module pixeltable.functions.fireworks

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

udf chat_completions()

chat_completions(
    messages: Json,
    *,
    model: String,
    model_kwargs: Json | None = None
) -> Json

Creates a model response for the given chat conversation. Equivalent to the Fireworks AI chat/completions API endpoint. For additional details, see: https://docs.fireworks.ai/api-reference/post-chatcompletions Request throttling: Applies the rate limit set in the config (section fireworks, key rate_limit). If no rate limit is configured, uses a default of 600 RPM. Requirements:

pip install fireworks-ai

Parameters:

messages (Json): A list of messages comprising the conversation so far.
model (String): The name of the model to use.
model_kwargs (Json | None): Additional keyword args for the Fireworks chat_completions API. For details on the available parameters, see: https://docs.fireworks.ai/api-reference/post-chatcompletions

Returns:

Json: A dictionary containing the response and other metadata.

Examples: Add a computed column that applies the model accounts/fireworks/models/mixtral-8x22b-instruct to an existing Pixeltable column tbl.prompt of the table tbl:

messages = [{'role': 'user', 'content': tbl.prompt}]
tbl.add_computed_column(
    response=chat_completions(
        messages, model='accounts/fireworks/models/mixtral-8x22b-instruct'
    )
)

​module pixeltable.functions.fireworks

​udf chat_completions()

module pixeltable.functions.fireworks

udf chat_completions()