Skip to content

elmer abstracts away differences in the way that different Providers represent various types of content, allowing you to more easily write code that works with any chatbot.

This set of classes represents the various types of content that can be sent to and received from a provider:

  • ContentText: simple text (often in markdown format). This is the only type of content that can be streamed live as it's received.

  • ContentImageRemote and ContentImageInline: images, either as a pointer to a remote URL or included inline in the object. See content_image_file() and friends for convenient ways to construct these objects.

  • ContentToolRequest: a request to perform a tool call (sent by the assistant).

  • ContentToolResult: the result of calling the tool (sent by the user).

Usage

Content()

ContentText(text = class_missing)

ContentImage()

ContentImageRemote(url = class_missing, detail = class_missing)

ContentImageInline(type = class_missing, data = class_missing)

ContentToolRequest(
  id = class_missing,
  name = class_missing,
  arguments = class_missing
)

ContentToolResult(
  id = class_missing,
  value = class_missing,
  error = class_missing
)

Arguments

text

A single string.

url

URL to a remote image.

detail

Not currently used.

type

MIME type of the image.

data

Base64 encoded image data.

id

Tool call id (used to associate a request and a result)

name

Function name

arguments

Named list of arguments to call the function with.

value, error

Either the results of calling the function if it succeeded, otherwise the error message, as a string. One of value and error will always be NULL.