discourse-ai/lib/completions/structured_output.rb
Rafael dos Santos Silva 478f31de47
FEATURE: add inferred concepts system (#1330)
* FEATURE: add inferred concepts system

This commit adds a new inferred concepts system that:
- Creates a model for storing concept labels that can be applied to topics
- Provides AI personas for finding new concepts and matching existing ones
- Adds jobs for generating concepts from popular topics
- Includes a scheduled job that automatically processes engaging topics

* FEATURE: Extend inferred concepts to include posts

* Adds support for concepts to be inferred from and applied to posts
* Replaces daily task with one that handles both topics and posts
* Adds database migration for posts_inferred_concepts join table
* Updates PersonaContext to include inferred concepts



Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
Co-authored-by: Keegan George <kgeorge13@gmail.com>
2025-06-02 14:29:20 -03:00

62 lines
1.8 KiB
Ruby

# frozen_string_literal: true
module DiscourseAi
module Completions
class StructuredOutput
def initialize(json_schema_properties)
@property_names = json_schema_properties.keys.map(&:to_sym)
@property_cursors =
json_schema_properties.reduce({}) do |m, (k, prop)|
m[k.to_sym] = 0 if prop[:type] == "string"
m
end
@tracked = {}
@raw_response = +""
@raw_cursor = 0
@partial_json_tracker = JsonStreamingTracker.new(self)
end
attr_reader :last_chunk_buffer
def <<(raw)
@raw_response << raw
@partial_json_tracker << raw
end
def read_buffered_property(prop_name)
# Safeguard: If the model is misbehaving and generating something that's not a JSON,
# treat response as a normal string.
# This is a best-effort to recover from an unexpected scenario.
if @partial_json_tracker.broken?
unread_chunk = @raw_response[@raw_cursor..]
@raw_cursor = @raw_response.length
return unread_chunk
end
# Maybe we haven't read that part of the JSON yet.
return nil if @tracked[prop_name].blank?
# This means this property is a string and we want to return unread chunks.
if @property_cursors[prop_name].present?
unread = @tracked[prop_name][@property_cursors[prop_name]..]
@property_cursors[prop_name] = @tracked[prop_name].length
unread
else
# Ints and bools, and arrays are always returned as is.
@tracked[prop_name]
end
end
def notify_progress(key, value)
key_sym = key.to_sym
return if !@property_names.include?(key_sym)
@tracked[key_sym] = value
end
end
end
end