Commit Graph

13 Commits

Author SHA1 Message Date
Rafael dos Santos Silva e3f5e86dc5
FIX: AI Automation scripts were broken when using seeded models () 2024-12-02 19:07:05 -03:00
Sam fbcc8e493a
FEATURE: Skip PM scanning in LLM triage by default ()
Usually people do not want to scan personal messages. Sometimes
they may. In that case they can enable triage on personal messages.
2024-11-28 09:25:29 +11:00
Sam 059d3b6fd2
FEATURE: better logging for automation reports ()
A new feature_context json column was added to ai_api_audit_logs

This allows us to store rich json like context on any LLM request
made.

This new field now stores automation id and name.

Additionally allows llm_triage to specify maximum number of tokens

This means that you can limit the cost of llm triage by scanning only
first N tokens of a post.
2024-10-23 16:49:56 +11:00
Roman Rizzi 72607c3560
Revert "FEATURE: Triage rule can skip posts created via email ()" ()
This reverts commit 6af415f7f0.
2024-08-27 15:45:55 -03:00
Roman Rizzi 6af415f7f0
FEATURE: Triage rule can skip posts created via email () 2024-08-27 12:04:55 -03:00
Roman Rizzi bed044448c
DEV: Remove old code now that features rely on LlmModels. ()
* DEV: Remove old code now that features rely on LlmModels.

* Hide old settings and migrate persona llm overrides

* Remove shadowing special URL + seeding code. Use srv:// prefix instead.
2024-07-30 13:44:57 -03:00
Natalie Tay f3b3312ce0
FIX: Avoid replying to the reply user for llm_triage automation ()
Avoid replying to the reply user. This causes an infinite conversation from the reply_user to the reply_user
2024-03-22 12:34:18 +08:00
Loïc Guitaut 6ae4218a96 DEV: Fix new Rubocop offenses 2024-03-06 15:23:29 +01:00
Rafael dos Santos Silva 1b72a00d2c
FEATURE: Option for AI triage to send a post to the review queue ()
Option for AI triage to send a post to the review queue
2024-02-29 12:33:28 +11:00
Sam a5d240991f
FEATURE: allow sending AI based report to a topic ()
This makes the reporting far more flexible cause it can target a
far wider audience by pointing it at a topic in a secure category
or an existing PM
2023-12-22 11:46:23 +11:00
Sam d0f54443ae
FEATURE: LLM based peroidical summary report ()
Introduce a Discourse Automation based periodical report. Depends on Discourse Automation.

Report works best with very large context language models such as GPT-4-Turbo and Claude 2.

- Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well)
- Adds GPT-4 turbo support to generic llm interface
2023-12-19 12:04:15 +11:00
Sam d87adcebea
FEATURE: Claude based scanning and OpenAI retries ()
llm_triage supported claude 2 in triage, this implements it

OpenAI rate limits frequently, this introduces some exponential
backoff (3 attempts - 3 seconds, 9 and 27)

Also reduces temp of classifiers so they have consistent behavior
2023-10-05 09:00:45 +11:00
Sam 0cbf14e343
FEATURE: automation rule for triaging posts using LLM ()
The new automation rule can be used to perform llm based classification and categorization of topics. 

You specify a system prompt (which has %%POST%% as an input), if it returns a particular piece of text then we will apply rules such as tagging, hiding, replying or categorizing.

This can be used as a spam filter, a "oops you are in the wrong place" filter and so on. 

Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
2023-10-03 08:55:30 +11:00