[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73FAJD620BGAEMXEYK9K95V":3,"skill-same:01M73FAJD620BGAEMXEYK9K95V":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M73FAJD620BGAEMXEYK9K95V","qdrant",null,"Qdrant vector database — collections, upsert, search, filtering, payloads, sparse vectors, BM25","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fqdrant\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: qdrant\ndescription: Qdrant vector database — collections, upsert, search, filtering, payloads, sparse vectors, BM25\ntriggers:\n  - qdrant\n  - vector database qdrant\n  - qdrant collection\n  - qdrant search\n  - qdrant upsert\n  - sparse dense hybrid search\n  - qdrant filter\n  - qdrant payload\n  - qdrant python client\n  - vector store qdrant\ndo_not_use_for:\n  - relational queries — use PostgreSQL\u002FSQLite\n  - full-text only — use Elasticsearch\n  - generic key-value store — use Redis\nsee_also:\n  - ragas\n  - langfuse\n  - crawl4ai\n  - firecrawl\n---\n\n# Qdrant — Vector Database\n\n## Connect + Create Collection\n\n```python\nfrom qdrant_client import QdrantClient\nfrom qdrant_client.models import (\n    Distance, VectorParams, PointStruct,\n    Filter, FieldCondition, MatchValue, Range,\n    SparseVectorParams, SparseIndexParams,\n)\n\n# Local (in-memory for dev)\nclient = QdrantClient(\":memory:\")\n\n# Local persistent\nclient = QdrantClient(path=\".\u002Fqdrant_storage\")\n\n# Remote\nclient = QdrantClient(\n    url=\"http:\u002F\u002Flocalhost:6333\",\n    api_key=\"your-api-key\",          # for Qdrant Cloud\n    timeout=30,\n)\n\n# Create collection\nclient.create_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(\n        size=1536,                    # OpenAI ada-002 dim\n        distance=Distance.COSINE,     # COSINE | EUCLID | DOT\n    ),\n)\n\n# With multiple named vectors\nfrom qdrant_client.models import NamedVectorStruct\nclient.create_collection(\n    collection_name=\"multi_vec\",\n    vectors_config={\n        \"dense\": VectorParams(size=1536, distance=Distance.COSINE),\n        \"sparse\": SparseVectorParams(index=SparseIndexParams(on_disk=False)),\n    },\n)\n```\n\n## Upsert Points\n\n```python\nfrom qdrant_client.models import PointStruct\n\n# Single or batch upsert\nclient.upsert(\n    collection_name=\"documents\",\n    points=[\n        PointStruct(\n            id=1,                           # int or UUID string\n            vector=[0.1, 0.2, ...],         # 1536-dim float list\n            payload={\n                \"text\": \"Document content\",\n                \"source\": \"wiki\",\n                \"year\": 2024,\n                \"tags\": [\"ml\", \"nlp\"],\n            },\n        ),\n        PointStruct(id=2, vector=embed(\"Second doc\"), payload={\"text\": \"...\"}),\n    ],\n    wait=True,                              # wait for indexing\n)\n\n# Batch upsert from embeddings\ntexts = [\"doc1\", \"doc2\", \"doc3\"]\nembeddings = embed_batch(texts)            # returns List[List[float]]\npoints = [\n    PointStruct(id=i, vector=vec, payload={\"text\": t})\n    for i, (t, vec) in enumerate(zip(texts, embeddings))\n]\nclient.upsert(collection_name=\"documents\", points=points)\n```\n\n## Search\n\n```python\n# Basic similarity search\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=embed(\"machine learning\"),\n    limit=5,\n    with_payload=True,\n    score_threshold=0.7,                    # minimum score\n)\nfor r in results:\n    print(r.score, r.payload[\"text\"])\n\n# Filtered search\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=embed(\"neural networks\"),\n    query_filter=Filter(\n        must=[\n            FieldCondition(key=\"source\", match=MatchValue(value=\"wiki\")),\n            FieldCondition(key=\"year\", range=Range(gte=2022, lte=2024)),\n        ],\n        should=[\n            FieldCondition(key=\"tags\", match=MatchValue(value=\"ml\")),\n        ],\n    ),\n    limit=10,\n    with_payload=[\"text\", \"source\"],        # select payload fields\n)\n```\n\n## Hybrid Search (Dense + Sparse \u002F BM25)\n\n```python\nfrom qdrant_client.models import SparseVector, NamedVector, NamedSparseVector\n\n# Sparse vector (BM25-style from fastembed)\nfrom fastembed import SparseTextEmbedding\nsparse_model = SparseTextEmbedding(\"prithivida\u002FSplade_PP_en_v1\")\n\ndef get_sparse(text: str) -> SparseVector:\n    emb = list(sparse_model.embed([text]))[0]\n    return SparseVector(indices=emb.indices.tolist(), values=emb.values.tolist())\n\n# Hybrid search with RRF fusion\nfrom qdrant_client.models import Prefetch, FusionQuery, Fusion\n\nresults = client.query_points(\n    collection_name=\"multi_vec\",\n    prefetch=[\n        Prefetch(query=embed_dense(query), using=\"dense\", limit=20),\n        