Skip to content

Feature request: read web pages #18

Description

@pavel-kirienko

Perhaps the most obvious way to approach this is to define a new tool that does this:

  1. Reads the HTML
  2. Renders it using Kaleido or Choreographer into an image
  3. Submits the image to the LLM via the completion API

One use case is to ask the bot to incorporate the data from a web page into its response.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    Status
    Todo

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions