I’m new to discourse AI. I’m using “sentence-transformers/all-mpnet-base-v2” as my embedding model. is this enough to do semantic search? Or Should i have to add a Hyde model for it? Please guide me on this.

[immagine] Ajindiscource: Or Should i have to add a Hyde model for it? You also need an LLM for semantic search. If you want to self-host see Self-Hosting an OpenSource LLM for DiscourseAI .

Thank you so much. Can you gimme an idea on the requirements to host model like “mistralai/Mistral-7B-Instruct-v0.2” on-prem and in cloud as well for an enterprise level website, please. And also i cant able to find any tokenizers for this model in the admin panel.

[immagine] Ajindiscource: Can you gimme an idea on the requirements to host model like “mistralai/Mistral-7B-Instruct-v0.2” on-prem and in cloud as well for an enterprise level website, please. There is nothing Discourse specific here, so standard rules apply. A 7B model, if ran using fp16, w…

Can you suggest us some LLM models for this scenario? We might be hosting our model on prem, so would like to know the compatibility factor of the models with Discourse. Thank you.

Depends on you budget, language support target, and what features of Discourse AI you want. Today Qwen 2.5 Instruct in 32B or 72B are a strong contender.

Is there any way that we can use a smaller model for the summarization feature? Because LLM’s take a bigger budget, and we might have to settle for something smaller for now…

Yes, you can use any model you want.

Can we alter the payload to the model for summarization or any other function? Especially, I want to change the system’s content. {‘role’: ‘system’, ‘content’: ‘You are an advanced summarization bot that generates concise, coherent summaries of provided text.\n\n- Only include the summary, withou…

That is not possible at the moment, but we already started work on making it possible. Should land in the coming weeks.

Aggiunta della funzione di Ricerca Semantica per il nostro sito Discourse auto-ospitato

Supporto

Falco (Falco) 19 Marzo 2025, 7:12pm 10

Al momento non è possibile, ma abbiamo già iniziato a lavorare per renderlo possibile. Dovrebbe arrivare nelle prossime settimane.

Argomento		Risposte	Visualizzazioni
Setup Inquiry: AI Summarization in Discourse & LLM Integration Support ai	10	397	Ottobre 6, 2025
Discourse AI - Self-Hosted Guide Self-Hosting ai	59	14686	Maggio 20, 2024
What LLM to use for Discourse AI? Site Management how-to , ai	0	977	Gennaio 23, 2025
Estimating cost of enabling Discourse AI for related content and search Support ai	2	224	Ottobre 28, 2025
Discourse AI - Large Language Model (LLM) settings page Site Management how-to , ai	1	4358	Settembre 30, 2024

Aggiunta della funzione di Ricerca Semantica per il nostro sito Discourse auto-ospitato

Argomenti correlati