Prefetch(query=get_sparse(query), using=\"sparse\", limit=20),\n    ],\n    query=FusionQuery(fusion=Fusion.RRF),   # Reciprocal Rank Fusion\n    limit=5,\n    with_payload=True,\n)\n```\n\n## Payload Indexing\n\n```python\nfrom qdrant_client.models import PayloadSchemaType\n\n# Create index for faster filtered search\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"source\",\n    field_schema=PayloadSchemaType.KEYWORD,\n)\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"year\",\n    field_schema=PayloadSchemaType.INTEGER,\n)\n```\n\n## Manage Points\n\n```python\n# Get by ID\npoints = client.retrieve(\n    collection_name=\"documents\",\n    ids=[1, 2, 3],\n    with_payload=True,\n    with_vectors=False,\n)\n\n# Delete\nclient.delete(\n    collection_name=\"documents\",\n    points_selector=Filter(\n        must=[FieldCondition(key=\"source\", match=MatchValue(value=\"old\"))]\n    ),\n)\n\n# Update payload\nclient.set_payload(\n    collection_name=\"documents\",\n    payload={\"updated\": True},\n    points=[1, 2],\n)\n\n# Scroll (iterate all points)\noffset = None\nwhile True:\n    result, offset = client.scroll(\n        collection_name=\"documents\",\n        limit=100,\n        offset=offset,\n        with_payload=True,\n    )\n    if not result:\n        break\n    process_batch(result)\n```\n\n## Collections Management\n\n```python\n# List collections\ncolls = client.get_collections()\nnames = [c.name for c in colls.collections]\n\n# Collection info\ninfo = client.get_collection(\"documents\")\nprint(info.points_count, info.vectors_count)\n\n# Delete collection\nclient.delete_collection(\"documents\")\n\n# Recreate (idempotent)\nclient.recreate_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(size=1536, distance=Distance.COSINE),\n)\n```\n\n## Anti-Fake-Pass Checks\n\n- Vector dimension must match `VectorParams(size=...)` exactly — mismatches raise `Unprocessable`\n- `id` must be `int` or UUID string — nested objects raise validation error\n- `score_threshold` filters out points — if no results, lower threshold or check embeddings\n- `wait=True` on upsert ensures indexing before search — omit only for fire-and-forget ingestion\n- Sparse vectors need `SparseVectorParams` in collection config — can't add after creation without recreation\n- `query_points` (v1.7+) replaces legacy `search` API — check client version\n","# Qdrant — Vector Database\n\n## Connect + Create Collection\n\n```python\nfrom qdrant_client import QdrantClient\nfrom qdrant_client.models import (\n    Distance, VectorParams, PointStruct,\n    Filter, FieldCondition, MatchValue, Range,\n    SparseVectorParams, SparseIndexParams,\n)\n\n# Local (in-memory for dev)\nclient = QdrantClient(\":memory:\")\n\n# Local persistent\nclient = QdrantClient(path=\".\u002Fqdrant_storage\")\n\n# Remote\nclient = QdrantClient(\n    url=\"http:\u002F\u002Flocalhost:6333\",\n    api_key=\"your-api-key\",          # for Qdrant Cloud\n    timeout=30,\n)\n\n# Create collection\nclient.create_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(\n        size=1536,                    # OpenAI ada-002 dim\n        distance=Distance.COSINE,     # COSINE | EUCLID | DOT\n    ),\n)\n\n# With multiple named vectors\nfrom qdrant_client.models import NamedVectorStruct\nclient.create_collection(\n    collection_name=\"multi_vec\",\n    vectors_config={\n        \"dense\": VectorParams(size=1536, distance=Distance.COSINE),\n        \"sparse\": SparseVectorParams(index=SparseIndexParams(on_disk=False)),\n    },\n)\n```\n\n## Upsert Points\n\n```python\nfrom qdrant_client.models import PointStruct\n\n# Single or batch upsert\nclient.upsert(\n    collection_name=\"documents\",\n    points=[\n        PointStruct(\n            id=1,                           # int or UUID string\n            vector=[0.1, 0.2, ...],         # 1536-dim float list\n            payload={\n                \"text\": \"Document content\",\n                \"source\": \"wiki\",\n                \"year\": 2024,\n                \"tags\": [\"ml\", \"nlp\"],\n            },\n        ),\n        PointStruct(id=2, vector=embed(\"Second doc\"), payload={\"text\": \"...