{"data":{"slug":"different-ai-embedbase","name":"embedbase","tagline":"A dead-simple API to build LLM-powered apps","github_url":"https://github.com/different-ai/embedbase","owner":"different-ai","repo":"embedbase","owner_avatar_url":"https://avatars.githubusercontent.com/u/118544361?v=4","primary_language":"TypeScript","stars":523,"forks":54,"topics":["ai","artificial-intelligence","chatgpt","chatgpt-plugin","embeddings","gpt-4","machine-learning","natural-language-processing","openai","pgvector","supabase","vector-database"],"archived":false,"github_pushed_at":"2024-11-27T22:10:36+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/different-ai-embedbase","markdown_url":"https://www.graphcanon.com/tools/different-ai-embedbase.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/different-ai-embedbase","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=different-ai-embedbase","description":"A dead-simple API to build LLM-powered apps","homepage_url":"https://docs.embedbase.xyz","license":"MIT","open_issues":35,"watchers":7,"ai_summary":"Embedbase provides a simple API for building applications powered by Large Language Models (LLMs) using embeddings and integration with vector databases.","readme_excerpt":"## Installation\n`npm i embedbase-js`\n\n```js\nimport { createClient } from 'embedbase-js'\n// initialize client\nconst embedbase = createClient(\n  'https://api.embedbase.xyz',\n  '<grab me here https://app.embedbase.xyz/>'\n)\n \nconst question =\n  'im looking for a nice pant that is comfortable and i can both use for work and for climbing'\n \n// search for information in a pre-defined dataset and returns the most relevant data\nconst searchResults = await embedbase.dataset('product-ads').search(question)\n \n// transform the results into a string so they can be easily used inside a prompt\nconst stringifiedSearchResults = searchResults\n  .map(result => result.data)\n  .join('')\n \nconst answer = await embedbase\n  .useModel('openai/gpt-3.5-turbo')\n  .generateText(`${stringifiedSearchResults} ${question}`)\n \nconsole.log(answer) // 'I suggest considering harem pants for your needs. Harem pants are known for their ...'\n```","github_created_at":"2022-12-26T12:56:20+00:00","created_at":"2026-07-11T11:28:11.511116+00:00","updated_at":"2026-08-22T00:01:18.574231+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":"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","name":"ai"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"embeddings","name":"embeddings"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"natural-language-processing","name":"natural-language-processing"},{"slug":"openai","name":"openai"},{"slug":"vector-database","name":"vector-database"}],"trust":{"provenance":{"is_fork":false,"github_id":582319835,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T00:01:17.334Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":632,"last_release_at":"2023-07-04T19:47:46Z","stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:28:12.596Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T00:01:17.810Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-22T00:01:17.810Z"},"languages":{"value":["typescript","python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-22T00:01:17.810Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-22T00:01:17.810Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["* Use Embedbase if you require direct integration capabilities specifically designed for embeddings and vector databases, like pgvector or Supabase.","* Opt for Embedbase when your project benefits from a lightweight API that emphasizes simplicity in integrating machine learning functionalities without overwhelming setup."],"when_not_to_use":["* Avoid using Embedbase if your application's technology stack cannot effectively integrate TypeScript, as its primary language support is in this framework and not others like Python.","* Do not use it when you need extensive customization options for the vector database configurations beyond what pgvector or Supabase offers."],"source":"enrich:decision_facts","observed_at":"2026-07-12T03:12:40.431Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Embedbase is a TypeScript-based API designed to facilitate the creation of Large Language Model (LLM) powered applications via integrations with embeddings and vector databases."}]}}