[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DGG6CFEE8VWHTJESJGE2QA":3,"skill-same:01M6DGG6CFEE8VWHTJESJGE2QA":81},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6DGG6CFEE8VWHTJESJGE2QA","qdrant",null,"Vector search engine for production RAG systems.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F60\u002F60dc4d7bcc4c18d37366de0b2480024c5761c79ff57284f7511d6d776bc301bd\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"Qdrant","vector","systems","engine","Production","HNSW","Similarity Search","Vector Search","embeddings","macos","search","semantic search","rag","distributed","windows","research","linux","2026-11-10 10:12:30",false,"---\nname: qdrant\ndescription: Vector search engine for production RAG systems.\nversion: 1.0.1\nauthor: Orchestra Research\nlicense: MIT\ndependencies: [qdrant-client>=1.14.0]\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [RAG, Vector Search, Qdrant, Semantic Search, Embeddings, Similarity Search, HNSW, Production, Distributed]\n\n---\n\n# Qdrant - Vector Similarity Search Engine\n\nHigh-performance vector database written in Rust for production RAG and semantic search.\n\n## When to use Qdrant\n\n**Use Qdrant when:**\n- Building production RAG systems requiring low latency\n- Need hybrid search (vectors + metadata filtering)\n- Require horizontal scaling with sharding\u002Freplication\n- Want on-premise deployment with full data control\n- Need multi-vector storage per record (dense + sparse)\n- Building real-time recommendation systems\n\n**Key features:**\n- **Rust-powered**: Memory-safe, high performance\n- **Rich filtering**: Filter by any payload field during search\n- **Multiple vectors**: Dense, sparse, multi-dense per point\n- **Quantization**: Scalar, product, binary for memory efficiency\n- **Distributed**: Raft consensus, sharding, replication\n- **REST + gRPC**: Both APIs with full feature parity\n\n**Use alternatives instead:**\n- **Chroma**: Simpler setup, embedded use cases\n- **FAISS**: Maximum raw speed, research\u002Fbatch processing\n- **Pinecone**: Fully managed, zero ops preferred\n- **Weaviate**: GraphQL preference, built-in vectorizers\n\n## Quick start\n\n### Installation\n\n```bash\n# Python client\npip install qdrant-client\n\n# Docker (recommended for development)\ndocker run -p 6333:6333 -p 6334:6334 qdrant\u002Fqdrant\n\n# Docker with persistent storage\ndocker run -p 6333:6333 -p 6334:6334 \\\n    -v $(pwd)\u002Fqdrant_storage:\u002Fqdrant\u002Fstorage \\\n    qdrant\u002Fqdrant\n```\n\n### Basic usage\n\n```python\nfrom qdrant_client import QdrantClient\nfrom qdrant_client.models import Distance, VectorParams, PointStruct\n\n# Connect to Qdrant\nclient = QdrantClient(host=\"localhost\", port=6333)\n\n# Create collection\nclient.create_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE)\n)\n\n# Insert vectors with payload\nclient.upsert(\n    collection_name=\"documents\",\n    points=[\n        PointStruct(\n            id=1,\n            vector=[0.1, 0.2, ...],  # 384-dim vector\n            payload={\"title\": \"Doc 1\", \"category\": \"tech\"}\n        ),\n        PointStruct(\n            id=2,\n            vector=[0.3, 0.4, ...],\n            payload={\"title\": \"Doc 2\", \"category\": \"science\"}\n        )\n    ]\n)\n\n# Search with filtering (query_points is the current API; client.search is removed in qdrant-client 1.14+)\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=[0.15, 0.25, ...],\n    query_filter={\n        \"must\": [{\"key\": \"category\", \"match\": {\"value\": \"tech\"}}]\n    },\n    limit=10\n)\n\nfor point in response.points:\n    print(f\"ID: {point.id}, Score: {point.score}, Payload: {point.payload}\")\n```\n\n## Core concepts\n\n### Points - Basic data unit\n\n```python\nfrom qdrant_client.models import PointStruct\n\n# Point = ID + Vector(s) + Payload\npoint = PointStruct(\n    id=123,                              # Integer or UUID string\n    vector=[0.1, 0.2, 0.3, ...],        # Dense vector\n    