[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z2WYBSKNXR0YGBJA5KBQ0":3,"skill-same:01M78Z2WYBSKNXR0YGBJA5KBQ0":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78Z2WYBSKNXR0YGBJA5KBQ0","rag-document-processing",null,"Guides LazyLLM RAG, document ingestion, readers, transforms, retrievers, rerankers, stores, BM25, and parser-service workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rag-document-processing\ndescription: \"Guides LazyLLM RAG, document ingestion, readers, transforms,\n  retrievers, rerankers, stores, BM25, and parser-service workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LazyLLM RAG and Document Processing\n\nUse this sub-skill for LazyLLM tasks involving `Document`, `DocNode`, document readers, transforms, node groups, retrievers, rerankers, BM25, stores\u002Findexes, document service metadata, parser service, Milvus\u002FOpenSearch, or RAG examples.\n\n## Start here when\n\n- The task mentions `lazyllm.tools.rag`, `Document`, `Retriever`, `Reranker`, `DocNode`, node groups, chunking, embedding, reranking, or BM25.\n- An import error says to run `lazyllm install rag`.\n- The user wants a local RAG app, parser-service architecture, URL\u002Ffile retriever, map store, Milvus\u002FOpenSearch index, or RAG with online\u002Flocal model modules.\n- You need to separate local text retrieval from optional embedding\u002Fvector database\u002Fmodel backends.\n\n## Files to read\n\n- [rag-workflows.md](references\u002Frag-workflows.md) for local RAG recipes, object relationships, and backend escalation.\n- [data-and-service-formats.md](references\u002Fdata-and-service-formats.md) for document\u002Fnode\u002Fservice request shapes and parser-service boundaries.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for missing dependencies, parser service, vector DB, and retrieval issues.\n- [scripts\u002Frag_bm25_smoke.py](scripts\u002Frag_bm25_smoke.py) for a no-network BM25 retrieval check.\n\n## Safe RAG workflow\n\n1. **Install\u002Fcheck the RAG extra** when importing RAG objects:\n   ```bash\n   lazyllm install rag\n   python ..\u002F..\u002Fscripts\u002Fcheck_lazyllm_env.py --require-rag\n   ```\n2. **Start local and text-only.** Use `DocNode` and BM25 or local readers before adding embeddings, rerankers, vector DBs, or model modules.\n3. **Decide ownership of model nodes.** Model modules used for embeddings\u002Freranking\u002Fchat belong to [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md) for backend checks.\n4. **Decide service boundaries.** Parser service, document service, Milvus\u002FOpenSearch\u002FRedis, object storage, and external URLs require service credentials or local fixtures.\n5. **Run local smoke.**\n   ```bash\n   python scripts\u002Frag_bm25_smoke.py\n   ```\n\n## Key public surfaces\n\n- `Document(*args, **kw)` is the main RAG container and index manager.\n- `Retriever(doc, group_name, similarity=None, similarity_cut_off=-inf, index='default', topk=6, embed_keys=None, target=None, output_format=None, join=False, weight=None, priority=None, **kwargs)` pulls contexts from a document\u002Findex.\n- `Reranker(name='ModuleReranker', *args, **kwargs)` reranks retrieved contexts and may depend on a model\u002Fbackend.\n- `DocNode` represents text chunks with metadata and relationships.\n- BM25 supports local English\u002FChinese retrieval with no embedding server.\n\n## Backend posture\n\n- **Required for local guidance:** base LazyLLM plus `rag` extra.\n- **Safe CPU candidates:** BM25, document\u002Fnode transforms, reader utilities, retriever logic, local doc-service manager with SQLite\u002Fmocked parser client.\n- **Optional external services:** Milvus, OpenSearch\u002FElasticsearch, Redis\u002FRedisVL, parser service workers, object storage, remote URLs.\n- **Optional model\u002FGPU:** embedding models, rerankers, local LLM answer generation, multimodal OCR\u002Faudio ingestion.\n\n## Handoff checklist\n\nWhen you complete a RAG task, report:\n\n- document source type and data format,\n- node\u002Fchunking\u002Fgrouping plan,\n- retrieval method and index\u002Fstore backend,\n- model\u002Fembedding\u002Freranker backend status,\n- local smoke command or reason it is optional\u002Fskipped,\n- clear separation between local artifacts and external services.\n","# LazyLLM RAG and Document Processing\n\nUse this sub-skill for LazyLLM tasks involving `Document`, `DocNode`, document readers, transforms, node groups, retrievers, rerankers, BM25, stores\u002Findexes, document service metadata, parser service, Milvus\u002FOpenSearch, or RAG examples.