{"data":{"slug":"jina-ai-clip-as-service","name":"clip-as-service","tagline":"Scalable embedding, reasoning, ranking for images and sentences with CLIP","github_url":"https://github.com/jina-ai/clip-as-service","owner":"jina-ai","repo":"clip-as-service","owner_avatar_url":"https://avatars.githubusercontent.com/u/60539444?v=4","primary_language":"Python","stars":12833,"forks":2064,"topics":["bert","bert-as-service","clip-as-service","clip-model","cross-modal-retrieval","cross-modality","deep-learning","image2vec","multi-modality","neural-search","onnx","openai","pytorch","sentence-encoding","sentence2vec"],"archived":false,"github_pushed_at":"2024-01-23T10:33:43+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/jina-ai-clip-as-service","markdown_url":"https://www.graphcanon.com/tools/jina-ai-clip-as-service.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jina-ai-clip-as-service","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jina-ai-clip-as-service","description":"🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP","homepage_url":"https://clip-as-service.jina.ai","license":"Other","open_issues":304,"watchers":217,"ai_summary":"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.","readme_excerpt":"# pip install clip-client\nfrom clip_client import Client\n\nc = Client(\n    'grpcs://<your-inference-address>-grpc.wolf.jina.ai',\n    credential={'Authorization': '<your access token>'},\n)\n\nr = c.encode(\n    [\n        'First do it',\n        'then do it right',\n        'then do it better',\n        'https://picsum.photos/200',\n    ]\n)\nprint(r)\n```\n</td>\n</tr>\n</table>\n\n---\n\n## Install\n\nCLIP-as-service consists of two Python packages `clip-server` and `clip-client` that can be installed _independently_. Both require Python 3.7+.\n\n---\n\n### Install server\n\n<table>\n<tr>\n<td> Pytorch Runtime ⚡ </td>\n<td> ONNX Runtime ⚡⚡</td>\n<td> TensorRT Runtime ⚡⚡⚡ </td>\n</tr>\n<tr>\n<td>\n\n```bash\npip install clip-server\n```\n\n</td>\n<td>\n\n```bash\npip install \"clip-server[onnx]\"\n```\n\n</td>\n<td>\n\n```bash\npip install nvidia-pyindex \npip install \"clip-server[tensorrt]\"\n```\n</td>\n</tr>\n</table>\n\nYou can also [host the server on Google Colab](https://clip-as-service.jina.ai/hosting/colab/), leveraging its free GPU/TPU.\n\n---\n\n### Install client\n\n```bash\npip install clip-client\n```","github_created_at":"2018-11-12T10:48:50+00:00","created_at":"2026-07-11T23:10:44.224264+00:00","updated_at":"2026-09-20T04:29:34.890869+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"bert","name":"bert"},{"slug":"clip-as-service","name":"clip-as-service"},{"slug":"clip-model","name":"clip-model"},{"slug":"cross-modal-retrieval","name":"cross-modal-retrieval"},{"slug":"cross-modality","name":"cross-modality"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"image2vec","name":"image2vec"},{"slug":"multi-modality","name":"multi-modality"}],"trust":{"provenance":{"is_fork":false,"github_id":157198623,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:16:54.419Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":968,"last_release_at":"2023-12-20T04:13:56Z","stars_delta_30d":-1,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:16:56.633Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:16:53.205Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:16:53.205Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-18T08:16:53.205Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"unknown","summary":"The repository does not provide specific pricing information for using clip-as-service."},"requirements":{"notes":["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+."],"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"pricing_model":"unknown","requires_docker":false},"when_to_use":["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.","When you want to host the server on Google Colab to take advantage of free GPU/TPU resources.","If you are working with Python 3.7+ and prefer a client-server architecture for your embedding tasks."],"when_not_to_use":["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.","If you do not have access to or do not want to use Google Colab for hosting the server.","When your project is not compatible with Python 3.7+ or you prefer a different programming language."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:36:11.590Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"unknown","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"unknown - The repository does not provide specific pricing information for using clip-as-service."},{"label":"Requirements","value":"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+."},{"label":"Adopt for","value":"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."}]}}