Claude Client

llm_annotator.clients.claude_client

Anthropic Claude provider implementation.

ClaudeRuntimeOptions dataclass

ClaudeRuntimeOptions(
    max_tokens: int | None = None,
    json_schema: dict[str, Any] | None = None,
    effort: Literal["low", "medium", "high", "xhigh", "max"]
    | None = None,
    thinking_type: Literal[
        "enabled", "disabled", "adaptive"
    ]
    | None = None,
    thinking_budget: int | None = None,
    thinking_display: Literal[
        "summarized", "omitted", "full"
    ]
    | None = None,
)

Bases: ProviderRuntimeOptions

Runtime options specific to the Claude provider.

effort class-attribute instance-attribute

effort: (
    Literal["low", "medium", "high", "xhigh", "max"] | None
) = None

Controls the amount of effort Claude puts into generating the response, which can affect quality and latency. Higher effort levels may produce better responses but take more time and compute resources. If not specified, the provider default will be used.

thinking_type class-attribute instance-attribute

thinking_type: (
    Literal["enabled", "disabled", "adaptive"] | None
) = None

When enabled, responses include thinking content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your max_tokens limit.

thinking_budget class-attribute instance-attribute

thinking_budget: int | None = None

Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than max_tokens.

thinking_display class-attribute instance-attribute

thinking_display: (
    Literal["summarized", "omitted", "full"] | None
) = None

When thinking is enabled (or adaptive). Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

ClaudeClient

ClaudeClient(
    model: str,
    max_workers: int = 4,
    api_key: str | None = None,
    on_error: OnError = "warn",
)

Bases: Client[ClaudeRuntimeOptions]

Client wrapper for Anthropic Claude APIs.

Initialize the Claude client.

Parameters:

Name	Type	Description	Default
model	str	Claude model identifier.	required
max_workers	int	Maximum number of concurrent worker threads for batch_generate.	4
api_key	str | None	Anthropic API key. If not provided, the client will attempt to read from the environment variable ANTHROPIC_API_KEY.	None
on_error	OnError	Error behavior when generation fails.	'warn'

View source on GitHub: src/llm_annotator/clients/claude_client.py lines 71–95

generate

generate(
    *,
    messages: list[dict[str, str]],
    options: ClaudeRuntimeOptions | None = None,
    gen_kwargs: dict[str, Any] | None = None,
) -> Response

Generate a response using Claude.

Parameters:

Name	Type	Description	Default
messages	list[dict[str, str]]	List of message dictionaries.	required
options	ClaudeRuntimeOptions | None	Provider-specific generation options.	None
gen_kwargs	dict[str, Any] | None	Additional provider-specific generation kwargs that are not covered by the standard options. Has precedence over options.	None

Returns:

Type	Description
Response	A Response object containing the generated response.

Raises:

Type	Description
ProviderError	If the provider call fails.

View source on GitHub: src/llm_annotator/clients/claude_client.py lines 132–196

batch_generate

batch_generate(
    *,
    messages: list[list[dict[str, str]]],
    options: ClaudeRuntimeOptions | None = None,
    gen_kwargs: dict[str, Any] | None = None,
) -> list[Response]

Generate responses for a batch of inputs concurrently.

The Anthropic API has no native synchronous batch endpoint, so requests are dispatched in parallel using a thread pool.

Parameters:

Name	Type	Description	Default
messages	list[list[dict[str, str]]]	List of message lists, one per request.	required
options	ClaudeRuntimeOptions | None	Provider-specific generation options.	None
gen_kwargs	dict[str, Any] | None	Additional provider-specific generation kwargs that are not covered by the standard options. Has precedence over options.	None

Returns:

Type	Description
list[Response]	A list of Response objects in the same order as the input.

Raises:

Type	Description
ProviderError	If any individual request fails.

View source on GitHub: src/llm_annotator/clients/claude_client.py lines 198–246

destroy

destroy() -> None

Clean up any resources used by the client.

View source on GitHub: src/llm_annotator/clients/claude_client.py lines 293–298