Logo

LLM Import

Common questions this page answers:

  • How do I enable LLM-powered model card import?
  • What LLM providers are supported?
  • What configuration options are available?
  • How do users interact with the import feature?

Bailo can optionally use a large language model (LLM) to extract model card data from free text, such as HuggingFace model cards or system cards. This page explains how to enable and configure the feature.

How to enable

The feature is disabled by default and requires an OpenAI-compatible chat completions endpoint.

To enable LLM import, set ui.llmImport.enabled to true and configure the llm section with your endpoint details in your configuration override (for example production.cjs or local.js):

{
  llm: {
    endpoint: 'https://api.openai.com/v1/chat/completions',
    apiKey: 'your-api-key',
    model: 'gpt-4o',
    maxTokens: 16384,
    timeoutMs: 120000,
    temperature: 0,
  },

  ui: {
    llmImport: {
      enabled: true,
    },
  },
}

For Helm deployments, these values are set in values.yaml under llm and config.ui.llmImport. See App Configuration for details on how configuration inheritance works.

Configuration options

  • ui.llmImport.enabled - Enables the feature and shows the "Import from Text" button in the model card editor. When false (the default), the button is hidden and the backend rejects any import requests
  • llm.endpoint - URL of an OpenAI-compatible chat completions endpoint
  • llm.apiKey - API key for authenticating with the LLM provider
  • llm.model - Model identifier for the LLM provider (for example gpt-4o or gpt-4.1-mini)
  • llm.maxTokens - Maximum number of tokens in the LLM response. Default: 16384
  • llm.timeoutMs - Timeout for LLM requests in milliseconds. Default: 120000
  • llm.temperature - Controls response determinism. A low value produces more deterministic responses. Default: 0
  • llm.systemPrompt - System prompt sent to the LLM. The default prompt instructs the model to extract only explicitly stated information and avoid generating placeholder values. You may want to tune this for your specific LLM and schema

What to expect

Once enabled, users see an Import from Text button when editing a model card. Clicking this opens a dialog where they can paste free text. Bailo sends the text and the model card schema to the configured LLM, which extracts structured data and populates matching fields in the model card.

The extracted data is validated against the schema before being applied. Any fields that do not match the schema or contain placeholder values are automatically filtered out. Validation warnings are shown to the user so they can review the result before saving.

Related pages

Copyright © Crown Copyright 2026.