[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-databricks-databricks-vector-search":3,"mdc--xbb664-key":33,"related-org-databricks-databricks-vector-search":2615,"related-repo-databricks-databricks-vector-search":2802},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":31,"mdContent":32},"databricks-vector-search","configure Databricks Vector Search for RAG","Databricks Vector Search endpoints and indexes for RAG and semantic search; covers index types, search modes, end-to-end RAG patterns",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"databricks","Databricks","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdatabricks.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"RAG","rag",{"name":20,"slug":21,"type":15},"Search","search",{"name":9,"slug":8,"type":15},204,"https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills","2026-07-12T08:04:50.559046",null,60,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":26},[],"https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills\u002Ftree\u002FHEAD\u002Fplugins\u002Fdatabricks\u002Fcopilot\u002Fskills\u002Fdatabricks-vector-search","---\nname: databricks-vector-search\ndescription: \"Databricks Vector Search endpoints and indexes for RAG and semantic search; covers index types, search modes, end-to-end RAG patterns\"\nmetadata:\n  version: \"0.1.0\"\nparent: databricks-core\n---\n\n# Databricks Vector Search\n\n**FIRST**: Use the parent `databricks-core` skill for CLI basics, authentication, and profile selection.\n\nPatterns for creating, managing, and querying vector search indexes for RAG and semantic search applications.\n\n## When to Use\n\nUse this skill when:\n- Building RAG (Retrieval-Augmented Generation) applications\n- Implementing semantic search or similarity matching\n- Creating vector indexes from Delta tables\n- Choosing between storage-optimized and standard endpoints\n- Querying vector indexes with filters\n\n## Overview\n\nDatabricks Vector Search provides managed vector similarity search with automatic embedding generation and Delta Lake integration.\n\n| Component | Description |\n|-----------|-------------|\n| **Endpoint** | Compute resource hosting indexes (Standard or Storage-Optimized) |\n| **Index** | Vector data structure for similarity search |\n| **Delta Sync** | Auto-syncs with source Delta table |\n| **Direct Access** | Manual CRUD operations on vectors |\n\n## Endpoint Types\n\n| Type | Latency | Capacity | Cost | Best For |\n|------|---------|----------|------|----------|\n| **Standard** | 20-50ms | 320M vectors (768 dim) | Higher | Real-time, low-latency |\n| **Storage-Optimized** | 300-500ms | 1B+ vectors (768 dim) | 7x lower | Large-scale, cost-sensitive |\n\n## Index Types\n\n| Type | Embeddings | Sync | Use Case |\n|------|------------|------|----------|\n| **Delta Sync (managed)** | Databricks computes | Auto from Delta | Easiest setup |\n| **Delta Sync (self-managed)** | You provide | Auto from Delta | Custom embeddings |\n| **Direct Access** | You provide | Manual CRUD | Real-time updates |\n\n## Quick Start\n\n### Create Endpoint\n\n```python\nfrom databricks.sdk import WorkspaceClient\n\nw = WorkspaceClient()\n\n# Create a standard endpoint\nendpoint = w.vector_search_endpoints.create_endpoint(\n    name=\"my-vs-endpoint\",\n    endpoint_type=\"STANDARD\"  # or \"STORAGE_OPTIMIZED\"\n)\n# Note: Endpoint creation is asynchronous; check status with get_endpoint()\n```\n\n### Create Delta Sync Index (Managed Embeddings)\n\n```python\n# Source table must have: primary key column + text column\nindex = w.vector_search_indexes.create_index(\n    name=\"catalog.schema.my_index\",\n    endpoint_name=\"my-vs-endpoint\",\n    primary_key=\"id\",\n    index_type=\"DELTA_SYNC\",\n    delta_sync_index_spec={\n        \"source_table\": \"catalog.schema.documents\",\n        \"embedding_source_columns\": [\n            {\n                \"name\": \"content\",  # Text column to embed\n                \"embedding_model_endpoint_name\": \"databricks-gte-large-en\"\n            }\n        ],\n        \"pipeline_type\": \"TRIGGERED\"  # or \"CONTINUOUS\"\n    }\n)\n```\n\n### Query Index\n\n```python\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"content\", \"metadata\"],\n    query_text=\"What is machine learning?