[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78V18850VEGXD4MMRNKAVE2":3,"skill-same:01M78V18850VEGXD4MMRNKAVE2":74},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78V18850VEGXD4MMRNKAVE2","index-updates-and-serving",null,"Mutate existing ColBERT indexes with IndexUpdater, persist index changes safely, coalesce updated artifacts, and expose a lightweight search API without import-time side effects.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: index-updates-and-serving\ndescription: \"Mutate existing ColBERT indexes with IndexUpdater, persist index\n  changes safely, coalesce updated artifacts, and expose a lightweight search\n  API without import-time side effects.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# ColBERT Index Updates and Serving\n\nUse this sub-skill when the task is to add passages to an existing ColBERT index, remove passage IDs, decide whether changes survive Searcher reloads, persist IndexUpdater changes to disk, coalesce multi-chunk index artifacts, or serve an existing index through a small JSON search API.\n\n## Route the task\n\n- For verified constructor signatures, method semantics, reload behavior, return shapes, and package facts, read `references\u002Fapi-reference.md`.\n- For safe add\u002Fremove\u002Fpersist workflows, disk mutation precautions, coalescing, backup strategy, and reload validation, read `references\u002Findex-update-workflows.md`.\n- For Flask-style serving, explicit CLI\u002Fenv configuration, `\u002Fapi\u002Fsearch` response shape, lazy Searcher creation, and `k \u003C= 100` behavior, read `references\u002Fserving-api.md`.\n- For install\u002Fimport, optional dependency, backend, pid, metadata, chunk, mmap, and server configuration failures, read `references\u002Ftroubleshooting.md`.\n- For an editable add\u002Fremove\u002Fpersist command template with no ColBERT import at `--help` time, adapt `scripts\u002Findex_update_template.py`.\n- For a safe lightweight JSON search service adapted from ColBERT's public server pattern with lazy Searcher creation, adapt `scripts\u002Fserve_search_api.py`.\n\n## Core boundaries\n\n- Cover `IndexUpdater(config, searcher, checkpoint=None)`, `Searcher(...)` reload behavior, index artifact mutation, `persist_to_disk()`, coalesced index directories, and lightweight HTTP serving.\n- Keep fresh index creation, baseline search, `search_all`, ranking save, and general search tuning in `..\u002Findexing-and-search\u002F`.\n- Keep TSV\u002Fqrels\u002Franking evaluation, query\u002Fcollection validation details, and metrics workflows in `..\u002Fdata-and-evaluation\u002F`.\n- Keep checkpoint internals, tokenizer\u002Fmodel compatibility, and training\u002Fdistillation in `..\u002Fmodeling-and-tokenization\u002F` and `..\u002Ftraining-and-distillation\u002F`.\n\n## Fast starting point\n\n1. Open an existing index with `Searcher(index=..., checkpoint=..., collection=..., config=..., index_root=...)` and create `IndexUpdater(config, searcher, checkpoint=...)` when adding passages.\n2. Use `remove([pid, ...])` for in-memory removal; use `add([passage, ...])` for in-memory append; call `persist_to_disk()` only after backing up or writing to a disposable copy of the index.\n3. Reload a fresh `Searcher` after `persist_to_disk()` to prove changes survived disk mutation; without persistence, changes affect only the current `Searcher` instance.\n4. Serve search through `scripts\u002Fserve_search_api.py` with explicit `--index-name` and either `--index-root` or a compatible ColBERT config; do not create a `Searcher` at module import time.\n\n## Verified package facts\n\n- Distribution: `colbert-ai` 0.2.22; import package: `colbert`.\n- Verified imports include `colbert`, `colbert.infra`, `colbert.data`, `colbert.modeling.checkpoint`, `utility`, and `baleen`.\n- CPU import inspection works and CPU search can work, but practical indexing, training, and passage encoding for updates usually require CUDA\u002FGPU-capable PyTorch.\n- Important signatures: `Indexer(checkpoint, config=None, verbose=3)`, `Searcher(index, checkpoint=None, collection=None, config=None, index_root=None, verbose=3)`, `IndexUpdater(config, searcher, checkpoint=None)`, `Collection(path=None, data=None)`, `Queries(path=None, data=None)`, and `Ranking(path=None, data=None, metrics=None, provenance=None)`.\n","# ColBERT Index Updates and Serving\n\nUse this sub-skill when the task is to add passages to an existing ColBERT index, remove passage IDs, decide whether changes survive Searcher reloads, persist IndexUpdater changes to disk, coalesce multi-chunk index artifacts, or serve an existing index through a small JSON search API.