payload={                            # Arbitrary JSON metadata\n        \"title\": \"Document title\",\n        \"category\": \"tech\",\n        \"timestamp\": 1699900000,\n        \"tags\": [\"python\", \"ml\"]\n    }\n)\n\n# Batch upsert (recommended)\nclient.upsert(\n    collection_name=\"documents\",\n    points=[point1, point2, point3],\n    wait=True  # Wait for indexing\n)\n```\n\n### Collections - Vector containers\n\n```python\nfrom qdrant_client.models import VectorParams, Distance, HnswConfigDiff\n\n# Create with HNSW configuration\nclient.create_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(\n        size=384,                        # Vector dimensions\n        distance=Distance.COSINE         # COSINE, EUCLID, DOT, MANHATTAN\n    ),\n    hnsw_config=HnswConfigDiff(\n        m=16,                            # Connections per node (default 16)\n        ef_construct=100,                # Build-time accuracy (default 100)\n        full_scan_threshold=10000        # Switch to brute force below this\n    ),\n    on_disk_payload=True                 # Store payload on disk\n)\n\n# Collection info\ninfo = client.get_collection(\"documents\")\nprint(f\"Points: {info.points_count}, Vectors: {info.vectors_count}\")\n```\n\n### Distance metrics\n\n| Metric | Use Case | Range |\n|--------|----------|-------|\n| `COSINE` | Text embeddings, normalized vectors | 0 to 2 |\n| `EUCLID` | Spatial data, image features | 0 to ∞ |\n| `DOT` | Recommendations, unnormalized | -∞ to ∞ |\n| `MANHATTAN` | Sparse features, discrete data | 0 to ∞ |\n\n## Search operations\n\n### Basic search\n\n```python\n# Simple nearest neighbor search (returns a QueryResponse; use .points)\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=[0.1, 0.2, ...],\n    limit=10,\n    with_payload=True,\n    with_vectors=False  # Don't return vectors (faster)\n)\nresults = response.points\n```\n\n### Filtered search\n\n```python\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue, Range\n\n# Complex filtering\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=query_embedding,\n    query_filter=Filter(\n        must=[\n            FieldCondition(key=\"category\", match=MatchValue(value=\"tech\")),\n            FieldCondition(key=\"timestamp\", range=Range(gte=1699000000))\n        ],\n        must_not=[\n            FieldCondition(key=\"status\", match=MatchValue(value=\"archived\"))\n        ]\n    ),\n    limit=10\n).points\n\n# Shorthand filter syntax\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=query_embedding,\n    query_filter={\n        \"must\": [\n            {\"key\": \"category\", \"match\": {\"value\": \"tech\"}},\n            {\"key\": \"price\", \"range\": {\"gte\": 10, \"lte\": 100}}\n        ]\n    },\n    limit=10\n).points\n```\n\n### Batch search\n\n```python\nfrom qdrant_client.models import QueryRequest\n\n# Multiple queries in one request (search_batch is replaced by query_batch_points)\nresponses = client.query_batch_points(\n    collection_name=\"documents\",\n    requests=[\n        QueryRequest(query=[0.1, ...], limit=5),\n        QueryRequest(query=[0.2, ...], limit=5, filter={\"must\": [...]}),\n        QueryRequest(query=[0.3, ...], limit=10)\n    ]\n)\n# Each element is a QueryResponse; use .points\nfor resp in responses:\n    for point in resp.points:\n        print(point.id, point.score)\n```\n\n## RAG integration\n\n### With sentence-transformers\n\n```python\nfrom sentence_transformers import SentenceTransformer\nfrom qdrant_client import QdrantClient\nfrom qdrant_client.models import VectorParams, Distance, PointStruct\n\n# Initialize\nencoder = SentenceTransformer(\"all-MiniLM-L6-v2\")\nclient = QdrantClient(host=\"localhost\", port=6333)\n\n# Create collection\nclient.create_collection(\n    collection_name=\"knowledge_base\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE)\n)\n\n# Index documents\ndocuments = [\n    {\"id\": 1, \"text\": \"Python is a programming language\", \"source\": \"wiki\"},\n    {\"id\": 2, \"text\": \"Machine