[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796689RAF90J2K6Y9SM0CSD":3,"skill-same:01M796689RAF90J2K6Y9SM0CSD":71},{"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},"01M796689RAF90J2K6Y9SM0CSD","text2vec",null,"Operate text2vec for text embeddings, similarity search, model fine-tuning, evaluation, and serving without reopening the source repository.","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\u002Ftext2vec\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: text2vec\ndescription: \"Operate text2vec for text embeddings, similarity search, model\n  fine-tuning, evaluation, and serving without reopening the source repository.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# text2vec\n\nUse this repo skill when a task involves the `text2vec` Python package, Chinese or multilingual sentence embeddings, text similarity, BM25 fallback retrieval, CoSENT\u002FSentence-BERT\u002FBGE fine-tuning, or text2vec service templates.\n\n## First checks\n\n1. Install a compatible PyTorch build before expecting public model APIs to import.\n2. Install `text2vec` and run a no-download import check:\n\n```bash\npython -c \"from text2vec import SentenceModel, Similarity, BM25; print('text2vec ok')\"\ntext2vec -h\n```\n\n3. For a safer environment probe, run the bundled helper from this skill:\n\n```bash\npython scripts\u002Fcheck_text2vec_env.py\n```\n\nRead [references\u002Finstallation.md](references\u002Finstallation.md) for optional dependency and backend decisions. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install, model download, CUDA, data, CLI, and service failures.\n\n## Route by task\n\n| User task | Read |\n|---|---|\n| Generate sentence embeddings, use `SentenceModel`, run the `text2vec` CLI, choose `EncoderType`, preserve batch output rows, use Word2Vec, or understand NGram caveats | [sub-skills\u002Fembeddings\u002FSKILL.md](sub-skills\u002Fembeddings\u002FSKILL.md) |\n| Score sentence pairs, use `Similarity`, call `cos_sim` \u002F `semantic_search`, run dense top-k retrieval, or use BM25 as a no-network lexical fallback | [sub-skills\u002Fsimilarity-search\u002FSKILL.md](sub-skills\u002Fsimilarity-search\u002FSKILL.md) |\n| Validate fine-tuning data, construct CoSENT\u002FSentence-BERT\u002FBERT-match\u002FBGE training commands, understand `train_model` parameters, or handle multi-GPU\u002Fbf16 training boundaries | [sub-skills\u002Ftraining-finetuning\u002FSKILL.md](sub-skills\u002Ftraining-finetuning\u002FSKILL.md) |\n| Choose among released models, interpret Spearman\u002FQPS tables, summarize local score files, or plan MTEB\u002FC-MTEB-style evaluation without running large downloads by default | [sub-skills\u002Fevaluation-benchmarks\u002FSKILL.md](sub-skills\u002Fevaluation-benchmarks\u002FSKILL.md) |\n| Build a FastAPI endpoint, compare FastAPI\u002FJina\u002FGradio service patterns, or avoid blocking forever-server verification | [sub-skills\u002Fserving-deployment\u002FSKILL.md](sub-skills\u002Fserving-deployment\u002FSKILL.md) |\n\n## Package surface at a glance\n\n- Main import: `import text2vec`.\n- Important inference APIs: `SentenceModel`, `SBert`, `EncoderType`, `Word2Vec`, `BM25`, `Similarity`, `SimilarityType`, `EmbeddingType`, `cos_sim`, `semantic_search`.\n- Training APIs: `CosentModel`, `SentenceBertModel`, `BertMatchModel`, `BgeModel`, plus text-matching and BGE dataset loaders.\n- CLI entry point: `text2vec`, with required `--input_file` and optional `--output_file`, `--model_type`, `--model_name`, `--encoder_type`, `--batch_size`, `--max_seq_length`, `--chunk_size`, `--device`, `--show_progress_bar`, `--normalize_embeddings`, and `--multi_gpu`.\n- Default neural model names usually require Hugging Face access unless cached. Prefer a local HF-compatible model directory for offline smoke tests.\n- Word2Vec requires `gensim` and either a local vector file or the built-in Tencent lightweight vector download.\n\n## Bundled root files\n\n- [references\u002Finstallation.md](references\u002Finstallation.md): public install variants, required `torch` note, optional dependencies, backend choices, and environment checks.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): cross-skill failure modes and recovery steps.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md): source snapshot used to create this skill; read before refresh decisions.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json): structured router metadata for managed repo-skill import.\n- [scripts\u002Fcheck_text2vec_env.py](scripts\u002Fcheck_text2vec_env.py): no-download diagnostic helper for imports, optional deps, torch backend, BM25, `cos_sim`, and `semantic_search`.\n\n## Operating rules\n\n- Do not run default model downloads, full training, benchmarks, JinaHub fetches, Gradio launches, or long-lived servers unless the user explicitly approves network\u002Fruntime side effects.\n- Do not use synthetic CPU smoke checks as proof of CUDA, bf16, multi-GPU, or production-scale training coverage.\n- Prefer bundled validators and helpers before expensive commands: data validation before training, no-network BM25 before dense retrieval when embeddings are absent, and local model directories before default downloads.\n- For stale-source decisions, compare the current checkout against [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) and refresh if APIs, docs, examples, tests, or package metadata changed.\n","# text2vec\n\nUse this repo skill when a task involves the `text2vec` Python package, Chinese or multilingual sentence embeddings, text similarity, BM25 fallback retrieval, CoSENT\u002FSentence-BERT\u002FBGE fine-tuning, or text2vec service templates.