module pixeltable.functions.deepseek

Pixeltable UDFs for Deepseek AI models. Provides integration with Deepseek’s language models for chat completions and other AI capabilities.

udf chat_completions()

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

Creates a model response for the given chat conversation. Equivalent to the Deepseek chat/completions API endpoint. For additional details, see: https://api-docs.deepseek.com/api/create-chat-completion Deepseek uses the OpenAI SDK, so you will need to install the openai package to use this UDF. Request throttling: Applies the rate limit set in the config (section deepseek, key rate_limit). If no rate limit is configured, uses a default of 600 RPM. Requirements:

pip install openai

Parameters:

messages (Json): A list of messages to use for chat completion, as described in the Deepseek API documentation.
model (String): The model to use for chat completion.
model_kwargs (Json | None): Additional keyword args for the Deepseek chat/completions API. For details on the available parameters, see: https://api-docs.deepseek.com/api/create-chat-completion
tools (Json | None): An optional list of Pixeltable tools to use for the request.
tool_choice (Json | None): An optional tool choice configuration.

Returns:

Json: A dictionary containing the response and other metadata.

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

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': tbl.prompt},
]
tbl.add_computed_column(
    response=chat_completions(messages, model='deepseek-chat')
)

​module pixeltable.functions.deepseek

​udf chat_completions()

module pixeltable.functions.deepseek

udf chat_completions()