\n\n## Start here when\n\n- The task mentions `lazyllm.tools.rag`, `Document`, `Retriever`, `Reranker`, `DocNode`, node groups, chunking, embedding, reranking, or BM25.\n- An import error says to run `lazyllm install rag`.\n- The user wants a local RAG app, parser-service architecture, URL\u002Ffile retriever, map store, Milvus\u002FOpenSearch index, or RAG with online\u002Flocal model modules.\n- You need to separate local text retrieval from optional embedding\u002Fvector database\u002Fmodel backends.\n\n## Files to read\n\n- [rag-workflows.md](references\u002Frag-workflows.md) for local RAG recipes, object relationships, and backend escalation.\n- [data-and-service-formats.md](references\u002Fdata-and-service-formats.md) for document\u002Fnode\u002Fservice request shapes and parser-service boundaries.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for missing dependencies, parser service, vector DB, and retrieval issues.\n- [scripts\u002Frag_bm25_smoke.py](scripts\u002Frag_bm25_smoke.py) for a no-network BM25 retrieval check.\n\n## Safe RAG workflow\n\n1. **Install\u002Fcheck the RAG extra** when importing RAG objects:\n   ```bash\n   lazyllm install rag\n   python ..\u002F..\u002Fscripts\u002Fcheck_lazyllm_env.py --require-rag\n   ```\n2. **Start local and text-only.** Use `DocNode` and BM25 or local readers before adding embeddings, rerankers, vector DBs, or model modules.\n3. **Decide ownership of model nodes.** Model modules used for embeddings\u002Freranking\u002Fchat belong to [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md) for backend checks.\n4. **Decide service boundaries.** Parser service, document service, Milvus\u002FOpenSearch\u002FRedis, object storage, and external URLs require service credentials or local fixtures.\n5. **Run local smoke.**\n   ```bash\n   python scripts\u002Frag_bm25_smoke.py\n   ```\n\n## Key public surfaces\n\n- `Document(*args, **kw)` is the main RAG container and index manager.\n- `Retriever(doc, group_name, similarity=None, similarity_cut_off=-inf, index='default', topk=6, embed_keys=None, target=None, output_format=None, join=False, weight=None, priority=None, **kwargs)` pulls contexts from a document\u002Findex.\n- `Reranker(name='ModuleReranker', *args, **kwargs)` reranks retrieved contexts and may depend on a model\u002Fbackend.\n- `DocNode` represents text chunks with metadata and relationships.\n- BM25 supports local English\u002FChinese retrieval with no embedding server.\n\n## Backend posture\n\n- **Required for local guidance:** base LazyLLM plus `rag` extra.\n- **Safe CPU candidates:** BM25, document\u002Fnode transforms, reader utilities, retriever logic, local doc-service manager with SQLite\u002Fmocked parser client.\n- **Optional external services:** Milvus, OpenSearch\u002FElasticsearch, Redis\u002FRedisVL, parser service workers, object storage, remote URLs.\n- **Optional model\u002FGPU:** embedding models, rerankers, local LLM answer generation, multimodal OCR\u002Faudio ingestion.\n\n## Handoff checklist\n\nWhen you complete a RAG task, report:\n\n- document source type and data format,\n- node\u002Fchunking\u002Fgrouping plan,\n- retrieval method and index\u002Fstore backend,\n- model\u002Fembedding\u002Freranker backend status,\n- local smoke command or reason it is optional\u002Fskipped,\n- clear separation between local artifacts and external services.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill rag-document-processing",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rag-document-processing",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rag-document-processing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdata-and-service-formats.md","REFERENCE","参考文档",2613,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing\u002Freferences\u002Fdata-and-service-formats.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frag-workflows.md",3215,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing\u002Freferences\u002Frag-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2329,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Frag_bm25_smoke.py","SCRIPT","脚本",1878,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Frag-document-processing\u002Fscripts\u002Frag_bm25_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]