jina-ai / clip-as-service

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

https://clip-as-service.jina.ai

jina-ai/clip-as-service Issues

Did anybody try to load BAAI/bge-m3 model in clip-as-service?
Updated a month ago
webui
Updated a month ago
About client API searching function
Updated a month ago5
How to set custom ports for replicas
Updated 2 months ago
Custom model abstractions
Updated 3 months ago
Creating an additional download source for clip onnx models
Updated 4 months ago7
Installing from readme instructions does not work, Flow is aborted due to ['clip_t'] can not be started.
Closed a year ago4
how to get textual and visual onnx model
Updated 6 months ago1
cn_clip miss & unexpected keyword argument 'global_average_pool'
Closed 6 months ago1
想用Chinese-CLIP项目中的中文CLIP模型
Updated 6 months ago1
An exception when executing "python -m clip_server"
Closed 6 months ago2
download links for visual and textual are expired
Updated 6 months ago9
Please add "EVA: Visual Representation Fantasies from BAAI"
Updated 7 months ago
trtexec throws error related to constant_folding(trt v8601)
Closed 7 months ago
Can't start ['clip_t'] when starting the server.
Updated 8 months ago4
sending uris as batch throws unexpected mimetype: text/html SOMETIMES*
Updated 8 months ago
About Openclip "coca_ViT-L-14" model
Updated 9 months ago
Building docker image throws error
Updated 9 months ago5
Running Docker image with customized yaml doesnt work
Updated 9 months ago9
rank function, sorting images according to text returns empty results, only scores
Updated 9 months ago3
How to use local clip model when start server
Updated 10 months ago3
Executor config，Make the following changes to torch-flow.yml， butBut it still executes according to the default configuration。
Updated 10 months ago1
Reporting a vulnerability
Closed 10 months ago
Model bert_uncased_L-12_H-768_A-12
Updated 10 months ago
the jina version is different between tensorrt.dockerfile and setup.py
Updated 10 months ago
How to properly build the cuda.dockerfile
Closed 10 months ago2
Modal Serverless GPU Integration
Updated a year ago1
Multilingual Models with ONNX: Missing Python Package
Updated a year ago
TensorRT support for openai/clip-vit-large-patch14-336
Updated a year ago1
sam-as-a-service | Segment anything as a service possible?
Updated a year ago2
Is there a plan to support the latest pretrained ViT CLIP model (ViT-G/14 on LAION-2B) ?
Closed a year ago1
_transform_ndarray vs _transform_blob
Closed a year ago2
Converting the model to onnx introduces errors
Updated a year ago3
how to work with the failed instance in the input batch
Updated a year ago2
How to get dynamic word vectors
Closed a year ago3
TRT Server Not Starting
Updated a year ago1
Text & Image Search Playground is throwing an exception
Updated a year ago5
基于WIN11的LINUX子系统安装CLIP报错
Closed a year ago6
Support huggingface transformers clip model?
Closed a year ago1
Which framework maximizes inference speed ?
Closed a year ago2
Does it support multiple gpu's running simultaneously on one machine? Maximize inference speed
Closed a year ago2
how to transform CLIP to TensorRT, ONNX, TorchScript?
Closed a year ago1
Error when using Client.encode() on a docarray created from the amazon-berkeley-objects-dataset
Updated a year ago3
When will it support Python3.11
Closed a year ago1
bugs
Closed a year ago1
Issue with public server
Updated a year ago2
Compatibility with OWL-ViT
Updated a year ago1
can we modify disk storage partation for clip embeddings?
Closed a year ago3
想了解分发任务的通信架构如何实现
Closed a year ago12
Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same
Closed a year ago9