Natalie Tay 683bb5725b DEV: Split content based on llmmodel's max_output_tokens (#1456) ...

In discourse/discourse-translator#249 we introduced splitting content (post.raw) prior to sending to translation as we were using a sync api.

Now that we're streaming thanks to #1424, we'll chunk based on the LlmModel.max_output_tokens.

2025-06-23 21:11:20 +08:00

..

configuration

DEV: Add back validator for Spam setting (#1415)

2025-06-06 10:56:36 -07:00

db/migrate

FIX: Open AI embeddings config migration & Seeded indexes cleanup & (#1092)

2025-01-27 15:24:43 -03:00

fabricators

FEATURE: persistent key-value storage for AI Artifacts (#1417)

2025-06-11 06:59:46 +10:00

fixtures

FEATURE: enforce jpg/png for all images (#1309)

2025-05-05 17:46:37 +10:00

jobs

DEV: Also make sure locale detection skips PMs that are not group PMs when public content only (#1457)

2025-06-23 19:07:40 +08:00

lib

DEV: Split content based on llmmodel's max_output_tokens (#1456)

2025-06-23 21:11:20 +08:00

models

FEATURE: persistent key-value storage for AI Artifacts (#1417)

2025-06-11 06:59:46 +10:00

reports

FEATURE: New sentiment analysis visualization report (#1109)

2025-02-20 09:14:10 -08:00

requests

DEV: Move title suggestion to an array (#1435)

2025-06-16 18:06:54 -03:00

serializers

DEV: Use a PORO to represent modules/features. (#1421)

2025-06-10 14:37:53 -03:00

services

DEV: Use structured responses for summaries (#1252)

2025-05-06 10:09:39 -03:00

shared

FEATURE: Add Qwen3 tokenizer and update Gemma to version 3 (#1440)

2025-06-17 10:25:03 -03:00

support

FEATURE: configurable embeddings (#1049)

2025-01-21 12:23:19 -03:00

system

FIX: AI preferences tab button not appearing unless Helper enabled (#1452)

2025-06-20 10:12:08 -07:00

tasks

DEV: Rename spec (#1344)

2025-05-16 09:40:08 +01:00

plugin_helper.rb

FEATURE: Personas powered summaries. (#1232)

2025-04-02 12:54:47 -03:00

plugin_spec.rb

FEATURE: Use different personas to power AI helper features.

2025-06-04 14:23:00 -03:00