[imagem] Concerns over personal privacy with the AI plugin Discourse AI was built agnostic from AI providers since day one, so the admins can pick an AI provider that they trust with the data I’ve been struggling to set up Embeddings with Mistral AI, I suspect because Mistral requires a model …

Try setting mistral-embed in the “Model name” field, that appears after you select “Provider” as OpenAI.

Thanks, that works :+1: I’m struggling to find out what would be the best tokenizer to use for this use case though. The Mixtral tokenizer is not selectable here. Do you have any suggestions?

Your post above token length according to some tokenizers: OpenAI: 45 Mixtral: 52 Gemini: 47 E5: 50 bge-large-en: 49 bge-m3: 50 mpnet: 49 Looks like Mistral-embed doesn’t differ much from the others. And since it supports a very large context window of 8k, you should be safe picking any and …

Looks like mistral-embed uses the same tokenizer as the first Mixtral model, and we already ship that anyway, so what do you think about enabling that tokenizer in the embeddings config page @Roman ?

Sure. I don’t see why not if it’s already there. This change will add it to the available options: https://github.com/discourse/discourse-ai/pull/1258

Como implementar Mistral com Embeddings

Suporte

Roman (Roman Rizzi) Abril 11, 2025, 2:44pm 6

Claro. Não vejo por que não, se já está lá. Esta alteração adicionará às opções disponíveis:

Tópico		Respostas	Visualizações
Use Mistral for embeddings Feature ai	1	154	6 de Abril de 2026
Support for Mistral API Feature ai	1	599	26 de Dezembro de 2023
Self-Hosting Embeddings for DiscourseAI Self-Hosting ai , ai-search , related-topics	21	2997	14 de Abril de 2025
Can´t set ai embedding model Support ai	3	217	16 de Julho de 2025
Warning of embedding `input must have less than 8192 tokens` with discourse ai Support ai	5	274	3 de Novembro de 2025

Como implementar Mistral com Embeddings

Tópicos relacionados