\",\n    num_results=5\n)\n\nfor doc in results.result.data_array:\n    score = doc[-1]  # Similarity score is last column\n    print(f\"Score: {score}, Content: {doc[1][:100]}...\")\n```\n\n## Common Patterns\n\n### Create Storage-Optimized Endpoint\n\n```python\n# For large-scale, cost-effective deployments\nendpoint = w.vector_search_endpoints.create_endpoint(\n    name=\"my-storage-endpoint\",\n    endpoint_type=\"STORAGE_OPTIMIZED\"\n)\n```\n\n### Delta Sync with Self-Managed Embeddings\n\n```python\n# Source table must have: primary key + embedding vector column\nindex = w.vector_search_indexes.create_index(\n    name=\"catalog.schema.my_index\",\n    endpoint_name=\"my-vs-endpoint\",\n    primary_key=\"id\",\n    index_type=\"DELTA_SYNC\",\n    delta_sync_index_spec={\n        \"source_table\": \"catalog.schema.documents\",\n        \"embedding_vector_columns\": [\n            {\n                \"name\": \"embedding\",  # Pre-computed embedding column\n                \"embedding_dimension\": 768\n            }\n        ],\n        \"pipeline_type\": \"TRIGGERED\"\n    }\n)\n```\n\n### Direct Access Index\n\n```python\nimport json\n\n# Create index for manual CRUD\nindex = w.vector_search_indexes.create_index(\n    name=\"catalog.schema.direct_index\",\n    endpoint_name=\"my-vs-endpoint\",\n    primary_key=\"id\",\n    index_type=\"DIRECT_ACCESS\",\n    direct_access_index_spec={\n        \"embedding_vector_columns\": [\n            {\"name\": \"embedding\", \"embedding_dimension\": 768}\n        ],\n        \"schema_json\": json.dumps({\n            \"id\": \"string\",\n            \"text\": \"string\",\n            \"embedding\": \"array\u003Cfloat>\",\n            \"metadata\": \"string\"\n        })\n    }\n)\n\n# Upsert data\nw.vector_search_indexes.upsert_data_vector_index(\n    index_name=\"catalog.schema.direct_index\",\n    inputs_json=json.dumps([\n        {\"id\": \"1\", \"text\": \"Hello\", \"embedding\": [0.1, 0.2, ...], \"metadata\": \"doc1\"},\n        {\"id\": \"2\", \"text\": \"World\", \"embedding\": [0.3, 0.4, ...], \"metadata\": \"doc2\"},\n    ])\n)\n\n# Delete data\nw.vector_search_indexes.delete_data_vector_index(\n    index_name=\"catalog.schema.direct_index\",\n    primary_keys=[\"1\", \"2\"]\n)\n```\n\n### Query with Embedding Vector\n\n```python\n# When you have pre-computed query embedding\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"text\"],\n    query_vector=[0.1, 0.2, 0.3, ...],  # Your 768-dim vector\n    num_results=10\n)\n```\n\n### Hybrid Search (Semantic + Keyword)\n\nHybrid search combines vector similarity (ANN) with BM25 keyword scoring. Use it when queries contain exact terms that must match — SKUs, error codes, proper nouns, or technical terminology — where pure semantic search might miss keyword-specific results. See [references\u002Fsearch-modes.md](references\u002Fsearch-modes.md) for detailed guidance on choosing between ANN and hybrid search.