{"id":51193821,"url":"https://github.com/bokuweb/ellisii-toolkit","last_synced_at":"2026-06-27T18:02:51.068Z","repository":{"id":358010639,"uuid":"1239495312","full_name":"bokuweb/ellisii-toolkit","owner":"bokuweb","description":null,"archived":false,"fork":false,"pushed_at":"2026-05-30T07:59:04.000Z","size":1289,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-30T08:15:38.155Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Rust","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/bokuweb.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":"2026-05-15T06:34:40.000Z","updated_at":"2026-05-30T07:23:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/bokuweb/ellisii-toolkit","commit_stats":null,"previous_names":["bokuweb/ellisii-toolkit"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/bokuweb/ellisii-toolkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bokuweb%2Fellisii-toolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bokuweb%2Fellisii-toolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bokuweb%2Fellisii-toolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bokuweb%2Fellisii-toolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bokuweb","download_url":"https://codeload.github.com/bokuweb/ellisii-toolkit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bokuweb%2Fellisii-toolkit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34862627,"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":"2026-06-27T18:02:50.428Z","updated_at":"2026-06-27T18:02:51.062Z","avatar_url":"https://github.com/bokuweb.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ellisii-toolkit\n\n[![CI](https://github.com/bokuweb/ellisii-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/bokuweb/ellisii-toolkit/actions/workflows/ci.yml)\n[![License: PolyForm-NC-1.0.0](https://img.shields.io/badge/license-PolyForm--NC--1.0.0-blue.svg)](./LICENSE)\n\nReusable Rust crates for building local-first RAG / NotebookLM-style\napplications. Extracted from [ellisii](https://github.com/bokuweb/ellisii)\nso the lower-level building blocks can be consumed from other projects\nwithout bringing in the Tauri app or the notebook domain layer.\n\n## Status\n\nPre-1.0. APIs may change. Not published to crates.io — consume via\n`git` dependency:\n\n```toml\n[dependencies]\nellisii-rag = { git = \"https://github.com/bokuweb/ellisii-toolkit\", rev = \"\u003ccommit\u003e\" }\n```\n\n## What's inside\n\n- **Parsers** — PDF / DOCX / XLSX / PPTX / Markdown / text / audio\n  (`parsers`, `parser-*`, `parsers-core`)\n- **OCR** — wrapper around `ndlocr-lite-rs`\n- **Chunking** (`chunker`)\n- **Embedders** — trait + Japanese static embedding implementation\n  (`embed-core`, `embed-static-jp`, `embed-dummy`)\n- **Vector stores** — trait + in-memory and SQLite (`sqlite-vec` + FTS5)\n  backends (`store-core`, `store-memory`, `store-sqlite`)\n- **LLM backends** — trait + stub and `llama.cpp` implementations\n  (`llm-core`, `llm-stub`, `llm-llamacpp`, `llm-prompt`)\n- **RAG pipeline** — retrieval, reranking, prompting, streaming, and\n  recall / answer evaluation harnesses (`rag`, `rag-answer-eval`,\n  `rag-eval-cli`)\n- **Japanese tokenizers** (`jp-tokenizer-*`)\n- **Provence reranker** (`provence-*`)\n- **Query rewriter** (`query-rewriter-*`)\n- **Ingest pipeline** — parse → chunk → embed → store orchestration\n  (`ingest`)\n- **SDK** — facade crate that re-exports the common surface (`sdk`)\n\n## License\n\n[PolyForm Noncommercial 1.0.0](./LICENSE). Free for personal, research,\neducational, and noncommercial use. Commercial use requires a separate\nlicense — contact the author.\n\nThird-party dependency licenses: see\n[`THIRD_PARTY_LICENSES.html`](./THIRD_PARTY_LICENSES.html) (regenerate\nwith `cargo about generate about.hbs --all-features`).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbokuweb%2Fellisii-toolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbokuweb%2Fellisii-toolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbokuweb%2Fellisii-toolkit/lists"}