Skip to main content
Pixeltable UDFs for Ollama local models. Provides integration with Ollama for running large language models locally, including chat completions and embeddings. View source on GitHub

​
UDFs

​
chat() udf

Generate the next message in a chat with a provided model. Signature: 
chat(
    messages: Json,
    model: String,
    tools: Optional[Json],
    format: Optional[String],
    options: Optional[Json]
)-> Json
Parameters:
  • messages (Json): The messages of the chat.
  • model (String): The model name.
  • tools (Optional[Json]): Tools for the model to use.
  • format (Optional[String]): The format of the response; must be one of 'json' or None.
  • options (Optional[Json]): Additional options to pass to the chat call, such as max_tokens, temperature, top_p, and top_k. For details, see the Valid Parameters and Values section of the Ollama documentation.

​
embed() udf

Generate embeddings from a model. Signature: 
embed(
    input: String,
    model: String,
    truncate: Bool,
    options: Optional[Json]
)-> Array[(None,), Float]
Parameters:
  • input (String): The input text to generate embeddings for.
  • model (String): The model name.
  • truncate (Bool): Truncates the end of each input to fit within context length. Returns error if false and context length is exceeded.
  • options (Optional[Json]): Additional options to pass to the embed call. For details, see the Valid Parameters and Values section of the Ollama documentation.

​
generate() udf

Generate a response for a given prompt with a provided model. Signature: 
generate(
    prompt: String,
    model: String,
    suffix: String,
    system: String,
    template: String,
    context: Optional[Json],
    raw: Bool,
    format: Optional[String],
    options: Optional[Json]
)-> Json
Parameters:
  • prompt (String): The prompt to generate a response for.
  • model (String): The model name.
  • suffix (String): The text after the model response.
  • format (Optional[String]): The format of the response; must be one of 'json' or None.
  • system (String): System message.
  • template (String): Prompt template to use.
  • context (Optional[Json]): The context parameter returned from a previous call to generate().
  • raw (Bool): If True, no formatting will be applied to the prompt.
  • options (Optional[Json]): Additional options for the Ollama chat call, such as max_tokens, temperature, top_p, and top_k. For details, see the Valid Parameters and Values section of the Ollama documentation.