[圖片] 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 to b…

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

如何使用嵌入实现Mistral

支持

RGJ (Richard - Communiteq) 2025年四月10日 18:32 3

好的，这很有效

不过，我很难弄清楚在这种用例下使用哪种分词器最好。Mixtral 分词器在这里不可选。你有什么建议吗？

話題		回覆	觀看
Use Mistral for embeddings Feature ai	1	168	2026年四月6日
Support for Mistral API Feature ai	1	605	2023年十二月26日
Self-Hosting Embeddings for DiscourseAI Self-Hosting ai , ai-search , related-topics	21	3065	2025年四月14日
Can´t set ai embedding model Support ai	3	228	2025年七月16日
Warning of embedding `input must have less than 8192 tokens` with discourse ai Support ai	5	291	2025年十一月3日

如何使用嵌入实现Mistral

相關主題