{"id":44289926,"url":"https://github.com/r0mdau/refind","last_synced_at":"2026-02-10T23:32:59.271Z","repository":{"id":168402311,"uuid":"644108057","full_name":"r0mdau/refind","owner":"r0mdau","description":"Experimenting Weaviate vector database with OpenAI vectorizer module and generative search","archived":false,"fork":false,"pushed_at":"2024-03-30T20:52:03.000Z","size":126,"stargazers_count":8,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-06-21T17:03:02.422Z","etag":null,"topics":["generative-ai","generative-search","golang","mlops","nearest-neighbor-search","vector-database","vector-search","vectorizer"],"latest_commit_sha":null,"homepage":"","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/r0mdau.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2023-05-22T20:44:59.000Z","updated_at":"2024-01-27T22:01:33.000Z","dependencies_parsed_at":"2024-03-30T21:34:11.386Z","dependency_job_id":"ed60c7cb-88ee-40f4-ba6e-b0ae10079438","html_url":"https://github.com/r0mdau/refind","commit_stats":null,"previous_names":["r0mdau/refind"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/r0mdau/refind","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r0mdau%2Frefind","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r0mdau%2Frefind/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r0mdau%2Frefind/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r0mdau%2Frefind/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/r0mdau","download_url":"https://codeload.github.com/r0mdau/refind/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r0mdau%2Frefind/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29321390,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-10T20:44:44.282Z","status":"ssl_error","status_checked_at":"2026-02-10T20:44:43.393Z","response_time":65,"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":["generative-ai","generative-search","golang","mlops","nearest-neighbor-search","vector-database","vector-search","vectorizer"],"created_at":"2026-02-10T23:32:58.145Z","updated_at":"2026-02-10T23:32:59.257Z","avatar_url":"https://github.com/r0mdau.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# refind\n\nRefind is a project to store my personnal documents in a [Weaviate] vector\n database and use [OpenAI] vectorizer module and generative search.\n\nHere is a shell recording with [asciinema](https://asciinema.org/) showing the\ndifferent answers with the same input question from :\n\n1. the current ChatGPt version (using\n[sgpt](https://github.com/TheR1D/shell_gpt) cli)\n1. the generative search with Weaviate containing a sample document from the\n[Enteprise Roadmap to SRE](https://sre.google/resources/practices-and-processes/enterprise-roadmap-to-sre/)\nbook\n\n![shell](demo.svg)\n\n## Getting started\n\nCreate and provide your OpenAI API key :\n\n```bash\nexport OPENAI_APIKEY=\"...\"\n```\n\nPut full-text documents with less than 4097 [tokens](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them).\nIf your prompt is 4000 tokens, your completion can be 97 tokens at most.\n\nLet's use it :\n\n```bash\n# start the weaviate database\ndocker-compose up -d\n\n# verify it is up and running\ncurl http://localhost:8080/v1/meta | jq .\ndocker-compose logs\n\n# import data, DO IT ONCE\ngo run main.go import\n\n# query data related to software\ngo run main.go query | jq .\n\n# when done, gracefully shutdown\ndocker-compose down\n```\n\nIn this example, Weaviate is returning software-related entries.\n\nWeaviate operations :\n\n```bash\n# get the schema\ncurl -s http://localhost:8080/v1/schema | jq .\n\n# get objects\ncurl -s http://localhost:8080/v1/objects | jq .\n\n# get one class from the schema\ncurl -s http://localhost:8080/v1/schema/Chatbot | jq .\n\n# delete a class\ncurl -s -XDELETE http://localhost:8080/v1/schema/Chatbot | jq .\n```\n\n## Goal\n\n[The ChatGPT Retrieval plugin](https://weaviate.io/blog/weaviate-retrieval-plugin).\n\n[Weaviate]: https://weaviate.io\n[OpenAI]: https://openai.com/\n\n### TODO\n\n1. automatically add more metadata in weaviate when ingesting documents\n1. automatically split documents bigger than the OpenAI token limit\n1. add query string as a flag when running the `query` command\n1. unit tests, let Copilot write them \\o/\n\n## Trying langchain\n\n[README.md](langchain/README.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr0mdau%2Frefind","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fr0mdau%2Frefind","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr0mdau%2Frefind/lists"}