module pixeltable.functions.mistralai

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

udf chat_completions()

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

Chat Completion API. Equivalent to the Mistral AI chat/completions API endpoint. For additional details, see: https://docs.mistral.ai/api/#tag/chat Request throttling: Applies the rate limit set in the config (section mistral, key rate_limit). If no rate limit is configured, uses a default of 600 RPM. Requirements:

pip install mistralai

Parameters:

messages (Json): The prompt(s) to generate completions for.
model (String): ID of the model to use. (See overview here: https://docs.mistral.ai/getting-started/models/)
model_kwargs (Json | None): Additional keyword args for the Mistral chat/completions API. For details on the available parameters, see: https://docs.mistral.ai/api/#tag/chat

Returns:

Json: A dictionary containing the response and other metadata.

Examples: Add a computed column that applies the model mistral-latest-small to an existing Pixeltable column tbl.prompt of the table tbl:

messages = [{'role': 'user', 'content': tbl.prompt}]
tbl.add_computed_column(
    response=completions(messages, model='mistral-latest-small')
)

udf embeddings()

embeddings(input: String, *, model: String) -> Array[(None,), Float]

Embeddings API. Equivalent to the Mistral AI embeddings API endpoint. For additional details, see: https://docs.mistral.ai/api/#tag/embeddings Request throttling: Applies the rate limit set in the config (section mistral, key rate_limit). If no rate limit is configured, uses a default of 600 RPM. Requirements:

pip install mistralai

Parameters:

input (String): Text to embed.
model (String): ID of the model to use. (See overview here: https://docs.mistral.ai/getting-started/models/)

Returns:

Array[(None,), Float]: An array representing the application of the given embedding to input.

udf fim_completions()

fim_completions(
    prompt: String,
    *,
    model: String,
    model_kwargs: Json | None = None
) -> Json

Fill-in-the-middle Completion API. Equivalent to the Mistral AI fim/completions API endpoint. For additional details, see: https://docs.mistral.ai/api/#tag/fim Request throttling: Applies the rate limit set in the config (section mistral, key rate_limit). If no rate limit is configured, uses a default of 600 RPM. Requirements:

pip install mistralai

Parameters:

prompt (String): The text/code to complete.
model (String): ID of the model to use. (See overview here: https://docs.mistral.ai/getting-started/models/)
model_kwargs (Json | None): Additional keyword args for the Mistral fim/completions API. For details on the available parameters, see: https://docs.mistral.ai/api/#tag/fim

Returns:

Json: A dictionary containing the response and other metadata.

Examples: Add a computed column that applies the model codestral-latest to an existing Pixeltable column tbl.prompt of the table tbl:

tbl.add_computed_column(
    response=completions(tbl.prompt, model='codestral-latest')
)

​module pixeltable.functions.mistralai

​udf chat_completions()

​udf embeddings()

​udf fim_completions()

module pixeltable.functions.mistralai

udf chat_completions()

udf embeddings()

udf fim_completions()