clip-as-service
Scalable embedding, reasoning, ranking for images and sentences with CLIP
GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
53views this month
Decision brief
clip-as-service offers scalable embedding, reasoning, and ranking for images and sentences using the CLIP model, with support for Pytorch, ONNX, and TensorRT runtimes.
Good fit when
- When you need to leverage the CLIP model for cross-modal retrieval tasks involving both images and text.
- If you require a scalable solution that supports multiple runtimes including Pytorch, ONNX, and TensorRT.
Avoid when
- If you are looking for a solution that does not support the CLIP model specifically and requires a different model for embeddings.
- When you do not need the scalability provided by multiple runtimes and prefer a simpler setup.
- Pricing:
- unknown - The repository does not provide specific pricing information for using clip-as-service.
- Requirements:
- Min 4 GB RAM; The server requires Python 3.7+ and supports Pytorch, ONNX, and TensorRT runtimes.; The client can be installed independently and also requires Python 3.7+.
Observed Sep 18, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (968d since push)
- As of Sep 18, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 18, 2026
- Security (OSV)
- No lockfile
- As of Sep 18, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install clip-as-serviceSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
CLIP-as-service provides scalable embedding, reasoning, and ranking capabilities for images and sentences using the CLIP model. It consists of two Python packages: clip-server and clip-client, which can be installed independently. The server supports Pytorch, ONNX, and TensorRT runtimes, while the client allows for easy encoding of text and images.
Capability facts
- Languages
- python
Source: github.language · Sep 18, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Sep 18, 2026)
CLIP-as-service consists of two Python packages `clip-server` and `clip-client` that can be installed _independently_.Source link
Tags
README
pip install clip client from clip client import Client c = Client( 'grpcs://<your inference address grpc.wolf.jina.ai', credential={'Authorization': '<your access token '}, ) r = c.encode( [ 'First do it', 'then do it right', 'then do it better', 'https://picsum.photos/200', ] )...
For agents
This page has a .md twin and JSON over the API.