{"data":{"slug":"awa-ai-awadb","name":"awadb","tagline":"AI Native Database for embedding vectors","github_url":"https://github.com/awa-ai/awadb","owner":"awa-ai","repo":"awadb","owner_avatar_url":"https://avatars.githubusercontent.com/u/134086017?v=4","primary_language":"C++","stars":175,"forks":16,"topics":["ai-native","aigc","chatgpt","embedding-vectors","llm","vectordb"],"archived":false,"github_pushed_at":"2024-11-04T08:36:21+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/awa-ai-awadb","markdown_url":"https://www.graphcanon.com/tools/awa-ai-awadb.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/awa-ai-awadb","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=awa-ai-awadb","description":"AI Native database for embedding vectors","homepage_url":"https://ljeagle.github.io/awadb","license":"Apache-2.0","open_issues":4,"watchers":7,"ai_summary":"AwaDB is an AI-native database designed for managing and searching embedding vectors with real-time capabilities and无需翻译剩余部分，因为它是中文的内容并且已经很简洁。我们可以直接使用英文描述来完成这个元数据。以下是完整的元数据信息：","readme_excerpt":"# AwaDB - AI Native Database for embedding vectors\n\nEasily Use - No boring database schema definition. No need to pay attention to vector indexing details.  \n\nRealtime Search - Lock free realtime index keeps new data fresh with millisecond level latency. No wait no manual operation.  \n\nStability - AwaDB builds upon over 5 years experience running production workloads at scale using a system called [Vearch](https://github.com/vearch/vearch), combined with best-of-breed ideas and practices from the community.\n\n## Run awadb locally on Mac OSX or Linux\n\nFirst install awadb:\n```bash\npip3 install awadb\n```\n\nThen use as below:\n```bash\nimport awadb\n# 1. Initialize awadb client!\nawadb_client = awadb.Client()\n\n# 2. Create table\nawadb_client.Create(\"test_llm1\") \n\n# 3. Add sentences, the sentence is embedded with SentenceTransformer by default\n#    You can also embed the sentences all by yourself with OpenAI or other LLMs\nawadb_client.Add([{'embedding_text':'The man is happy'}, {'source' : 'pic1'}])\nawadb_client.Add([{'embedding_text':'The man is very happy'}, {'source' : 'pic2'}])\nawadb_client.Add([{'embedding_text':'The cat is happy'}, {'source' : 'pic3'}])\nawadb_client.Add([{'embedding_text':'The man is eating'}, {'source':'pic4'}])\n\n# 4. Search the most Top3 sentences by the specified query\nquery = \"The man is happy\"\nresults = awadb_client.Search(query, 3)\n\n# Output the results\nprint(results)\n```\nHere the text is embedded by SentenceTransformer which is supported by [Hugging Face](https://huggingface.co)  \nMore detailed python local library usage you can read [here](https://ljeagle.github.io/awadb/)\n\n## Run AwaDB as a service \nIf you are on the Windows platform or want a awadb service, you can download and deploy the awadb docker.\nThe installation of awadb docker please see [here](https://github.com/awa-ai/awadb/tree/main/docs/source/docker_deploy.md)\n\n- Python Usage\n\nFirst, Install gRPC and awadb service python client as below:\n\n```bash\npip3 install grpcio\npip3 install awadb-client\n```\n\nA simple example as below:\n\n```bash\n# Import the package and module\nfrom awadb_client import Awa\n\n# Initialize awadb client\nclient = Awa()\n\n# Add dict with vector to table 'example1'\nclient.add(\"example1\", {'name':'david', 'feature':[1.3, 2.5, 1.9]})\nclient.add(\"example1\", {'name':'jim', 'feature':[1.1, 1.4, 2.3]})\n\n# Search\nresults = client.search(\"example1\", [1.0, 2.0, 3.0])\n\n# Output results\nprint(results)\n\n# '_id' is the primary key of each document\n# It can be specified clearly when adding documents\n# Here no field '_id' is specified, it is generated by the awadb server \ndb_name: \"default\"\ntable_name: \"example1\"\nresults {\n  total: 2\n  msg: \"Success\"\n  result_items {\n    score: 0.860000074\n    fields {\n      name: \"_id\" \n      value: \"64ddb69d-6038-4311-9118-605686d758d9\"\n    }\n    fields {\n      name: \"name\"\n      value: \"jim\"\n    }\n  }\n  result_items {\n    score: 1.55\n    fields {\n      name: \"_id\"\n      value: \"f9f3035b-faaf-48d4-a947-801416c005b3\"\n    }\n    fields {\n      name: \"name\"\n      value: \"david\"\n    }\n  }\n}\nresult_code: SUCCESS\n```\nMore python sdk for service is [here](https://ljeagle.github.io/awadb/)  \n\n- RESTful Usage\n```bash\n# add documents to table 'test' of db 'default', no need to create table first\ncurl -H \"Content-Type: application/json\" -X POST -d '{\"db\":\"default\", \"table\":\"test\", \"docs\":[{\"_id\":1, \"name\":\"lj\", \"age\":23, \"f\":[1,0]},{\"_id\":2, \"name\":\"david\", \"age\":32, \"f\":[1,2]}]}' http://localhost:8080/add\n\n# search documents by the vector field 'f' of the value '[1, 1]'\ncurl -H \"Content-Type: application/json\" -X POST -d '{\"db\":\"default\", \"table\":\"test\", \"vector_query\":{\"f\":[1, 1]}}' http://localhost:8080/search\n```\nMore detailed RESTful API is [here](https://github.com/awa-ai/awadb/tree/main/docs/source/restful_tutorial.md)\n\n\n## What are the Embeddings?\n\nAny unstructured data(image/text/audio/video) can be transferred to vectors which are generally understanded by computers through AI(LLMs or other deep neural networks).","github_created_at":"2023-05-19T16:22:02+00:00","created_at":"2026-07-11T23:19:01.173483+00:00","updated_at":"2026-08-02T18:00:59.988634+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"ai-native","name":"ai-native"},{"slug":"aigc","name":"aigc"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"embedding-vectors","name":"embedding-vectors"},{"slug":"llm","name":"llm"},{"slug":"vectordb","name":"vectordb"}],"trust":{"provenance":{"is_fork":false,"github_id":642912355,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-02T18:00:59.037Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":636,"last_release_at":null},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:19:03.636Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-02T18:00:59.697Z"},"languages":{"value":["c++","python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-02T18:00:59.697Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-02T18:00:59.697Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"requires_docker":true},"when_to_use":["When you prioritize ease of use without the need to define complex schemas or manage vector indexing details manually.","If your application requires real-time updates and searches with minimal latency in milliseconds.","For projects leveraging AI models like SentenceTransformer, as AwaDB supports text embedding out-of-the-box."],"when_not_to_use":["When the requirement is for a database that can also function seamlessly on Windows without docker deployment complexities.","If you need extensive customization of vector embedding processes beyond what AwaDB offers with its default integrations like SentenceTransformer."],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:56:42.548Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Requires Docker"},{"label":"Adopt for","value":"AwaDB is an AI-native database for embedding vectors, offering real-time indexing with millisecond latency and no manual operations."},{"label":"License detail","value":"This tool uses an Apache-2.0 license, allowing free use and modification for both commercial and non-commercial purposes, provided that the copyright notice is retained."}]}}