWS session token to use. Default use environment variable: AWS_SESSION_TOKEN",
|
||||
)
|
||||
region_name: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The default AWS Region to use, for example, us-west-1 or us-west-2."
|
||||
"Default use environment variable: AWS_DEFAULT_REGION",
|
||||
)
|
||||
profile_name: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The profile name that contains credentials to use."
|
||||
"Default use environment variable: AWS_PROFILE",
|
||||
)
|
||||
total_max_attempts: Optional[int] = Field(
|
||||
default=None,
|
||||
description="An integer representing the maximum number of attempts that will be made for a single request, "
|
||||
"including the initial attempt. Default use environment variable: AWS_MAX_ATTEMPTS",
|
||||
)
|
||||
retry_mode: Optional[str] = Field(
|
||||
default=None,
|
||||
description="A string representing the type of retries Boto3 will perform."
|
||||
"Default use environment variable: AWS_RETRY_MODE",
|
||||
)
|
||||
connect_timeout: Optional[float] = Field(
|
||||
default=60,
|
||||
description="The time in seconds till a timeout exception is thrown when attempting to make a connection. "
|
||||
"The default is 60 seconds.",
|
||||
)
|
||||
read_timeout: Optional[float] = Field(
|
||||
default=60,
|
||||
description="The time in seconds till a timeout exception is thrown when attempting to read from a connection."
|
||||
"The default is 60 seconds.",
|
||||
)
|
||||
|
|
@ -75,4 +75,15 @@ def available_providers() -> List[ProviderSpec]:
|
|||
header_extractor_class="llama_stack.providers.adapters.inference.together.TogetherHeaderExtractor",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
api=Api.inference,
|
||||
adapter=AdapterSpec(
|
||||
adapter_id="bedrock",
|
||||
pip_packages=[
|
||||
"boto3",
|
||||
],
|
||||
module="llama_stack.providers.adapters.inference.bedrock",
|
||||
config_class="llama_stack.providers.adapters.inference.bedrock.BedrockConfig",
|
||||
),
|
||||
),
|
||||
]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue