[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EX18HASXD49A009MPHE1CT":3,"skill-same:01M6EX18HASXD49A009MPHE1CT":88},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":14,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6EX18HASXD49A009MPHE1CT","qdrant-vector-search",null,"High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.","henriquescastilho\u002Fmy-claude","henriquescastilho","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F153296945?v=4","01M6ESH7EXPXTH9CVQ4K16SRG8","Henrique Scheer","01M6ESH7JHEK2PTNNH4HEH787Z",0,"MIT","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-code-templates\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-qdrant\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"qdrant vector search","search","vector","Vector Search","Qdrant","with","performance","Scalable","Hybrid Search","high-performance","use","filtering","engine","embeddings","semantic search","rag","distributed","storage","research","rust","2026-11-10 10:12:30",false,"---\nname: qdrant-vector-search\ndescription: High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [RAG, Vector Search, Qdrant, Semantic Search, Embeddings, Similarity Search, HNSW, Production, Distributed]\ndependencies: [qdrant-client>=1.12.0]\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\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=[0.15, 0.25, ...],\n    query_filter={\n        \"must\": [{\"key\": \"category\", \"match\": {\"value\": \"tech\"}}]\n    },\n    limit=10\n)\n\nfor point in results:\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\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=[0.1, 0.2, ...],\n    limit=10,\n    with_payload=True,\n    with_vectors=False  # Don't return vectors (faster)\n)\n```\n\n### Filtered search\n\n```python\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue, Range\n\n# Complex filtering\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=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)\n\n# Shorthand filter syntax\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=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)\n```\n\n### Batch search\n\n```python\nfrom qdrant_client.models import SearchRequest\n\n# Multiple queries in one request\nresults = client.search_batch(\n    collection_name=\"documents\",\n    requests=[\n        SearchRequest(vector=[0.1, ...], limit=5),\n        SearchRequest(vector=[0.2, ...], limit=5, filter={\"must\": [...]}),\n        SearchRequest(vector=[0.3, ...], limit=10)\n    ]\n)\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    results = client.search(\n        collection_name=\"knowledge_base\",\n        query_vector=query_vector,\n        limit=top_k\n    )\n    return [{\"text\": r.payload[\"text\"], \"score\": r.score} for r in results]\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 vector\nresults = client.search(\n    collection_name=\"hybrid_search\",\n    query_vector=(\"dense\", query_dense),  # Specify which vector\n    limit=10\n)\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\nresults = client.search(\n    collection_name=\"quantized\",\n    query_vector=query,\n    search_params={\"quantization\": {\"rescore\": True}},  # Rescore top results\n    limit=10\n)\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**: 1.12.0+\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\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=[0.15, 0.25, ...],\n    query_filter={\n        \"must\": [{\"key\": \"category\", \"match\": {\"value\": \"tech\"}}]\n    },\n    limit=10\n)\n\nfor point in results:\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\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=[0.1, 0.2, ...],\n    limit=10,\n    with_payload=True,\n    with_vectors=False  # Don't return vectors (faster)\n)\n```\n\n### Filtered search\n\n```python\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue, Range\n\n# Complex filtering\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=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)\n\n# Shorthand filter syntax\nresults = client.search(\n    collection_name=\"documents\",\n    query_vector=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)\n```\n\n### Batch search\n\n```python\nfrom qdrant_client.models import SearchRequest\n\n# Multiple queries in one request\nresults = client.search_batch(\n    collection_name=\"documents\",\n    requests=[\n        SearchRequest(vector=[0.1, ...], limit=5),\n        SearchRequest(vector=[0.2, ...], limit=5, filter={\"must\": [...]