mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-02-07 12:08:13 +00:00
6282b6d21f
Previous to this changeset we used a custom system for tools/command support for Anthropic. We defined commands by using !command as a signal to execute it Following Anthropic Claude 2.1, there is an official supported syntax (beta) for tools execution. eg: ``` + <function_calls> + <invoke> + <tool_name>image</tool_name> + <parameters> + <prompts> + [ + "an oil painting", + "a cute fluffy orange", + "3 apple's", + "a cat" + ] + </prompts> + </parameters> + </invoke> + </function_calls> ``` This implements the spec per Anthropic, it should be stable enough to also work on other LLMs. Keep in mind that OpenAI is not impacted here at all, as it has its own custom system for function calls. Additionally: - Fixes the title system prompt so it works with latest Anthropic - Uses new spec for "system" messages by Anthropic - Tweak forum helper persona to guide Anthropic a tiny be better Overall results are pretty awesome and Anthropic Claude performs really well now on Discourse
36 lines
1008 B
Ruby
36 lines
1008 B
Ruby
#frozen_string_literal: true
|
|
|
|
module DiscourseAi
|
|
module AiBot
|
|
module Personas
|
|
class General < Persona
|
|
def commands
|
|
[
|
|
Commands::SearchCommand,
|
|
Commands::GoogleCommand,
|
|
Commands::ImageCommand,
|
|
Commands::ReadCommand,
|
|
Commands::ImageCommand,
|
|
Commands::CategoriesCommand,
|
|
Commands::TagsCommand,
|
|
]
|
|
end
|
|
|
|
def system_prompt
|
|
<<~PROMPT
|
|
You are a helpful Discourse assistant.
|
|
You _understand_ and **generate** Discourse Markdown.
|
|
You live in a Discourse Forum Message.
|
|
|
|
You live in the forum with the URL: {site_url}
|
|
The title of your site: {site_title}
|
|
The description is: {site_description}
|
|
The participants in this conversation are: {participants}
|
|
The date now is: {time}, much has changed since you were trained.
|
|
PROMPT
|
|
end
|
|
end
|
|
end
|
|
end
|
|
end
|