is there any tool to split input text into chunks? or which embedding api support more than 8192 tokens? i am using Qwen/Qwen3-Embedding-0.6B Message (15 copies reported) OpenAI Embeddings failed with status: 413 body: {"code":20042,"message":"input must have less than 8192 tokens","data":null} …

If you self-host that same model, it can take up to 32k tokens. It is what we run on our hosting these days. If that’s out of the question, then you need to configure the embeddings model to limit inputs to the maximum allowed on your provider. This way, our AI Bot RAG will split uploaded files int…

how to configure embedding model? in discourse ?or model provider?

i am sure Qwen/Qwen3-Embedding-0.6B support up to 32k tokens and i have configured sequence length 32k [image] [image] but there still are many error of embedding [image] [image] [image]

[이미지] whitewaterdeu: i am sure Qwen/Qwen3-Embedding-0.6B support up to 32k tokens It does if your API providers allows it. [이미지] whitewaterdeu: but there still are many error of embedding If your API provider limits it to 8192, you gotta follow their rules.

Discourse AI에서 임베딩 시 `input must have less than 8192 tokens` 경고 발생

제품 지원

Falco (Falco) 11월 2, 2025, 5:08오후 5

API 제공업체가 허용한다면 가능합니다.

API 제공업체가 8192로 제한하고 있다면, 그들의 규칙을 따라야 합니다.

글		댓글	조회수
Embedding of post is not being properly truncated in discourse-ai plugin Bug ai	4	491	8월 17, 2023
Ai:embeddings:backfill - Handling OpenAI's 400 Error for Excessive Tokens in Embeddings Bug ai	9	1025	3월 15, 2024
AI exceeds LLM token thresholds randomly and unpredictably Product Support ai	3	232	5월 6, 2026
Adding Semantic Search feature for our self-hosted discourse site Product Support ai , ai-search	9	464	3월 19, 2025
Gemini API Embedding Configuration Clarification Product Support ai	3	584	10월 16, 2025

Discourse AI에서 임베딩 시 `input must have less than 8192 tokens` 경고 발생

Related topics