{"id":51192346,"url":"https://github.com/tiny-systems/embedding-module","last_synced_at":"2026-06-27T16:30:50.620Z","repository":{"id":358851096,"uuid":"1243347293","full_name":"tiny-systems/embedding-module","owner":"tiny-systems","description":"In-cluster text embeddings for Tiny Systems flows. Ships TEI as a curated bundle.","archived":false,"fork":false,"pushed_at":"2026-06-03T20:25:51.000Z","size":74,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-03T22:11:27.746Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tiny-systems.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2026-05-19T09:00:35.000Z","updated_at":"2026-06-03T20:25:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/tiny-systems/embedding-module","commit_stats":null,"previous_names":["tiny-systems/embedding-module-v0"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/tiny-systems/embedding-module","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tiny-systems%2Fembedding-module","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tiny-systems%2Fembedding-module/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tiny-systems%2Fembedding-module/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tiny-systems%2Fembedding-module/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tiny-systems","download_url":"https://codeload.github.com/tiny-systems/embedding-module/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tiny-systems%2Fembedding-module/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34860892,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-27T02:00:06.362Z","response_time":126,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2026-06-27T16:30:47.810Z","updated_at":"2026-06-27T16:30:50.516Z","avatar_url":"https://github.com/tiny-systems.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Tiny Systems Embedding Module\n\nIn-cluster text embeddings for Tiny Systems flows. Wraps HuggingFace text-embeddings-inference (TEI) and ships it as a curated bundle, so installing this module also provisions the TEI service in the same namespace — no external API, no separate helm install.\n\n## Components\n\n### embed_text\n\nTakes a string, returns its dense vector embedding.\n\n- **Input:** `{ context: any, text: string }`\n- **Output:** `{ context: any, embedding: float32[], dims: int }`\n- **Error:** `{ context: any, error: string }` when enabled\n\nThe component reads `TEI_URL` from env. The platform's install flow wires this automatically when the TEI bundle is enabled. To point at an external embedding endpoint, set `baseURL` in the node settings instead.\n\n## Install\n\nThe module declares the `tei` bundle with `DefaultEnabled: true`, so a plain `helm upgrade --install` of the operator chart pulls TEI in as a subchart and starts a Deployment + Service alongside the module.\n\nDefault model: `BAAI/bge-small-en-v1.5` — 384-dim, CPU-friendly, decent quality for English RAG. Override via `--set bundles.tei.image.tag=cpu-1.5 --set bundles.tei.modelId=intfloat/multilingual-e5-large` if you need a different model.\n\nThe TEI Service lands at `\u003crelease-name\u003e-tei:80` inside the namespace; the install flow sets `TEI_URL` on the module pod's env to match.\n\n## Pairs with\n\n- `database-module` vector_search / vector_upsert components (also via a bundle: `pgvector`) — embed + store + retrieve as a three-component RAG slice.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftiny-systems%2Fembedding-module","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftiny-systems%2Fembedding-module","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftiny-systems%2Fembedding-module/lists"}