\n\n```python\n# Combines vector similarity with keyword matching\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"content\"],\n    query_text=\"SPARK-12345 executor memory error\",\n    query_type=\"HYBRID\",\n    num_results=10\n)\n```\n\n## Filtering\n\n### Standard Endpoint Filters (Dictionary)\n\n```python\n# filters_json uses dictionary format\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"content\"],\n    query_text=\"machine learning\",\n    num_results=10,\n    filters_json='{\"category\": \"ai\", \"status\": [\"active\", \"pending\"]}'\n)\n```\n\n### Storage-Optimized Filters (SQL-like)\n\nStorage-Optimized endpoints use SQL-like filter syntax via the `databricks-vectorsearch` package's `filters` parameter (accepts a string):\n\n```python\nfrom databricks.vector_search.client import VectorSearchClient\n\nvsc = VectorSearchClient()\nindex = vsc.get_index(endpoint_name=\"my-storage-endpoint\", index_name=\"catalog.schema.my_index\")\n\n# SQL-like filter syntax for storage-optimized endpoints\nresults = index.similarity_search(\n    query_text=\"machine learning\",\n    columns=[\"id\", \"content\"],\n    num_results=10,\n    filters=\"category = 'ai' AND status IN ('active', 'pending')\"\n)\n\n# More filter examples\n# filters=\"price > 100 AND price \u003C 500\"\n# filters=\"department LIKE 'eng%'\"\n# filters=\"created_at >= '2024-01-01'\"\n```\n\n### Trigger Index Sync\n\n```python\n# For TRIGGERED pipeline type, manually sync\nw.vector_search_indexes.sync_index(\n    index_name=\"catalog.schema.my_index\"\n)\n```\n\n### Scan All Index Entries\n\n```python\n# Retrieve all vectors (for debugging\u002Fexport)\nscan_result = w.vector_search_indexes.scan_index(\n    index_name=\"catalog.schema.my_index\",\n    num_results=100\n)\n```\n\n## Reference Files\n\n| Topic | File | Description |\n|-------|------|-------------|\n| Index Types | [references\u002Findex-types.md](references\u002Findex-types.md) | Detailed comparison of Delta Sync (managed\u002Fself-managed) vs Direct Access |\n| End-to-End RAG | [references\u002Fend-to-end-rag.md](references\u002Fend-to-end-rag.md) | Complete walkthrough: source table → endpoint → index → query → agent integration |\n| Search Modes | [references\u002Fsearch-modes.md](references\u002Fsearch-modes.md) | When to use semantic (ANN) vs hybrid search, decision guide |\n| Operations | [references\u002Ftroubleshooting-and-operations.md](references\u002Ftroubleshooting-and-operations.md) | Monitoring, cost optimization, capacity planning, migration |\n\n## CLI Quick Reference\n\n```bash\n# List endpoints\ndatabricks vector-search-endpoints list-endpoints\n\n# Create endpoint (positional args: NAME ENDPOINT_TYPE)\ndatabricks vector-search-endpoints create-endpoint my-endpoint STANDARD\n\n# List indexes on endpoint (positional arg: ENDPOINT_NAME)\ndatabricks vector-search-indexes list-indexes my-endpoint\n\n# Get index status (positional arg: INDEX_NAME)\ndatabricks vector-search-indexes get-index catalog.schema.my_index\n\n# Sync index (positional arg: INDEX_NAME)\ndatabricks vector-search-indexes sync-index catalog.schema.my_index\n\n# Delete index (positional arg: INDEX_NAME)\ndatabricks vector-search-indexes delete-index catalog.schema.my_index\n```\n\n## Common Issues\n\n| Issue | Solution |\n|-------|----------|\n| **Index sync slow** | Use Storage-Optimized endpoints (20x faster indexing) |\n| **Query latency high** | Use Standard endpoint for \u003C100ms latency |\n| **filters_json not working** | Storage-Optimized uses SQL-like string filters via `databricks-vectorsearch` package's `filters` parameter |\n| **Embedding dimension mismatch** | Ensure query and index dimensions match |\n| **Index not updating** | Check pipeline_type; use sync_index() for TRIGGERED |\n| **Out of capacity** | Upgrade to Storage-Optimized (1B+ vectors) |\n| **`query_vector` truncated** | Large vectors (e.g. 1024-dim) can be truncated when serialized as JSON. Use `query_text` instead (for managed embedding indexes), or use the Databricks SDK to pass raw vectors |\n\n## Embedding Models\n\nDatabricks provides built-in embedding models:\n\n| Model | Dimensions | Context Window | Use Case |\n|-------|------------|----------------|----------|\n| `databricks-gte-large-en` | 