Skip to content

anthropic

pixeltable.functions.anthropic

Pixeltable UDFs that wrap various endpoints from the Anthropic API. In order to use them, you must first pip install anthropic and configure your Anthropic credentials, as described in the Working with Anthropic tutorial.

invoke_tools 

invoke_tools(tools: Tools, response: Expr) -> InlineDict

Converts an Anthropic response dict to Pixeltable tool invocation format and calls tools._invoke().

messages async 

messages(
    messages: Json,
    *,
    model: String,
    max_tokens: Int = 1024,
    metadata: Optional[Json] = None,
    stop_sequences: Optional[Json] = None,
    system: Optional[String] = None,
    temperature: Optional[Float] = None,
    tool_choice: Optional[Json] = None,
    tools: Optional[Json] = None,
    top_k: Optional[Int] = None,
    top_p: Optional[Float] = None,
    timeout: Optional[Float] = None
) -> Json

Create a Message.

Equivalent to the Anthropic messages API endpoint. For additional details, see: https://docs.anthropic.com/en/api/messages

Request throttling: Uses the rate limit-related headers returned by the API to throttle requests adaptively, based on available request and token capacity. No configuration is necessary.

Requirements:

  • pip install anthropic

Parameters:

  • messages (Json) –

    Input messages.

  • model (String) –

    The model that will complete your prompt.

For details on the other parameters, see: https://docs.anthropic.com/en/api/messages

Returns:

  • Json –

    A dictionary containing the response and other metadata.

Examples:

Add a computed column that applies the model claude-3-haiku-20240307 to an existing Pixeltable column tbl.prompt of the table tbl:

>>> msgs = [{'role': 'user', 'content': tbl.prompt}]
... tbl.add_computed_column(response= messages(msgs, model='claude-3-haiku-20240307'))