\n\n## First checks\n\n1. Install a compatible PyTorch build before expecting public model APIs to import.\n2. Install `text2vec` and run a no-download import check:\n\n```bash\npython -c \"from text2vec import SentenceModel, Similarity, BM25; print('text2vec ok')\"\ntext2vec -h\n```\n\n3. For a safer environment probe, run the bundled helper from this skill:\n\n```bash\npython scripts\u002Fcheck_text2vec_env.py\n```\n\nRead [references\u002Finstallation.md](references\u002Finstallation.md) for optional dependency and backend decisions. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install, model download, CUDA, data, CLI, and service failures.\n\n## Route by task\n\n| User task | Read |\n|---|---|\n| Generate sentence embeddings, use `SentenceModel`, run the `text2vec` CLI, choose `EncoderType`, preserve batch output rows, use Word2Vec, or understand NGram caveats | [sub-skills\u002Fembeddings\u002FSKILL.md](sub-skills\u002Fembeddings\u002FSKILL.md) |\n| Score sentence pairs, use `Similarity`, call `cos_sim` \u002F `semantic_search`, run dense top-k retrieval, or use BM25 as a no-network lexical fallback | [sub-skills\u002Fsimilarity-search\u002FSKILL.md](sub-skills\u002Fsimilarity-search\u002FSKILL.md) |\n| Validate fine-tuning data, construct CoSENT\u002FSentence-BERT\u002FBERT-match\u002FBGE training commands, understand `train_model` parameters, or handle multi-GPU\u002Fbf16 training boundaries | [sub-skills\u002Ftraining-finetuning\u002FSKILL.md](sub-skills\u002Ftraining-finetuning\u002FSKILL.md) |\n| Choose among released models, interpret Spearman\u002FQPS tables, summarize local score files, or plan MTEB\u002FC-MTEB-style evaluation without running large downloads by default | [sub-skills\u002Fevaluation-benchmarks\u002FSKILL.md](sub-skills\u002Fevaluation-benchmarks\u002FSKILL.md) |\n| Build a FastAPI endpoint, compare FastAPI\u002FJina\u002FGradio service patterns, or avoid blocking forever-server verification | [sub-skills\u002Fserving-deployment\u002FSKILL.md](sub-skills\u002Fserving-deployment\u002FSKILL.md) |\n\n## Package surface at a glance\n\n- Main import: `import text2vec`.\n- Important inference APIs: `SentenceModel`, `SBert`, `EncoderType`, `Word2Vec`, `BM25`, `Similarity`, `SimilarityType`, `EmbeddingType`, `cos_sim`, `semantic_search`.\n- Training APIs: `CosentModel`, `SentenceBertModel`, `BertMatchModel`, `BgeModel`, plus text-matching and BGE dataset loaders.\n- CLI entry point: `text2vec`, with required `--input_file` and optional `--output_file`, `--model_type`, `--model_name`, `--encoder_type`, `--batch_size`, `--max_seq_length`, `--chunk_size`, `--device`, `--show_progress_bar`, `--normalize_embeddings`, and `--multi_gpu`.\n- Default neural model names usually require Hugging Face access unless cached. Prefer a local HF-compatible model directory for offline smoke tests.\n- Word2Vec requires `gensim` and either a local vector file or the built-in Tencent lightweight vector download.\n\n## Bundled root files\n\n- [references\u002Finstallation.md](references\u002Finstallation.md): public install variants, required `torch` note, optional dependencies, backend choices, and environment checks.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): cross-skill failure modes and recovery steps.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md): source snapshot used to create this skill; read before refresh decisions.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json): structured router metadata for managed repo-skill import.\n- [scripts\u002Fcheck_text2vec_env.py](scripts\u002Fcheck_text2vec_env.py): no-download diagnostic helper for imports, optional deps, torch backend, BM25, `cos_sim`, and `semantic_search`.\n\n## Operating rules\n\n- Do not run default model downloads, full training, benchmarks, JinaHub fetches, Gradio launches, or long-lived servers unless the user explicitly approves network\u002Fruntime side effects.\n- Do not use synthetic CPU smoke checks as proof of CUDA, bf16, multi-GPU, or production-scale training coverage.\n- Prefer bundled validators and helpers before expensive commands: data validation before training, no-network BM25 before dense retrieval when embeddings are absent, and local model directories before default downloads.\n- For stale-source decisions, compare the current checkout against [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) and refresh if APIs, docs, examples, tests, or package metadata changed.\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\u002Ftext2vec",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 text2vec",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill text2vec",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill text2vec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext2vec\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finstallation.md","REFERENCE","参考文档",3800,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext2vec\u002Freferences\u002Finstallation.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",1938,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext2vec\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",422,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext2vec\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4325,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext2vec\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_text2vec_env.py","SCRIPT","脚本",5331,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext2vec\u002Fscripts\u002Fcheck_text2vec_env.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]