Resumen semanal de temas de IA

Comentarios del sitio Resúmenes del foro
91

Weekly Summary of AI Activity on meta.discourse.org

Period: 2025-10-13 to 2025-10-20

Overview

This week, AI discussions spanned search UX improvements, localization quirks, embeddings configuration, and bug fixes post-upgrade. Administrators and developers delved into making AI search results more discoverable, tweaking Gemini embeddings settings, and resolving errors introduced in the 3.6.0 beta. Community members also explored using Discourse for niche groups, tested local LLM integrations, and reported composer glitches with pasted images. Major themes hit #ai-support, ai-search, Bug, Community, and UX.

“We just deployed a big improvement to the underlying tech that powers semantic search…” — Falco ref
“Many users are still wary of AI so they don’t toggle the switch…” — RBoy ref

Interesting Topics

  • Hiding XX results found using AI—enable toggle by default (Support ai ai-search)
    RBoy kicked off the thread by noting that AI search results were hidden by default. NateDhaliwal pointed to existing docs ref, and Falco explained how it now auto-toggles when native results are missing ref. A temporary theme script to force the toggle was also shared ref.

  • Falsche Übersetzung, wenn post locale = UI locale (Bug ai dynaloc content-localization)
    Jakob_Naumann reported that English posts were showing up in German after a default-locale change ref. Falco recommended purging and re-creating the localization cache ref.

  • Gemini API Embedding Configuration Clarification (Support ai)
    RBoy asked what sequence length maps to in the embedding settings and how to throttle API backfills to avoid 429 errors ref. Falco confirmed sequence length equals the model’s token capacity (2048) and pointed out the hidden ai_embeddings_backfill_batch_size setting ref.

  • Exploring Reranking Options for Discourse AI (Support ai)
    In a longer-running thread, Falco rolled out a major semantic search improvement ref, expected to reduce reliance on external rerankers. tpetrov queried support for uploaded RAG documents versus forum topics ref, and Falco confirmed the change covers all embedding use cases ref.

  • Would this work for a community of women over 45+ (Community ai)
    bessnlj wondered if Discourse with AI-powered search fits a niche dating/coaching site ref. tobiaseigen clarified that meta.discourse.org is for Discourse hosts but encouraged spinning up a trial for custom use ref and pointed to existing communities for inspiration ref.

  • Local Ollama is not working with the Plugin (Support ai)
    Tikkel faced an “Internal Server Error” when Discourse called the Ollama service, despite successful cURL tests ref. Falco asked for container logs ref, and Tikkel confirmed that adjusting DISCOURSE_ALLOWED_INTERNAL_HOSTS syntax to use pipes solved it ref.

  • Gemini Embeddings Issue After Discourse Update to 3.6.0 Beta 2 (Support ai)
    Upgrading to 3.6.0.beta2 broke embedding tests for RBoy, who spotted that Gemini’s old embedding-001 model was retired ref. He fixed it by switching to gemini-embedding-001 in the plugin settings ref.

  • Embedding error with 3.6.0 beta 2 (Bug ai)
    A related bug, reported by RBoy, showed “invalid input syntax for type halfvec: “[NULL]”” when querying embeddings post-upgrade ref. This points to null-vector handling issues in the new release.

  • After sending the image, add this to the beginning of the message: [object InputEvent] (Bug ai)
    kuaza discovered that copy-pasting images into the composer prepends an [object InputEvent] string ref. Uploading via the file selector avoids the glitch, leading to further UX tweaks.

  • How to solve discourse ai: No endpoints found that support tool use (Support ai)
    whitewaterdeu saw a 404 “No endpoints found that support tool use” error testing OpenRouter’s qwen3-8b model ref. Disabling native tool integration resolved the issue ref.

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile: