I’m trying to setup the AI spam detector for my own Discourse instance, but have several questions: The system prompt of spam detector persona can’t be edited. I can create a new persona but there is no field to make Discourse know that it is going to be used as a spam detector? I want to use Qwen…

I just did a quick setup and it works fine selecting the custom persona for spam. [Screenshot 2025-11-19 at 1.54.11 PM] [Screenshot 2025-11-19 at 1.51.51 PM] Let us know again if you are not able to do so via /discourse-ai/ai-spam

Hi there, to answer your question: [صورة] lilydjwg: What does the tokenizer do here? From the docs: [صورة] Discourse AI - Large Language Model (LLM) settings page What is tokenizer? The tokenizer translates strings into tokens, which is what a model uses to understand the input.

Thanks, but I know what a tokenizer is. What I don’t know is what Discourse uses it for, and what would happen if I picked the wrong tokenizer? I don’t need a tokenizer to call an LLM anyway.

[صورة] lilydjwg: The system prompt of spam detector persona can’t be edited. Can you try visiting this https://<your-site>/admin/plugins/discourse-ai/ai-spam - it should allow you to select your persona insert custom instructions and test against a post [صورة] lilydjwg: Does QwenTokeni…

[صورة] nat: insert custom instructions IIUC this instruction is concatenated to the system prompt instead of replacing it, making the prompt even longer and have mixed languages… [صورة] nat: Yup you can go ahead and do that, then run the “Test” But passing the test doesn’t mean there …

Thanks, so that “spam detector” label only affects the list filering of personas? I’ll setup a test environment and try it.

I checked the source code. If I didn’t make mistakes, the tokenizer is used for two things: count tokens for statistics and price estimation, and truncate posts to the set limit. So it shouldn’t affect me a lot if a wrong one is used.

إحباطات بشأن كاشف البريد العشوائي للذكاء الاصطناعي

الدعم

NateDhaliwal (Nate Dhaliwal) 19 نوفمبر 2025، 3:59ص 2

مرحباً، للإجابة على سؤالك:

من الوثائق:

الموضوع		الردود	مرات العرض
Discourse AI - Large Language Model (LLM) settings page Site Management ai , how-to	20	3156	26 نوفمبر 2025
AI powered Spam detection Announcements spam , ai	11	1022	11 يناير 2025
Discourse AI - Spam detection Site Management moderation , spam , how-to , ai	32	3667	10 مارس 2026
Introducing Discourse AI Blog	26	3793	4 مايو 2023
What's the cheapest/best AI to use for AI Spam? Support spam , ai	6	282	18 مارس 2025

إحباطات بشأن كاشف البريد العشوائي للذكاء الاصطناعي

الموضوعات ذات الصلة