learning uses algorithms\", \"source\": \"textbook\"},\n]\n\npoints = [\n    PointStruct(\n        id=doc[\"id\"],\n        vector=encoder.encode(doc[\"text\"]).tolist(),\n        payload={\"text\": doc[\"text\"], \"source\": doc[\"source\"]}\n    )\n    for doc in documents\n]\nclient.upsert(collection_name=\"knowledge_base\", points=points)\n\n# RAG retrieval\ndef retrieve(query: str, top_k: int = 5) -> list[dict]:\n    query_vector = encoder.encode(query).tolist()\n    response = client.query_points(\n        collection_name=\"knowledge_base\",\n        query=query_vector,\n        limit=top_k\n    )\n    return [{\"text\": r.payload[\"text\"], \"score\": r.score} for r in response.points]\n\n# Use in RAG pipeline\ncontext = retrieve(\"What is Python?\")\nprompt = f\"Context: {context}\\n\\nQuestion: What is Python?\"\n```\n\n### With LangChain\n\n```python\nfrom langchain_community.vectorstores import Qdrant\nfrom langchain_community.embeddings import HuggingFaceEmbeddings\n\nembeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\nvectorstore = Qdrant.from_documents(documents, embeddings, url=\"http:\u002F\u002Flocalhost:6333\", collection_name=\"docs\")\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 5})\n```\n\n### With LlamaIndex\n\n```python\nfrom llama_index.vector_stores.qdrant import QdrantVectorStore\nfrom llama_index.core import VectorStoreIndex, StorageContext\n\nvector_store = QdrantVectorStore(client=client, collection_name=\"llama_docs\")\nstorage_context = StorageContext.from_defaults(vector_store=vector_store)\nindex = VectorStoreIndex.from_documents(documents, storage_context=storage_context)\nquery_engine = index.as_query_engine()\n```\n\n## Multi-vector support\n\n### Named vectors (different embedding models)\n\n```python\nfrom qdrant_client.models import VectorParams, Distance\n\n# Collection with multiple vector types\nclient.create_collection(\n    collection_name=\"hybrid_search\",\n    vectors_config={\n        \"dense\": VectorParams(size=384, distance=Distance.COSINE),\n        \"sparse\": VectorParams(size=30000, distance=Distance.DOT)\n    }\n)\n\n# Insert with named vectors\nclient.upsert(\n    collection_name=\"hybrid_search\",\n    points=[\n        PointStruct(\n            id=1,\n            vector={\n                \"dense\": dense_embedding,\n                \"sparse\": sparse_embedding\n            },\n            payload={\"text\": \"document text\"}\n        )\n    ]\n)\n\n# Search specific named vector (pass the vector name via `using`)\nresponse = client.query_points(\n    collection_name=\"hybrid_search\",\n    query=query_dense,\n    using=\"dense\",  # Specify which named vector to search\n    limit=10\n)\nresults = response.points\n```\n\n### Sparse vectors (BM25, SPLADE)\n\n```python\nfrom qdrant_client.models import SparseVectorParams, SparseIndexParams, SparseVector\n\n# Collection with sparse vectors\nclient.create_collection(\n    collection_name=\"sparse_search\",\n    vectors_config={},\n    sparse_vectors_config={\"text\": SparseVectorParams(index=SparseIndexParams(on_disk=False))}\n)\n\n# Insert sparse vector\nclient.upsert(\n    collection_name=\"sparse_search\",\n    points=[PointStruct(id=1, vector={\"text\": SparseVector(indices=[1, 5, 100], values=[0.5, 0.8, 0.2])}, payload={\"text\": \"document\"})]\n)\n```\n\n## Quantization (memory optimization)\n\n```python\nfrom qdrant_client.models import ScalarQuantization, ScalarQuantizationConfig, ScalarType\n\n# Scalar quantization (4x memory reduction)\nclient.create_collection(\n    collection_name=\"quantized\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE),\n    quantization_config=ScalarQuantization(\n        scalar=ScalarQuantizationConfig(\n            type=ScalarType.INT8,\n            quantile=0.99,        # Clip outliers\n            always_ram=True      # Keep quantized in RAM\n        )\n    )\n)\n\n# Search with rescoring\nresponse = client.query_points(\n    collection_name=\"quantized\",\n    query=query,\n    