{"id":28528811,"url":"https://github.com/oramasearch/oramacore","last_synced_at":"2026-03-16T14:01:15.815Z","repository":{"id":272752376,"uuid":"877756055","full_name":"oramasearch/oramacore","owner":"oramasearch","description":"OramaCore is the complete runtime you need for your projects, answer engines, copilots, and search. It includes a fully-fledged full-text search engine, vector database, LLM interface, and many more utilities.","archived":false,"fork":false,"pushed_at":"2026-02-16T13:20:00.000Z","size":31422,"stargazers_count":230,"open_issues_count":10,"forks_count":19,"subscribers_count":3,"default_branch":"develop","last_synced_at":"2026-02-16T19:56:19.888Z","etag":null,"topics":["fulltext-search","inference","llms","vector-database","vector-search"],"latest_commit_sha":null,"homepage":"https://docs.orama.com/docs/cloud","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/oramasearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-10-24T07:31:27.000Z","updated_at":"2026-02-16T13:05:14.000Z","dependencies_parsed_at":"2025-02-17T11:21:00.972Z","dependency_job_id":"9eae4218-463f-466c-a1fa-cb7b27d10650","html_url":"https://github.com/oramasearch/oramacore","commit_stats":null,"previous_names":["oramasearch/orama-core","oramasearch/oramacore"],"tags_count":156,"template":false,"template_full_name":null,"purl":"pkg:github/oramasearch/oramacore","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oramasearch%2Foramacore","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oramasearch%2Foramacore/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oramasearch%2Foramacore/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oramasearch%2Foramacore/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oramasearch","download_url":"https://codeload.github.com/oramasearch/oramacore/tar.gz/refs/heads/develop","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oramasearch%2Foramacore/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29537122,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-17T05:00:25.817Z","status":"ssl_error","status_checked_at":"2026-02-17T04:57:16.126Z","response_time":100,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["fulltext-search","inference","llms","vector-database","vector-search"],"created_at":"2025-06-09T13:11:38.085Z","updated_at":"2026-02-17T07:58:38.487Z","avatar_url":"https://github.com/oramasearch.png","language":"Rust","funding_links":[],"categories":["Rust"],"sub_categories":[],"readme":"![OramaCore](/misc/oramacore.png)\n\n**OramaCore** is the AI runtime you need for your projects, answer engines,\ncopilots, and search.\n\nIt includes a fully-fledged full-text search engine, vector database, LLM\ninterface with action planning and reasoning, a JavaScript runtime to write and\nrun your own custom agents on your data, and many more utilities.\n\n## Getting Started\n\nThe absolute easier way to get started is by following the\n[docker-compose.yml](./docker-compose.yml) file that you can find in this\nrepository.\n\nYou can either clone the entire repo or setup `oramasearch/oramacore:latest` as\nimage in your `docker-compose.yml` file under the `oramacore` service.\n\nThen compile your\n[configuration file](https://docs.oramacore.com/docs/guide/configuration) and\nrun it:\n\n```sh\ndocker compose up\n```\n\nThis will create the following architecture, allowing you to perform\nhigh-performance RAG with little to zero configuration.\n\n![OramaCore Architecture](/docs/public/oramacore-arch.png)\n\nAn NVIDIA GPU is highly recommended for running the application. For production\nusage, we recommend using minimum one NVIDIA A100. Optimal configuration would\ninclude four NVIDIA H100.\n\n## Available Dockerfiles\n\nDepending on your machine, you may want to use different Docker images.