jina-ai/clip-as-service
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
PythonNOASSERTION
Issues
- 0
Support open-clip-torch 2.24.0
#951 opened by onny - 0
Support docarray 0.40.0
#950 opened by onny - 0
- 0
webui
#948 opened by jacky68147527 - 5
About client API searching function
#921 opened by kkiskkk - 0
How to set custom ports for replicas
#947 opened by iaroslav-geraskin - 0
Custom model abstractions
#946 opened by miguelalba96 - 7
- 1
how to get textual and visual onnx model
#940 opened by susht3 - 1
- 1
想用Chinese-CLIP项目中的中文CLIP模型
#932 opened by jkyeah - 2
An exception when executing "python -m clip_server"
#937 opened by sawsam - 9
download links for visual and textual are expired
#931 opened by pasa13142 - 0
- 0
- 4
Can't start ['clip_t'] when starting the server.
#924 opened by Charlestar - 0
- 0
About Openclip "coca_ViT-L-14" model
#928 opened by yiluzhou1 - 5
Building docker image throws error
#926 opened by pasa13142 - 9
- 3
rank function, sorting images according to text returns empty results, only scores
#922 opened by kkiskkk - 3
How to use local clip model when start server
#925 opened by MrRace - 1
Executor config,Make the following changes to torch-flow.yml, butBut it still executes according to the default configuration。
#923 opened by kkiskkk - 0
Reporting a vulnerability
#907 opened by igibek - 0
Model bert_uncased_L-12_H-768_A-12
#920 opened by edersoncorbari - 0
- 2
How to properly build the cuda.dockerfile
#902 opened by themantalope - 1
Modal Serverless GPU Integration
#916 opened by DoctorSlimm - 0
- 1
- 2
- 1
Is there a plan to support the latest pretrained ViT CLIP model (ViT-G/14 on LAION-2B) ?
#912 opened by joyjayng - 2
_transform_ndarray vs _transform_blob
#904 opened by mrjackbo - 3
Converting the model to onnx introduces errors
#908 opened by geekchen007 - 2
- 3
How to get dynamic word vectors
#905 opened by MarrytheToilet - 1
TRT Server Not Starting
#901 opened by andrearosasco - 5
- 6
基于WIN11的LINUX子系统安装CLIP报错
#895 opened by billhuang6277 - 1
Support huggingface transformers clip model?
#884 opened by ScottishFold007 - 2
Which framework maximizes inference speed ?
#877 opened by SimJeg - 2
Does it support multiple gpu's running simultaneously on one machine? Maximize inference speed
#886 opened by ScottishFold007 - 1
- 3
Error when using Client.encode() on a docarray created from the amazon-berkeley-objects-dataset
#879 opened by devinzli - 1
When will it support Python3.11
#887 opened by learningpro - 1
- 2
Issue with public server
#892 opened by Techsetter - 1
Compatibility with OWL-ViT
#891 opened by NOT-HAL9000 - 3
- 12
想了解分发任务的通信架构如何实现
#885 opened by fqzhao-win