search_params={\"quantization\": {\"rescore\": True}},  # Rescore top results\n    limit=10\n)\nresults = response.points\n```\n\n## Payload indexing\n\n```python\nfrom qdrant_client.models import PayloadSchemaType\n\n# Create payload index for faster filtering\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"category\",\n    field_schema=PayloadSchemaType.KEYWORD\n)\n\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"timestamp\",\n    field_schema=PayloadSchemaType.INTEGER\n)\n\n# Index types: KEYWORD, INTEGER, FLOAT, GEO, TEXT (full-text), BOOL\n```\n\n## Production deployment\n\n### Qdrant Cloud\n\n```python\nfrom qdrant_client import QdrantClient\n\n# Connect to Qdrant Cloud\nclient = QdrantClient(\n    url=\"https:\u002F\u002Fyour-cluster.cloud.qdrant.io\",\n    api_key=\"your-api-key\"\n)\n```\n\n### Performance tuning\n\n```python\n# Optimize for search speed (higher recall)\nclient.update_collection(\n    collection_name=\"documents\",\n    hnsw_config=HnswConfigDiff(ef_construct=200, m=32)\n)\n\n# Optimize for indexing speed (bulk loads)\nclient.update_collection(\n    collection_name=\"documents\",\n    optimizer_config={\"indexing_threshold\": 20000}\n)\n```\n\n## Best practices\n\n1. **Batch operations** - Use batch upsert\u002Fsearch for efficiency\n2. **Payload indexing** - Index fields used in filters\n3. **Quantization** - Enable for large collections (>1M vectors)\n4. **Sharding** - Use for collections >10M vectors\n5. **On-disk storage** - Enable `on_disk_payload` for large payloads\n6. **Connection pooling** - Reuse client instances\n\n## Common issues\n\n**Slow search with filters:**\n```python\n# Create payload index for filtered fields\nclient.create_payload_index(\n    collection_name=\"docs\",\n    field_name=\"category\",\n    field_schema=PayloadSchemaType.KEYWORD\n)\n```\n\n**Out of memory:**\n```python\n# Enable quantization and on-disk storage\nclient.create_collection(\n    collection_name=\"large_collection\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE),\n    quantization_config=ScalarQuantization(...),\n    on_disk_payload=True\n)\n```\n\n**Connection issues:**\n```python\n# Use timeout and retry\nclient = QdrantClient(\n    host=\"localhost\",\n    port=6333,\n    timeout=30,\n    prefer_grpc=True  # gRPC for better performance\n)\n```\n\n## References\n\n- **[Advanced Usage](references\u002Fadvanced-usage.md)** - Distributed mode, hybrid search, recommendations\n- **[Troubleshooting](references\u002Ftroubleshooting.md)** - Common issues, debugging, performance tuning\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant (22k+ stars)\n- **Docs**: https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002F\n- **Python Client**: https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-client\n- **Cloud**: https:\u002F\u002Fcloud.qdrant.io\n- **Version**: 1.14.0+\n- **License**: Apache 2.0\n","# Qdrant - Vector Similarity Search Engine\n\nHigh-performance vector database written in Rust for production RAG and semantic search.\n\n## When to use Qdrant\n\n**Use Qdrant when:**\n- Building production RAG systems requiring low latency\n- Need hybrid search (vectors + metadata filtering)\n- Require horizontal scaling with sharding\u002Freplication\n- Want on-premise deployment with full data control\n- Need multi-vector storage per record (dense + sparse)\n- Building real-time recommendation systems\n\n**Key features:**\n- **Rust-powered**: Memory-safe, high performance\n- **Rich filtering**: Filter by any payload field during search\n- **Multiple vectors**: Dense, sparse, multi-dense per point\n- **Quantization**: Scalar, product, binary for memory efficiency\n- **Distributed**: Raft consensus, sharding, replication\n- **REST + gRPC**: Both APIs with full feature parity\n\n**Use alternatives instead:**\n- **Chroma**: Simpler setup, embedded use cases\n- **FAISS**: Maximum raw speed, research\u002Fbatch processing\n- **Pinecone**: Fully managed, zero ops preferred\n- **Weaviate**: GraphQL preference, built-in