\n\n| Application   | CPU/GPU                              | Docker image                                                                                            |\n| ------------- | ------------------------------------ | ------------------------------------------------------------------------------------------------------- |\n| **OramaCore** | X86_64                               | [`oramasearch/oramacore`](https://hub.docker.com/r/oramasearch/oramacore)                               |\n| **OramaCore** | ARM64 (Mac M series for example)     | [`oramasearch/oramacore-arm64`](https://hub.docker.com/r/oramasearch/oramacore-arm64)                   |\n| **AI Server** | Any CPU architecture, no CUDA access | [`oramasearch/oramacore-ai-server`](https://hub.docker.com/r/oramasearch/oramacore-ai-server)           |\n| **AI Server** | Any CPU architecture, CUDA available | [`oramasearch/oramacore-ai-server-cuda`](https://hub.docker.com/r/oramasearch/oramacore-ai-server-cuda) |\n\n## Using the JavaScript SDK\n\nYou can install the official JavaScript SDK with npm:\n\n```sh\nnpm i @orama/core\n```\n\nThen, you can start by creating a collection (a database index) with all of the\ndata you want to perform AI search \u0026 experiences on:\n\n```js\nimport { OramaCoreManager } from \"@orama/core\";\n\nconst orama = new OramaCoreManager({\n    url: \"http://localhost:8080\",\n    masterAPIKey: \"\u003cmaster-api-key\u003e\", // The master API key set in your config file\n});\n\nconst newCollection = await orama.createCollection({\n    id: \"products\",\n    writeAPIKey: \"my-write-api-key\", // A custom API key to perform write operations on your collection\n    readAPIKey: \"my-read-api-key\", // A custom API key to perform read operations on your collection\n});\n```\n\nThen, insert some data:\n\n```js\nimport { CollectionManager } from \"@orama/core\";\n\nconst collection = new CollectionManager({\n    url: \"http://localhost:8080\",\n    collectionID: \"\u003cCOLLECTION_ID\u003e\",\n    writeAPIKey: \"\u003cwrite_api_key\u003e\",\n});\n\n// You can insert a single document\nawait collection.insert({\n    title: \"My first document\",\n    content: \"This is the content of my first document.\",\n});\n\n// Or you can insert multiple documents by passing an array of objects\nawait collection.insert([\n    {\n        title: \"My first document\",\n        content: \"This is the content of my first document.\",\n    },\n    {\n        title: \"My second document\",\n        content: \"This is the content of my second document.\",\n    },\n]);\n```\n\nOramaCore will automatically generate highly optimized embeddings for you and\nwill store them inside its built-in vector database.\n\nNow you can perform vector, hybrid, full-text search, or let OramaCore decide\nwhich one is best for your specific query:\n\n```js\nimport { CollectionManager } from \"@orama/core\";\n\nconst collection = new CollectionManager({\n    url: \"http://localhost:8080\",\n    collectionID: \"\u003cCOLLECTION_ID\u003e\",\n    readAPIKey: \"\u003cread_api_key\u003e\",\n});\n\nconst results = await collection.search({\n    term: \"The quick brown fox\",\n    mode: \"auto\", // can be \"fulltext\", \"vector\", \"hybrid\", or \"auto\"\n});\n```\n\nYou can also perform **Answer Sessions** as you'd do on **Perplexity** or\n**SearchGPT**, but on your own data!\n\n```js\nimport { CollectionManager } from \"@orama/core\";\n\nconst collection = new CollectionManager({\n    url: \"http://localhost:8080\",\n    collectionID: \"\u003cCOLLECTION_ID\u003e\",\n    readAPIKey: \"\u003cread_api_key\u003e\",\n});\n\nconst answerSession = collection.createAnswerSession({\n    initialMessages: [\n        {\n            role: \"user\",\n            content: \"How do I install OramaCore?\",\n        },\n        {\n            role: \"assistant\",\n            content:\n                \"You can install OramaCore by pulling the oramasearch/oramacore:latest Docker image\",\n        },\n    ],\n    events: {\n        onStateChange(state) {\n            console.log(\"State changed:\", state);\n        },\n    },\n});\n```\n\nRead more on the [official documentation](https://docs.oramacore.com/docs).\n\n## License\n\n[AGPLv3](/LICENSE.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foramasearch%2Foramacore","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foramasearch%2Foramacore","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foramasearch%2Foramacore/lists"}