[image] 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 t…

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 ?

How to implement Mistral with Embeddings

Support

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

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

Topic		Replies	Views
Use Mistral for embeddings Feature ai	1	86	April 6, 2026
Support for Mistral API Feature ai	1	551	December 26, 2023
Self-Hosting Embeddings for DiscourseAI Self-Hosting ai , ai-search , related-topics	21	2669	April 14, 2025
Can´t set ai embedding model Support ai	3	146	July 16, 2025
Warning of embedding `input must have less than 8192 tokens` with discourse ai Support ai	5	182	November 3, 2025

How to implement Mistral with Embeddings

Related topics