eval

Run signal judging on provided search results

Run signal judging on sample search results Request body: ticker: Stock ticker for context results: Array of search results to judge (title, url, text) If not provided, uses sample results

Returns: results: Array of {search_result, judgment} pairs model: Model used prompt_version: Prompt version identifier

post/eval/track-b-judge

Request

  • Base URL: https://api.fed10.ai/api
  • URL: https://api.fed10.ai/api/eval/track-b-judge
  • Auth: API key in header Authorization

Response

Success

Changes

No recorded changes to this operation across all 1 revision of this API.