module pixeltable.functions.bedrock

Pixeltable UDFs for AWS Bedrock AI models. Provides integration with AWS Bedrock for accessing various foundation models including Anthropic Claude, Amazon Titan, and other providers.

func invoke_tools()

Signature

invoke_tools(
    tools: pixeltable.func.tools.Tools,
    response: pixeltable.exprs.expr.Expr
) -> pixeltable.exprs.inline_expr.InlineDict

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

udf converse()

Signature

@pxt.udf
converse(
    messages: pxt.Json,
    *,
    model_id: pxt.String,
    system: pxt.Json | None = None,
    inference_config: pxt.Json | None = None,
    additional_model_request_fields: pxt.Json | None = None,
    tool_config: pxt.Json | None = None
) -> pxt.Json

Generate a conversation response. Equivalent to the AWS Bedrock converse API endpoint. For additional details, see: https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-runtime/client/converse.html Requirements:

pip install boto3

Parameters:

messages (pxt.Json): Input messages.
model_id (pxt.String): The model that will complete your prompt.
system (pxt.Json | None): An optional system prompt.
inference_config (pxt.Json | None): Base inference parameters to use.
additional_model_request_fields (pxt.Json | None): Additional inference parameters to use.

Returns:

pxt.Json: A dictionary containing the response and other metadata.

Examples: Add a computed column that applies the model anthropic.claude-3-haiku-20240307-v1:0 to an existing Pixeltable column tbl.prompt of the table tbl:

msgs = [{'role': 'user', 'content': [{'text': tbl.prompt}]}]
tbl.add_computed_column(
    response=messages(
        msgs, model_id='anthropic.claude-3-haiku-20240307-v1:0'
    )
)

SDK Reference

Documentation Index

​module pixeltable.functions.bedrock

​func invoke_tools()

​udf converse()

module pixeltable.functions.bedrock

func invoke_tools()

udf converse()