}),\n        SearchRequest(vector=[0.3, ...], limit=10)\n    ]\n)\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    results = client.search(\n        collection_name=\"knowledge_base\",\n        query_vector=query_vector,\n        limit=top_k\n    )\n    return [{\"text\": r.payload[\"text\"], \"score\": r.score} for r in results]\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 vector\nresults = client.search(\n    collection_name=\"hybrid_search\",\n    query_vector=(\"dense\", query_dense),  # Specify which vector\n    limit=10\n)\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\nresults = client.search(\n    collection_name=\"quantized\",\n    query_vector=query,\n    search_params={\"quantization\": {\"rescore\": True}},  # Rescore top results\n    limit=10\n)\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**: 1.12.0+\n- **License**: Apache 2.0\n",{"name":5,"tags":44,"author":52,"license":15,"version":53,"description":7,"dependencies":54},[45,22,23,46,47,48,49,50,51],"RAG","Semantic Search","Embeddings","Similarity Search","HNSW","Production","Distributed","Orchestra Research","1.0.0",[55],"qdrant-client>=1.12.0","main","7925716f065257435fdb12e97f7e52842147d5ad",".codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-code-templates\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-qdrant","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude","https:\u002F\u002Fclaude.com\u002Fclaude-code","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho","Software · Applied AI · Quantitative Modeling · Building with Claude.","2026-06-10 12:24:46",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add henriquescastilho\u002Fmy-claude --skill qdrant-vector-search",{"tool":70,"command":71},"bunx","bunx skills add henriquescastilho\u002Fmy-claude --skill qdrant-vector-search",{"tool":73,"command":74},"pnpm","pnpm dlx skills add henriquescastilho\u002Fmy-claude --skill qdrant-vector-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-code-templates\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-qdrant\u002FSKILL.md",true,[78,84],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fadvanced-usage.md","REFERENCE","参考文档",14969,"https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-code-templates\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-qdrant\u002Freferences\u002Fadvanced-usage.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Ftroubleshooting.md",12682,"https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-code-templates\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-qdrant\u002Freferences\u002Ftroubleshooting.md",[89,130,139,148,169,197],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":111,"publishedAt":39},"01M6F0B6XPQ65AX2X0DWK8KT3E","markitdown","Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-scientific-writer\u002Fskills\u002Fmarkitdown\u002FSKILL.md",[95,100,103,106],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":104,"categoryName":105,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[91,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,24],"docx","PDF","pptx","xlsx","documents","csv","ocr","Audio","Bash","markdown","convert","read","write","edit","html","images","files","youtube",{"skillNo":131,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":138,"publishedAt":39},"01M6F06SBHR9F0SDWE282Y8075","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-scientific-writer\u002Fscientific_writer\u002F.claude\u002Fskills\u002Fmarkitdown\u002FSKILL.md",[134,135,136,137],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":104,"categoryName":105,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},[91,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,24],{"skillNo":140,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":147,"publishedAt":39},"01M6F02D4R14EJAPBWVDF9J9VQ","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-scientific-writer\u002F.claude\u002Fskills\u002Fmarkitdown\u002FSKILL.md",[143,144,145,146],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":104,"categoryName":105,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},[91,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,24],{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":39},"01M6F000KS6YB4MKS774G4R8ND","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-scientific-skills\u002Fscientific-skills\u002Fzarr-python\u002FSKILL.md",[],[155,156,36,157,158,159,160,161,162,163,164,165,166,167,168],"python","zarr python","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"publishedAt":39},"01M6EZZJWFXM1GR78KTW6J0DN8","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-scientific-skills\u002Fscientific-skills\u002Fwhat-if-oracle\u002FSKILL.md",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发",[179,180,181,182,183,184,185,186,187,188,189,123,124,190,191,192,193,194,195,196],"oracle","what if oracle","go","run","ux","futures","analysis","explore","decision","branch","question","idea","exploration","options","stress-test","strategies","scenario","stress",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":213,"publishedAt":39},"01M6EZZCXAEB49RXGQCJX5E8GB","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Fhenriquescastilho\u002Fmy-claude\u002Fblob\u002Fmain\u002F.codex\u002Fvendor_imports\u002Fclaude\u002Fmarketplaces\u002Fclaude-scientific-skills\u002Fscientific-skills\u002Fvenue-templates\u002FSKILL.md",[203,206,209,210],{"categoryNo":204,"categoryName":205,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":207,"categoryName":208,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":176,"categoryName":177,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":211,"categoryName":212,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000036","内容创作者",[214,215,37,216,217,218,219,220,120,221,123,124,125,222,223,224,225,226,168,227],"templates","venue templates","guidelines","NeurIPS","ICML","LaTeX","science","access","proposals","Academic","requirements","formatting","journal","chi"]