1024 | 8192 tokens | English text, high quality |\n| `databricks-bge-large-en` | 1024 | 512 tokens | English text, general purpose |\n\n```python\n# Use with managed embeddings\nembedding_source_columns=[\n    {\n        \"name\": \"content\",\n        \"embedding_model_endpoint_name\": \"databricks-gte-large-en\"\n    }\n]\n```\n\n## Notes\n\n- **Storage-Optimized is newer** — better for most use cases unless you need \u003C100ms latency\n- **Delta Sync recommended** — easier than Direct Access for most scenarios\n- **Hybrid search** — available for both Delta Sync and Direct Access indexes\n- **`columns_to_sync` matters** — only synced columns are available in query results; include all columns you need\n- **Filter syntax differs by endpoint** — Standard uses dict-format filters, Storage-Optimized uses SQL-like string filters. Use the `databricks-vectorsearch` package's `filters` parameter which accepts both formats\n- **Management vs runtime** — CLI and SDK handle lifecycle management; for agent tool-calling at runtime, use `VectorSearchRetrieverTool`\n\n## Related Skills\n\n- **databricks-model-serving** - Deploy agents that use VectorSearchRetrieverTool\n- **[databricks-agent-bricks](..\u002Fdatabricks-agent-bricks\u002FSKILL.md)** - Knowledge Assistants use RAG over indexed documents\n- **[databricks-unstructured-pdf-generation](..\u002Fdatabricks-unstructured-pdf-generation\u002FSKILL.md)** - Generate documents to index in Vector Search\n- **[databricks-unity-catalog](..\u002Fdatabricks-unity-catalog\u002FSKILL.md)** - Manage the catalogs and tables that back Delta Sync indexes\n- **databricks-pipelines** - Build Delta tables used as Vector Search sources\n",{"data":34,"body":38},{"name":4,"description":6,"metadata":35,"parent":37},{"version":36},"0.1.0","databricks-core",{"type":39,"children":40},"root",[41,49,69,74,81,86,116,122,127,219,225,324,330,436,442,449,552,558,707,713,798,804,810,855,861,992,998,1290,1296,1356,1362,1375,1442,1448,1454,1521,1527,1548,1684,1690,1728,1734,1779,1785,1893,1899,2120,2126,2287,2293,2298,2382,2444,2450,2538,2544,2609],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Databricks Vector Search",{"type":42,"tag":50,"props":51,"children":52},"p",{},[53,59,61,67],{"type":42,"tag":54,"props":55,"children":56},"strong",{},[57],{"type":47,"value":58},"FIRST",{"type":47,"value":60},": Use the parent ",{"type":42,"tag":62,"props":63,"children":65},"code",{"className":64},[],[66],{"type":47,"value":37},{"type":47,"value":68}," skill for CLI basics, authentication, and profile selection.",{"type":42,"tag":50,"props":70,"children":71},{},[72],{"type":47,"value":73},"Patterns for creating, managing, and querying vector search indexes for RAG and semantic search applications.",{"type":42,"tag":75,"props":76,"children":78},"h2",{"id":77},"when-to-use",[79],{"type":47,"value":80},"When to Use",{"type":42,"tag":50,"props":82,"children":83},{},[84],{"type":47,"value":85},"Use this skill when:",{"type":42,"tag":87,"props":88,"children":89},"ul",{},[90,96,101,106,111],{"type":42,"tag":91,"props":92,"children":93},"li",{},[94],{"type":47,"value":95},"Building RAG (Retrieval-Augmented Generation) applications",{"type":42,"tag":91,"props":97,"children":98},{},[99],{"type":47,"value":100},"Implementing semantic search or similarity matching",{"type":42,"tag":91,"props":102,"children":103},{},[104],{"type":47,"value":105},"Creating vector indexes from Delta tables",{"type":42,"tag":91,"props":107,"children":108},{},[109],{"type":47,"value":110},"Choosing between storage-optimized and standard endpoints",{"type":42,"tag":91,"props":112,"children":113},{},[114],{"type":47,"value":115},"Querying vector indexes with filters",{"type":42,"tag":75,"props":117,"children":119},{"id":118},"overview",[120],{"type":47,"value":121},"Overview",{"type":42,"tag":50,"props":123,"children":124},{},[125],{"type":47,"value":126},"Databricks