vectorizers\n\n## Quick start\n\n### Installation\n\n```bash\n# Python client\npip install qdrant-client\n\n# Docker (recommended for development)\ndocker run -p 6333:6333 -p 6334:6334 qdrant\u002Fqdrant\n\n# Docker with persistent storage\ndocker run -p 6333:6333 -p 6334:6334 \\\n    -v $(pwd)\u002Fqdrant_storage:\u002Fqdrant\u002Fstorage \\\n    qdrant\u002Fqdrant\n```\n\n### Basic usage\n\n```python\nfrom qdrant_client import QdrantClient\nfrom qdrant_client.models import Distance, VectorParams, PointStruct\n\n# Connect to Qdrant\nclient = QdrantClient(host=\"localhost\", port=6333)\n\n# Create collection\nclient.create_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE)\n)\n\n# Insert vectors with payload\nclient.upsert(\n    collection_name=\"documents\",\n    points=[\n        PointStruct(\n            id=1,\n            vector=[0.1, 0.2, ...],  # 384-dim vector\n            payload={\"title\": \"Doc 1\", \"category\": \"tech\"}\n        ),\n        PointStruct(\n            id=2,\n            vector=[0.3, 0.4, ...],\n            payload={\"title\": \"Doc 2\", \"category\": \"science\"}\n        )\n    ]\n)\n\n# Search with filtering (query_points is the current API; client.search is removed in qdrant-client 1.14+)\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=[0.15, 0.25, ...],\n    query_filter={\n        \"must\": [{\"key\": \"category\", \"match\": {\"value\": \"tech\"}}]\n    },\n    limit=10\n)\n\nfor point in response.points:\n    print(f\"ID: {point.id}, Score: {point.score}, Payload: {point.payload}\")\n```\n\n## Core concepts\n\n### Points - Basic data unit\n\n```python\nfrom qdrant_client.models import PointStruct\n\n# Point = ID + Vector(s) + Payload\npoint = PointStruct(\n    id=123,                              # Integer or UUID string\n    vector=[0.1, 0.2, 0.3, ...],        # Dense vector\n    payload={                            # Arbitrary JSON metadata\n        \"title\": \"Document title\",\n        \"category\": \"tech\",\n        \"timestamp\": 1699900000,\n        \"tags\": [\"python\", \"ml\"]\n    }\n)\n\n# Batch upsert (recommended)\nclient.upsert(\n    collection_name=\"documents\",\n    points=[point1, point2, point3],\n    wait=True  # Wait for indexing\n)\n```\n\n### Collections - Vector containers\n\n```python\nfrom qdrant_client.models import VectorParams, Distance, HnswConfigDiff\n\n# Create with HNSW configuration\nclient.create_collection(\n    collection_name=\"documents\",\n    vectors_config=VectorParams(\n        size=384,                        # Vector dimensions\n        distance=Distance.COSINE         # COSINE, EUCLID, DOT, MANHATTAN\n    ),\n    hnsw_config=HnswConfigDiff(\n        m=16,                            # Connections per node (default 16)\n        ef_construct=100,                # Build-time accuracy (default 100)\n        full_scan_threshold=10000        # Switch to brute force below this\n    ),\n    on_disk_payload=True                 # Store payload on disk\n)\n\n# Collection info\ninfo = client.get_collection(\"documents\")\nprint(f\"Points: {info.points_count}, Vectors: {info.vectors_count}\")\n```\n\n### Distance metrics\n\n| Metric | Use Case | Range |\n|--------|----------|-------|\n| `COSINE` | Text embeddings, normalized vectors | 0 to 2 |\n| `EUCLID` | Spatial data, image features | 0 to ∞ |\n| `DOT` | Recommendations, unnormalized | -∞ to ∞ |\n| `MANHATTAN` | Sparse features, discrete data | 0 to ∞ |\n\n## Search operations\n\n### Basic search\n\n```python\n# Simple nearest neighbor search (returns a QueryResponse; use .points)\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=[0.1, 0.2, ...],\n    limit=10,\n    with_payload=True,\n    with_vectors=False  # Don't return vectors (faster)\n)\nresults = response.points\n```\n\n### Filtered search\n\n```python\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue, Range\n\n# Complex filtering\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=query_embedding,\n    query_filter=Filter(\n        