Invalid response from Embedding models

AI & Data Science NVIDIA NIM Models
,
1

Junk response is popping for embedding request for below model, with batch size 50 it is giving proper response but failing for more

{
“input”: [
“39”,
“40”,
“41”,
“42”,
“43”,
“44”,
“45”,
“46”,
“47”,
“48”,
“49”,
“50”,
“51”,
“52”,
“53”,
“54”,
“55”,
“56”,
“57”,
“58”,
“59”,
“60”,
“61”,
“62”,
“63”,
“64”,
“65”,
“66”,
“67”,
“68”,
“69”,
“70”,
“71”,
“72”,
“73”,
“74”,
“75”,
“76”,
“77”,
“78”,
“79”,
“80”,
“81”,
“82”,
“83”,
“84”,
“85”,
“86”,
“87”,
“88”,
“89”,
“90”,
“91”,
“92”,
“93”,
“94”,
“95”,
“96”,
“97”,
“98”,
“99”,
“100”,
“101”,
“102”,
“103”,
“104”,
“105”,
“106”,
“107”,
“108”
],
“truncate”: “NONE”,
“encoding_format”: “float”,
“input_type”: “passage”,
“model”: “nvidia/nv-embed-v1”
}

Other embed models like nvidia/embed-qa-4 giving proper response.

2

Hi @sumit.mehta are you downloading and hosting the NIM locally, or using the hosted version on the nvidia api catalogue?

Thanks

Sophie

3

I am using hosted version Nvidia api , below are the curl request ( attached ss)

curl --location ‘https://integrate.api.nvidia.com/v1/embeddings’
–header ‘Content-Type: application/json’
–header ‘Authorization: Bearer <Bearer_token>’
–data '{“input”:[“801”,“802”,“803”,“804”,“805”,“806”,“807”,“808”,“809”,“810”,“811”,“812”,“813”,“814”,“815”,“816”,“817”,“818”,“819”,“820”,“821”,“822”,“823”,“824”,“825”,“826”,“827”,“828”,“829”,“830”,“831”,“832”,“833”,“834”,“835”,“836”,“837”,“838”,“839”,“840”,“841”,“842”,“843”,“844”,“845”,“846”,“847”,“848”,“849”,“850”,“851”,“852”,“853”,“854”,“855”,“856”,“857”,“858”,“859”,“860”,“861”,“862”,“863”,“864”,“865”,“866”,“867”,“868”,“869”,“870”,“871”,“872”,“873”,“874”,“875”,“876”,“877”,“878”,“879”,“880”,“881”,“882”,“883”,“884”,“885”,“886”,“887”,“888”,“889”,“890”,“891”,“892”,“893”,“894”,“895”,“896”,“897”,“898”,“899”,“900”],“truncate”:“NONE”,“encoding_format”:“float”,“input_type”:“passage”,“model”:“nvidia/nv-embed-v1”} ’

Screenshot 2025-04-14 215059
Screenshot 2025-04-14 2150591381×766 74.7 KB

4

Hi @sumit.mehta we have filed a bug with the right team internally, and I’ll let you know when there are updates. Thanks for bringing this to our attention!

Best,

Sophie