\"}),\n    ],\n    wait=True,                              # wait for indexing\n)\n\n# Batch upsert from embeddings\ntexts = [\"doc1\", \"doc2\", \"doc3\"]\nembeddings = embed_batch(texts)            # returns List[List[float]]\npoints = [\n    PointStruct(id=i, vector=vec, payload={\"text\": t})\n    for i, (t, vec) in enumerate(zip(texts, embeddings))\n]\nclient.upsert(collection_name=\"documents\", points=points)\n```\n\n## Search\n\n```python\n# Basic similarity search\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=embed(\"machine learning\"),\n    limit=5,\n    with_payload=True,\n    score_threshold=0.7,                    # minimum score\n)\nfor r in results:\n    print(r.score, r.payload[\"text\"])\n\n# Filtered search\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=embed(\"neural networks\"),\n    query_filter=Filter(\n        must=[\n            FieldCondition(key=\"source\", match=MatchValue(value=\"wiki\")),\n            FieldCondition(key=\"year\", range=Range(gte=2022, lte=2024)),\n        ],\n        should=[\n            FieldCondition(key=\"tags\", match=MatchValue(value=\"ml\")),\n        ],\n    ),\n    limit=10,\n    with_payload=[\"text\", \"source\"],        # select payload fields\n)\n```\n\n## Hybrid Search (Dense + Sparse \u002F BM25)\n\n```python\nfrom qdrant_client.models import SparseVector, NamedVector, NamedSparseVector\n\n# Sparse vector (BM25-style from fastembed)\nfrom fastembed import SparseTextEmbedding\nsparse_model = SparseTextEmbedding(\"prithivida\u002FSplade_PP_en_v1\")\n\ndef get_sparse(text: str) -> SparseVector:\n    emb = list(sparse_model.embed([text]))[0]\n    return SparseVector(indices=emb.indices.tolist(), values=emb.values.tolist())\n\n# Hybrid search with RRF fusion\nfrom qdrant_client.models import Prefetch, FusionQuery, Fusion\n\nresults = client.query_points(\n    collection_name=\"multi_vec\",\n    prefetch=[\n        Prefetch(query=embed_dense(query), using=\"dense\", limit=20),\n        Prefetch(query=get_sparse(query), using=\"sparse\", limit=20),\n    ],\n    query=FusionQuery(fusion=Fusion.RRF),   # Reciprocal Rank Fusion\n    limit=5,\n    with_payload=True,\n)\n```\n\n## Payload Indexing\n\n```python\nfrom qdrant_client.models import PayloadSchemaType\n\n# Create index for faster filtered search\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"source\",\n    field_schema=PayloadSchemaType.KEYWORD,\n)\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"year\",\n    field_schema=PayloadSchemaType.INTEGER,\n)\n```\n\n## Manage Points\n\n```python\n# Get by ID\npoints = client.retrieve(\n    collection_name=\"documents\",\n    ids=[1, 2, 3],\n    with_payload=True,\n    with_vectors=False,\n)\n\n# Delete\nclient.delete(\n    collection_name=\"documents\",\n    points_selector=Filter(\n        must=[FieldCondition(key=\"source\", match=MatchValue(value=\"old\"))]\n    ),\n)\n\n# Update payload\nclient.set_payload(\n    collection_name=\"documents\",\n    payload={\"updated\": True},\n    points=[1, 2],\n)\n\n# Scroll (iterate all points)\noffset = None\nwhile True:\n    result, offset = client.scroll(\n        collection_name=\"documents\",\n        limit=100,\n        offset=offset,\n        with_payload=True,\n    )\n    if not result:\n        break\n    process_batch(result)\n```\n\n## Collections Management\n\n```python\n# List collections\ncolls = client.get_collections()\nnames = [c.name for c in colls.collections]\n\n# Collection info\ninfo = client.get_collection(\"documents\")\nprint(info.points_count, info.vectors_count)\n\n# Delete collection\nclient.delete_collection(\"documents\")\n\n# Recreate (idempotent)\nclient.recreate_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(size=1536, distance=Distance.COSINE),\n)\n```\n\n## Anti-Fake-Pass Checks\n\n- Vector dimension must match `VectorParams(size=...)` exactly — mismatches raise `Unprocessable`\n- `id` must be `int` or UUID string — nested objects raise validation error\n- `score_threshold` filters out points — if no results, lower threshold or check embeddings\n- `wait=True` on upsert ensures indexing before search — omit only for fire-and-forget ingestion\n- Sparse vectors need `SparseVectorParams` in collection config — can't add after creation without recreation\n- `query_points` (v1.7+) replaces legacy `search` API — check client version\n",{"name":5,"see_also":24,"triggers":29,"description":7,"do_not_use_for":39},[25,26,27,28],"ragas","langfuse","crawl4ai","firecrawl",[5,30,31,32,33,34,35,36,37,38],"vector database qdrant","qdrant collection","qdrant search","qdrant upsert","sparse dense hybrid search","qdrant filter","qdrant payload","qdrant python client","vector store qdrant",[40,41,42],"relational queries — use PostgreSQL\u002FSQLite","full-text only — use Elasticsearch","generic key-value store — use Redis","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fqdrant",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-12 23:12:27",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill qdrant",{"tool":59,"command":60},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill qdrant",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill qdrant","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fqdrant\u002FSKILL.md",true,[],[68,76,83,91,99,107],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]