must=[\n            FieldCondition(key=\"category\", match=MatchValue(value=\"tech\")),\n            FieldCondition(key=\"timestamp\", range=Range(gte=1699000000))\n        ],\n        must_not=[\n            FieldCondition(key=\"status\", match=MatchValue(value=\"archived\"))\n        ]\n    ),\n    limit=10\n).points\n\n# Shorthand filter syntax\nresponse = client.query_points(\n    collection_name=\"documents\",\n    query=query_embedding,\n    query_filter={\n        \"must\": [\n            {\"key\": \"category\", \"match\": {\"value\": \"tech\"}},\n            {\"key\": \"price\", \"range\": {\"gte\": 10, \"lte\": 100}}\n        ]\n    },\n    limit=10\n).points\n```\n\n### Batch search\n\n```python\nfrom qdrant_client.models import QueryRequest\n\n# Multiple queries in one request (search_batch is replaced by query_batch_points)\nresponses = client.query_batch_points(\n    collection_name=\"documents\",\n    requests=[\n        QueryRequest(query=[0.1, ...], limit=5),\n        QueryRequest(query=[0.2, ...], limit=5, filter={\"must\": [...]}),\n        QueryRequest(query=[0.3, ...], limit=10)\n    ]\n)\n# Each element is a QueryResponse; use .points\nfor resp in responses:\n    for point in resp.points:\n        print(point.id, point.score)\n```\n\n## RAG integration\n\n### With sentence-transformers\n\n```python\nfrom sentence_transformers import SentenceTransformer\nfrom qdrant_client import QdrantClient\nfrom qdrant_client.models import VectorParams, Distance, PointStruct\n\n# Initialize\nencoder = SentenceTransformer(\"all-MiniLM-L6-v2\")\nclient = QdrantClient(host=\"localhost\", port=6333)\n\n# Create collection\nclient.create_collection(\n    collection_name=\"knowledge_base\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE)\n)\n\n# Index documents\ndocuments = [\n    {\"id\": 1, \"text\": \"Python is a programming language\", \"source\": \"wiki\"},\n    {\"id\": 2, \"text\": \"Machine learning uses algorithms\", \"source\": \"textbook\"},\n]\n\npoints = [\n    PointStruct(\n        id=doc[\"id\"],\n        vector=encoder.encode(doc[\"text\"]).tolist(),\n        payload={\"text\": doc[\"text\"], \"source\": doc[\"source\"]}\n    )\n    for doc in documents\n]\nclient.upsert(collection_name=\"knowledge_base\", points=points)\n\n# RAG retrieval\ndef retrieve(query: str, top_k: int = 5) -> list[dict]:\n    query_vector = encoder.encode(query).tolist()\n    response = client.query_points(\n        collection_name=\"knowledge_base\",\n        query=query_vector,\n        limit=top_k\n    )\n    return [{\"text\": r.payload[\"text\"], \"score\": r.score} for r in response.points]\n\n# Use in RAG pipeline\ncontext = retrieve(\"What is Python?\")\nprompt = f\"Context: {context}\\n\\nQuestion: What is Python?\"\n```\n\n### With LangChain\n\n```python\nfrom langchain_community.vectorstores import Qdrant\nfrom langchain_community.embeddings import HuggingFaceEmbeddings\n\nembeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\nvectorstore = Qdrant.from_documents(documents, embeddings, url=\"http:\u002F\u002Flocalhost:6333\", collection_name=\"docs\")\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 5})\n```\n\n### With LlamaIndex\n\n```python\nfrom llama_index.vector_stores.qdrant import QdrantVectorStore\nfrom llama_index.core import VectorStoreIndex, StorageContext\n\nvector_store = QdrantVectorStore(client=client, collection_name=\"llama_docs\")\nstorage_context = StorageContext.from_defaults(vector_store=vector_store)\nindex = VectorStoreIndex.from_documents(documents, storage_context=storage_context)\nquery_engine = index.as_query_engine()\n```\n\n## Multi-vector support\n\n### Named vectors (different embedding models)\n\n```python\nfrom qdrant_client.models import VectorParams, Distance\n\n# Collection with multiple vector types\nclient.create_collection(\n    collection_name=\"hybrid_search\",\n    vectors_config={\n        \"dense\": VectorParams(size=384, distance=Distance.COSINE),\n        \"sparse\": VectorParams(size=30000, distance=Distance.DOT)\n    }\n)\n\n# Insert with named vectors\nclient.upsert(\n    collection_name=\"hybrid_search\",\n    points=[\n        PointStruct(\n            id=1,\n            vector={\n                \"dense\": dense_embedding,\n                \"sparse\": sparse_embedding\n            },\n            payload={\"text\": \"document text\"}\n        )\n    ]\n)\n\n# Search specific named vector (pass the vector name via `using`)\nresponse = client.query_points(\n    collection_name=\"hybrid_search\",\n    query=query_dense,\n    using=\"dense\",  # Specify which named vector to search\n    limit=10\n)\nresults = response.points\n```\n\n### Sparse vectors (BM25, SPLADE)\n\n```python\nfrom qdrant_client.models import SparseVectorParams, SparseIndexParams, SparseVector\n\n# Collection with sparse vectors\nclient.create_collection(\n    collection_name=\"sparse_search\",\n    vectors_config={},\n    sparse_vectors_config={\"text\": SparseVectorParams(index=SparseIndexParams(on_disk=False))}\n)\n\n# Insert sparse vector\nclient.upsert(\n    collection_name=\"sparse_search\",\n    points=[PointStruct(id=1, vector={\"text\": SparseVector(indices=[1, 5, 100], values=[0.5, 0.8, 0.2])}, payload={\"text\": \"document\"})]\n)\n```\n\n## Quantization (memory optimization)\n\n```python\nfrom qdrant_client.models import ScalarQuantization, ScalarQuantizationConfig, ScalarType\n\n# Scalar quantization (4x memory reduction)\nclient.create_collection(\n    collection_name=\"quantized\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE),\n    quantization_config=ScalarQuantization(\n        scalar=ScalarQuantizationConfig(\n            type=ScalarType.INT8,\n            quantile=0.99,        # Clip outliers\n            always_ram=True      # Keep quantized in RAM\n        )\n    )\n)\n\n# Search with rescoring\nresponse = client.query_points(\n    collection_name=\"quantized\",\n    query=query,\n    search_params={\"quantization\": {\"rescore\": True}},  # Rescore top results\n    limit=10\n)\nresults = response.points\n```\n\n## Payload indexing\n\n```python\nfrom qdrant_client.models import PayloadSchemaType\n\n# Create payload index for faster filtering\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"category\",\n    field_schema=PayloadSchemaType.KEYWORD\n)\n\nclient.create_payload_index(\n    collection_name=\"documents\",\n    field_name=\"timestamp\",\n    field_schema=PayloadSchemaType.INTEGER\n)\n\n# Index types: KEYWORD, INTEGER, FLOAT, GEO, TEXT (full-text), BOOL\n```\n\n## Production deployment\n\n### Qdrant Cloud\n\n```python\nfrom qdrant_client import QdrantClient\n\n# Connect to Qdrant Cloud\nclient = QdrantClient(\n    url=\"https:\u002F\u002Fyour-cluster.cloud.qdrant.io\",\n    api_key=\"your-api-key\"\n)\n```\n\n### Performance tuning\n\n```python\n# Optimize for search speed (higher recall)\nclient.update_collection(\n    collection_name=\"documents\",\n    hnsw_config=HnswConfigDiff(ef_construct=200, m=32)\n)\n\n# Optimize for indexing speed (bulk loads)\nclient.update_collection(\n    collection_name=\"documents\",\n    optimizer_config={\"indexing_threshold\": 20000}\n)\n```\n\n## Best practices\n\n1. **Batch operations** - Use batch upsert\u002Fsearch for efficiency\n2. **Payload indexing** - Index fields used in filters\n3. **Quantization** - Enable for large collections (>1M vectors)\n4. **Sharding** - Use for collections >10M vectors\n5. **On-disk storage** - Enable `on_disk_payload` for large payloads\n6. **Connection pooling** - Reuse client instances\n\n## Common issues\n\n**Slow search with filters:**\n```python\n# Create payload index for filtered fields\nclient.create_payload_index(\n    collection_name=\"docs\",\n    field_name=\"category\",\n    field_schema=PayloadSchemaType.KEYWORD\n)\n```\n\n**Out of memory:**\n```python\n# Enable quantization and on-disk storage\nclient.create_collection(\n    collection_name=\"large_collection\",\n    vectors_config=VectorParams(size=384, distance=Distance.COSINE),\n    