huggingface/text-embeddings-inference

Issues

• Support jinaai/jina-embeddings-v3

  #418 opened 2 months ago by luonist
  4

• Using CPU Image without ONNX

  #388 opened 3 months ago by ramipellumbi
  0

• Allow fetching token embeddings from a cross-encoding

  #407 opened 2 months ago by dan-octo
  1

• Health check endpoint is also locked behind API KEY once API_KEY is set, causing healthchecks to fail

  #427 opened a month ago by Jason-CKY
  2

• Download of BAAI/bge-m3 fails on 1.5 using ONNX

  #417 opened 2 months ago by avvertix
  4

• Inconsistent Embeddings with SentenceTransformer

  #420 opened a month ago by lytning98
  2

• Could auto-truncate also deal with character limits?

  #364 opened a month ago by qherreros
  0

• Better HTTP Status Code for Empty Requests

  #365 opened a month ago by mbbyn
  5

• Support Alibaba-NLP/gte-multilingual-base & Alibaba-NLP/gte-multilingual-reranker-base

  #366 opened a month ago by sigridjineth
  4

• Input validation error: inputs must have less than 512 tokens

  #369 opened a month ago by ellahe-git
  5

• C API/ C Wrapper API

  #370 opened a month ago by 0110G
  1

• how to support a SequenceClassification model

  #371 opened a month ago by homily707
  1

• /embed_sparse Parameters

  #372 opened a month ago by dbc-2024
  0

• Local intall failure

  #373 opened a month ago by plageon
  3

• Automatically split batches > MAX_CLIENT_BATCH_SIZE

  #378 opened a month ago by leversberg
  1

• How do i deploy to vertex ?

  #380 opened a month ago by pulkitmehtaworkmetacube
  1

• Question for released docker image

  #383 opened a month ago by PeterYang12
  1

• TEI fails for Finetuned JinaAI Embeddings models

  #384 opened a month ago by StefanRaab
  2

• Incomplete tutorial

  #395 opened a month ago by sleepingcat4
  1

• Support NV-Embed-v2 model

  #419 opened 2 months ago by jorgeantonio21
  1

• thread 'tokio-runtime-worker' panicked at /usr/src/backends/src/lib.rs:176:14

  #424 opened a month ago by jackli0127
  2

• Get opentelemetry trace id from request headers instead of creating a new trace

  #374 opened 3 months ago by ptanov
  2

• Use Nomic Embed from local weights

  #422 opened a month ago by sinaayyy
  0

• new model lier007/xiaobu-embedding-v2

  #423 opened a month ago by Mars-1990
  0

• 只是支持苹果系统吗

  #421 opened a month ago by Joker-sad
  0

• Feature Request: Multi-GPU inference or the ability to choose a GPU at startup

  #411 opened a month ago by dangerzone
  2

• Support env `HF_ENDPOINT`?

  #416 opened 2 months ago by yufeng97
  1

• Add support for other pooling methods in python backend

  #414 opened 2 months ago by OskarLiew
  0

• Different behavior between SentenceTransformer and TEI when using gte-large-en-v1.5

  #358 opened 2 months ago by Smityz
  5

• Too many router/tokenizer threads

  #404 opened 2 months ago by askervin
  1

• Too many model backend threads destroy performance when running on CPU

  #405 opened 2 months ago by askervin
  0

• Paged attention optimization for memory efficient continuously batched requests

  #391 opened 2 months ago by jorgeantonio21
  1

• CUDA_COMPUTE_CAP doesn't take effect in Dockerfile-cuda

  #381 opened 2 months ago by PeterYang12
  2

• Unsupported model IR version

  #355 opened 2 months ago by netw0rkf10w
  1

• serving bge-reranker-v2-m3

  #408 opened 2 months ago by gree2
  0

• Max Token Mismatch

  #406 opened 2 months ago by endomorphosis
  1

• unknown flag: --gpus See 'docker run --help'

  #397 opened 3 months ago by sswolf
  1

• Inconsistency in how different URL paths are handled (in inference endpoints)

  #398 opened 3 months ago by MoritzLaurer
  0

• dunzhang/stella_en_1.5B_v5 Maximum Token Limit Set to 512 Despite Model Capabilities

  #396 opened 3 months ago by taoari
  0

• Input validation error: `inputs` must have less than 32000 characters. Given: 67337

  #394 opened 3 months ago by ffalkenberg
  0

• can support bge-visualized ?

  #393 opened 3 months ago by whybeyoung
  0

• Adding support for stella_en_400M_v5

  #359 opened 4 months ago by netw0rkf10w
  2

• Input validation error: `inputs` must have less than 512 tokens. Given: 534

  #356 opened 4 months ago by gctian
  6

• add support bge-reranker-v2.5-gemma-lightweight

  #368 opened 4 months ago by ziozzang
  2

• `bge-reranker-v2-m3` model throughput benchmark

  #392 opened 3 months ago by rere950303
  0

• Request support for Llama Prompt Guard

  #354 opened 4 months ago by bluenevus
  3

• curl: (56) Recv failure: Connection reset by peer

  #387 opened 3 months ago by luyu0816
  1

• TEI failed to serve fine-tuned bge-m3 model

  #385 opened 3 months ago by KCFindstr
  0

• Support Alibaba-NLP/gte-large-en-v1.5 on CPU/MPS

  #375 opened 3 months ago by tmostak
  0

• [CPU][Performance] ort is slower than python backend

  #362 opened 4 months ago by zhuhaozhe
  0