llumpy.providers.AsyncAnthropicClient

class AsyncAnthropicClient(model)

Bases: AsyncModelClient

Async client interface for interacting with Anthropic API

Parameters:

model (str)

__init__(model)

Initialize connection to Anthropic

Parameters:

model (str) – LLM to use

Raises:

EnvironmentError – If the ‘ANTHROPIC_API_KEY’ env var is not defined

Methods

__init__(model)	Initialize connection to Anthropic
extract_text(response)	Extract LLM response text from Anthropic object
prompt_many(conversation, *[, handler, retries])	Prompt a model with a full conversation
prompt_one(message, *[, handler, retries])	Prompt a model with a single user message
prompt_stream(conversation, **prompt_kwargs)	Prompt a model and stream the response
system([content, file])	Init conversation with a system message
user([content, file])	Init conversation with a user message
validate()	Verify Anthropic key is valid and has access to the requested model
vendor_prompt(conversation, **prompt_kwargs)	Prompt a model for Anthropic chat completion
vendor_prompt_stream(conversation, ...)	Prompt a model for a streamed Anthropic chat completion

Attributes

model

Name of the model

extract_text(response)

Extract LLM response text from Anthropic object

Parameters:

response (Message | Annotated[TextEvent | CitationEvent | ThinkingEvent | SignatureEvent | InputJsonEvent | RawMessageStartEvent | RawMessageDeltaEvent | MessageStopEvent | RawContentBlockStartEvent | RawContentBlockDeltaEvent | ContentBlockStopEvent, PropertyInfo(alias='None', format=None, format_template='None', discriminator='type')]) – Anthropic chat response

Returns:

Text message if present, else None

Return type:

str | None

async validate()

Verify Anthropic key is valid and has access to the requested model

Raises:

• InvalidAPIKeyError – If the Anthropic key is invalid

• ModelNotFoundError – If requested model does not exist

• PermissionDeniedError – If key does not have access to requested model

Return type:

None

async vendor_prompt(conversation, **prompt_kwargs)

Prompt a model for Anthropic chat completion

Parameters:

• conversation (Conversation) – Messages to send to llm

• prompt_kwargs (Any) – kwargs for chat

Returns:

Chat completion

Return type:

Message

async vendor_prompt_stream(conversation, **prompt_kwargs)

Prompt a model for a streamed Anthropic chat completion

Parameters:

• conversation (Conversation) – Messages to send to llm

• prompt_kwargs (Any) – kwargs for chat

Returns:

Chat completion stream

Return type:

AsyncStream[Annotated[RawMessageStartEvent | RawMessageDeltaEvent | RawMessageStopEvent | RawContentBlockStartEvent | RawContentBlockDeltaEvent | RawContentBlockStopEvent, PropertyInfo(alias=’None’, format=None, format_template=’None’, discriminator=’type’)]]