quantization_config=ScalarQuantization(...),\n    on_disk_payload=True\n)\n```\n\n**Connection issues:**\n```python\n# Use timeout and retry\nclient = QdrantClient(\n    host=\"localhost\",\n    port=6333,\n    timeout=30,\n    prefer_grpc=True  # gRPC for better performance\n)\n```\n\n## References\n\n- **[Advanced Usage](references\u002Fadvanced-usage.md)** - Distributed mode, hybrid search, recommendations\n- **[Troubleshooting](references\u002Ftroubleshooting.md)** - Common issues, debugging, performance tuning\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant (22k+ stars)\n- **Docs**: https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002F\n- **Python Client**: https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-client\n- **Cloud**: https:\u002F\u002Fcloud.qdrant.io\n- **Version**: 1.14.0+\n- **License**: Apache 2.0\n",{"name":5,"author":41,"license":15,"version":42,"metadata":43,"platforms":50,"description":7,"dependencies":51},"Orchestra Research","1.0.1",{"hermes":44},{"tags":45},[46,26,19,47,48,25,24,23,49],"RAG","Semantic Search","Embeddings","Distributed",[35,28,33],[52],"qdrant-client>=1.14.0","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F60\u002F60dc4d7bcc4c18d37366de0b2480024c5761c79ff57284f7511d6d776bc301bd",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add zapabob\u002FSkills --skill qdrant",{"tool":67,"command":68},"bunx","bunx skills add zapabob\u002FSkills --skill qdrant",{"tool":70,"command":71},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill qdrant","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F60\u002F60dc4d7bcc4c18d37366de0b2480024c5761c79ff57284f7511d6d776bc301bd\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"index.json","REFERENCE","参考文档",653,"https:\u002F\u002Fgithub.com\u002FDCx7C5\u002Fai-marketplace\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-containers-scanning-trivy\u002Findex.json",[82,116,151,178,205,222],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":101,"publishedAt":36},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[88,93,96],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":94,"categoryName":95,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[84,102,28,103,104,35,33,105,29,106,107,108,109,110,111,112,53,113,114,115],"openclaw","cli","github","official","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":133,"publishedAt":36},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[122,125,128,129,130],{"categoryNo":123,"categoryName":124,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":126,"categoryName":127,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":94,"categoryName":95,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":131,"categoryName":132,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者",[134,135,136,137,28,138,35,139,33,140,141,142,143,144,145,146,147,148,149,150],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":36},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000016","图像与多媒体",[153,28,35,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":187,"publishedAt":36},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[184],{"categoryNo":185,"categoryName":186,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000013","分析与可视化",[188,28,189,190,33,191,192,193,194,195,196,168,197,198,199,200,201,202,203,204],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":212,"publishedAt":36},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[211],{"categoryNo":94,"categoryName":95,"taxonomyType":91,"taxonomyTypeDesc":92},[207,28,213,104,35,214,215,216,217,218,219,110,111,220,221],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":230,"publishedAt":36},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[228,229],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[231,232,233,35,34,161,234,235,236,164,23,108,237,238,239,240,241,242,243,244],"llms","vLLM","serving llms vllm","openai api","tensor","Inference Serving","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]