\n\n## Route the task\n\n- For verified constructor signatures, method semantics, reload behavior, return shapes, and package facts, read `references\u002Fapi-reference.md`.\n- For safe add\u002Fremove\u002Fpersist workflows, disk mutation precautions, coalescing, backup strategy, and reload validation, read `references\u002Findex-update-workflows.md`.\n- For Flask-style serving, explicit CLI\u002Fenv configuration, `\u002Fapi\u002Fsearch` response shape, lazy Searcher creation, and `k \u003C= 100` behavior, read `references\u002Fserving-api.md`.\n- For install\u002Fimport, optional dependency, backend, pid, metadata, chunk, mmap, and server configuration failures, read `references\u002Ftroubleshooting.md`.\n- For an editable add\u002Fremove\u002Fpersist command template with no ColBERT import at `--help` time, adapt `scripts\u002Findex_update_template.py`.\n- For a safe lightweight JSON search service adapted from ColBERT's public server pattern with lazy Searcher creation, adapt `scripts\u002Fserve_search_api.py`.\n\n## Core boundaries\n\n- Cover `IndexUpdater(config, searcher, checkpoint=None)`, `Searcher(...)` reload behavior, index artifact mutation, `persist_to_disk()`, coalesced index directories, and lightweight HTTP serving.\n- Keep fresh index creation, baseline search, `search_all`, ranking save, and general search tuning in `..\u002Findexing-and-search\u002F`.\n- Keep TSV\u002Fqrels\u002Franking evaluation, query\u002Fcollection validation details, and metrics workflows in `..\u002Fdata-and-evaluation\u002F`.\n- Keep checkpoint internals, tokenizer\u002Fmodel compatibility, and training\u002Fdistillation in `..\u002Fmodeling-and-tokenization\u002F` and `..\u002Ftraining-and-distillation\u002F`.\n\n## Fast starting point\n\n1. Open an existing index with `Searcher(index=..., checkpoint=..., collection=..., config=..., index_root=...)` and create `IndexUpdater(config, searcher, checkpoint=...)` when adding passages.\n2. Use `remove([pid, ...])` for in-memory removal; use `add([passage, ...])` for in-memory append; call `persist_to_disk()` only after backing up or writing to a disposable copy of the index.\n3. Reload a fresh `Searcher` after `persist_to_disk()` to prove changes survived disk mutation; without persistence, changes affect only the current `Searcher` instance.\n4. Serve search through `scripts\u002Fserve_search_api.py` with explicit `--index-name` and either `--index-root` or a compatible ColBERT config; do not create a `Searcher` at module import time.\n\n## Verified package facts\n\n- Distribution: `colbert-ai` 0.2.22; import package: `colbert`.\n- Verified imports include `colbert`, `colbert.infra`, `colbert.data`, `colbert.modeling.checkpoint`, `utility`, and `baleen`.\n- CPU import inspection works and CPU search can work, but practical indexing, training, and passage encoding for updates usually require CUDA\u002FGPU-capable PyTorch.\n- Important signatures: `Indexer(checkpoint, config=None, verbose=3)`, `Searcher(index, checkpoint=None, collection=None, config=None, index_root=None, verbose=3)`, `IndexUpdater(config, searcher, checkpoint=None)`, `Collection(path=None, data=None)`, `Queries(path=None, data=None)`, and `Ranking(path=None, data=None, metrics=None, provenance=None)`.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill index-updates-and-serving",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill index-updates-and-serving",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill index-updates-and-serving","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",3727,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Findex-update-workflows.md",5079,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002Freferences\u002Findex-update-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fserving-api.md",3449,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002Freferences\u002Fserving-api.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",4626,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Findex_update_template.py","SCRIPT","脚本",7514,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002Fscripts\u002Findex_update_template.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fserve_search_api.py",7051,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcolbert\u002Fsub-skills\u002Findex-updates-and-serving\u002Fscripts\u002Fserve_search_api.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]