discourse-ai/lib/modules
Sam 30778d8af8
FIX: avoid storing corrupt prompts (#92)
```
prompt << build_message(bot_user.username, reply)
```

Would store a "cooked" prompt which is invalid, instead just store the raw
values which are later passed to build_message

Additionally:

1. Disable summary command which needs honing
2. Stop storing decorations (searched for X) in prompt which leads to straying
3. Ship username directly to model, avoiding "user: content" in prompts. This
 was causing GPT to stray
2023-06-20 15:44:03 +10:00
..
ai_bot FIX: avoid storing corrupt prompts (#92) 2023-06-20 15:44:03 +10:00
ai_helper FEATURE: Multi-model support for the AI Bot module. (#56) 2023-05-11 10:03:03 -03:00
embeddings FIX: Ensure embeddings database outages are handled gracefully (#80) 2023-05-23 22:57:52 +01:00
nsfw FEATURE: Handle invalid media in NSFW module (#57) 2023-05-11 15:35:39 -03:00
sentiment DEV: DiscourseAI -> DiscourseAi rename to have consistent folders and files (#9) 2023-03-14 16:03:50 -03:00
summarization FEATURE: Allow using large context OpenAI models for summarization (#86) 2023-06-13 15:23:48 -03:00
toxicity DEV: applies chat namespacing (#12) 2023-03-17 15:15:38 +01:00