text-embeddings-inference icon indicating copy to clipboard operation
text-embeddings-inference copied to clipboard

Input validation error: inputs must have less than 512 tokens

Open ellahe-git opened this issue 1 year ago • 4 comments

text-embeddings-router start an embedding serving, but always got the error 【 Input validation error: inputs must have less than 512 tokens】,which param should i use to change max tokens of input?512 is too short, i can not find true param in RAEDME or --help

To solve the issue of 'Input validation error: inputs must have less than 512 tokens', I added the auto truncate parameter to' true 'when starting the Docker image, but the image failed to start. What is the reason for this? The startup command is as follows: Docker run -- rm -- gpus all - d - p 18082:80-- name multilingual-e5-large-v 'model mount address'' mirror address' -- model id 'model id' --auto-truncate true

ellahe-git avatar Aug 06 '24 05:08 ellahe-git

I am also facing the same issue. Looks like --max-input-tokens flag has not been written to allow us to specify it during the startup.

vjsrinath avatar Aug 08 '24 02:08 vjsrinath

I am also facing the same issue, too

lluck42 avatar Aug 21 '24 02:08 lluck42

same here

atlas-comstock avatar Aug 28 '24 03:08 atlas-comstock

this is a problem of model but not TEI. You can see on other issue. issue365

lluck42 avatar Aug 30 '24 00:08 lluck42

This limit is set by the model. TEI only enforces it and cannot update it.

OlivierDehaene avatar Oct 17 '24 10:10 OlivierDehaene