Vector Search provides managed vector similarity search with automatic embedding generation and Delta Lake integration.",{"type":42,"tag":128,"props":129,"children":130},"table",{},[131,150],{"type":42,"tag":132,"props":133,"children":134},"thead",{},[135],{"type":42,"tag":136,"props":137,"children":138},"tr",{},[139,145],{"type":42,"tag":140,"props":141,"children":142},"th",{},[143],{"type":47,"value":144},"Component",{"type":42,"tag":140,"props":146,"children":147},{},[148],{"type":47,"value":149},"Description",{"type":42,"tag":151,"props":152,"children":153},"tbody",{},[154,171,187,203],{"type":42,"tag":136,"props":155,"children":156},{},[157,166],{"type":42,"tag":158,"props":159,"children":160},"td",{},[161],{"type":42,"tag":54,"props":162,"children":163},{},[164],{"type":47,"value":165},"Endpoint",{"type":42,"tag":158,"props":167,"children":168},{},[169],{"type":47,"value":170},"Compute resource hosting indexes (Standard or Storage-Optimized)",{"type":42,"tag":136,"props":172,"children":173},{},[174,182],{"type":42,"tag":158,"props":175,"children":176},{},[177],{"type":42,"tag":54,"props":178,"children":179},{},[180],{"type":47,"value":181},"Index",{"type":42,"tag":158,"props":183,"children":184},{},[185],{"type":47,"value":186},"Vector data structure for similarity search",{"type":42,"tag":136,"props":188,"children":189},{},[190,198],{"type":42,"tag":158,"props":191,"children":192},{},[193],{"type":42,"tag":54,"props":194,"children":195},{},[196],{"type":47,"value":197},"Delta Sync",{"type":42,"tag":158,"props":199,"children":200},{},[201],{"type":47,"value":202},"Auto-syncs with source Delta table",{"type":42,"tag":136,"props":204,"children":205},{},[206,214],{"type":42,"tag":158,"props":207,"children":208},{},[209],{"type":42,"tag":54,"props":210,"children":211},{},[212],{"type":47,"value":213},"Direct Access",{"type":42,"tag":158,"props":215,"children":216},{},[217],{"type":47,"value":218},"Manual CRUD operations on vectors",{"type":42,"tag":75,"props":220,"children":222},{"id":221},"endpoint-types",[223],{"type":47,"value":224},"Endpoint Types",{"type":42,"tag":128,"props":226,"children":227},{},[228,259],{"type":42,"tag":132,"props":229,"children":230},{},[231],{"type":42,"tag":136,"props":232,"children":233},{},[234,239,244,249,254],{"type":42,"tag":140,"props":235,"children":236},{},[237],{"type":47,"value":238},"Type",{"type":42,"tag":140,"props":240,"children":241},{},[242],{"type":47,"value":243},"Latency",{"type":42,"tag":140,"props":245,"children":246},{},[247],{"type":47,"value":248},"Capacity",{"type":42,"tag":140,"props":250,"children":251},{},[252],{"type":47,"value":253},"Cost",{"type":42,"tag":140,"props":255,"children":256},{},[257],{"type":47,"value":258},"Best For",{"type":42,"tag":151,"props":260,"children":261},{},[262,293],{"type":42,"tag":136,"props":263,"children":264},{},[265,273,278,283,288],{"type":42,"tag":158,"props":266,"children":267},{},[268],{"type":42,"tag":54,"props":269,"children":270},{},[271],{"type":47,"value":272},"Standard",{"type":42,"tag":158,"props":274,"children":275},{},[276],{"type":47,"value":277},"20-50ms",{"type":42,"tag":158,"props":279,"children":280},{},[281],{"type":47,"value":282},"320M vectors (768 dim)",{"type":42,"tag":158,"props":284,"children":285},{},[286],{"type":47,"value":287},"Higher",{"type":42,"tag":158,"props":289,"children":290},{},[291],{"type":47,"value":292},"Real-time, low-latency",{"type":42,"tag":136,"props":294,"children":295},{},[296,304,309,314,319],{"type":42,"tag":158,"props":297,"children":298},{},[299],{"type":42,"tag":54,"props":300,"children":301},{},[302],{"type":47,"value":303},"Storage-Optimized",{"type":42,"tag":158,"props":305,"children":306},{},[307],{"type":47,"value":308},"300-500ms",{"type":42,"tag":158,"props":310,"children":311},{},[312],{"type":47,"value":313},"1B+ vectors (768 dim)",{"type":42,"tag":158,"props":315,"children":316},{},[317],{"type":47,"value":318},"7x lower",{"type":42,"tag":158,"props":320,"children":321},{},[322],{"type":47,"value":323},"Large-scale, cost-sensitive",{"type":42,"tag":75,"props":325,"children":327},{"id":326},"index-types",[328],{"type":47,"value":329},"Index Types",{"type":42,"tag":128,"props":331,"children":332},{},[333,358],{"type":42,"tag":132,"props":334,"children":335},{},[336],{"type":42,"tag":136,"props":337,"children":338},{},[339,343,348,353],{"type":42,"tag":140,"props":340,"children":341},{},[342],{"type":47,"value":238},{"type":42,"tag":140,"props":344,"children":345},{},[346],{"type":47,"value":347},"Embeddings",{"type":42,"tag":140,"props":349,"children":350},{},[351],{"type":47,"value":352},"Sync",{"type":42,"tag":140,"props":354,"children":355},{},[356],{"type":47,"value":357},"Use Case",{"type":42,"tag":151,"props":359,"children":360},{},[361,387,412],{"type":42,"tag":136,"props":362,"children":363},{},[364,372,377,382],{"type":42,"tag":158,"props":365,"children":366},{},[367],{"type":42,"tag":54,"props":368,"children":369},{},[370],{"type":47,"value":371},"Delta Sync (managed)",{"type":42,"tag":158,"props":373,"children":374},{},[375],{"type":47,"value":376},"Databricks computes",{"type":42,"tag":158,"props":378,"children":379},{},[380],{"type":47,"value":381},"Auto from Delta",{"type":42,"tag":158,"props":383,"children":384},{},[385],{"type":47,"value":386},"Easiest setup",{"type":42,"tag":136,"props":388,"children":389},{},[390,398,403,407],{"type":42,"tag":158,"props":391,"children":392},{},[393],{"type":42,"tag":54,"props":394,"children":395},{},[396],{"type":47,"value":397},"Delta Sync (self-managed)",{"type":42,"tag":158,"props":399,"children":400},{},[401],{"type":47,"value":402},"You provide",{"type":42,"tag":158,"props":404,"children":405},{},[406],{"type":47,"value":381},{"type":42,"tag":158,"props":408,"children":409},{},[410],{"type":47,"value":411},"Custom embeddings",{"type":42,"tag":136,"props":413,"children":414},{},[415,422,426,431],{"type":42,"tag":158,"props":416,"children":417},{},[418],{"type":42,"tag":54,"props":419,"children":420},{},[421],{"type":47,"value":213},{"type":42,"tag":158,"props":423,"children":424},{},[425],{"type":47,"value":402},{"type":42,"tag":158,"props":427,"children":428},{},[429],{"type":47,"value":430},"Manual CRUD",{"type":42,"tag":158,"props":432,"children":433},{},[434],{"type":47,"value":435},"Real-time updates",{"type":42,"tag":75,"props":437,"children":439},{"id":438},"quick-start",[440],{"type":47,"value":441},"Quick Start",{"type":42,"tag":443,"props":444,"children":446},"h3",{"id":445},"create-endpoint",[447],{"type":47,"value":448},"Create Endpoint",{"type":42,"tag":450,"props":451,"children":456},"pre",{"className":452,"code":453,"language":454,"meta":455,"style":455},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from databricks.sdk import WorkspaceClient\n\nw = WorkspaceClient()\n\n# Create a standard endpoint\nendpoint = w.vector_search_endpoints.create_endpoint(\n    name=\"my-vs-endpoint\",\n    endpoint_type=\"STANDARD\"  # or \"STORAGE_OPTIMIZED\"\n)\n# Note: Endpoint creation is asynchronous; check status with get_endpoint()\n","python","",[457],{"type":42,"tag":62,"props":458,"children":459},{"__ignoreMap":455},[460,471,481,490,498,507,516,525,534,543],{"type":42,"tag":461,"props":462,"children":465},"span",{"class":463,"line":464},"line",1,[466],{"type":42,"tag":461,"props":467,"children":468},{},[469],{"type":47,"value":470},"from databricks.sdk import WorkspaceClient\n",{"type":42,"tag":461,"props":472,"children":474},{"class":463,"line":473},2,[475],{"type":42,"tag":461,"props":476,"children":478},{"emptyLinePlaceholder":477},true,[479],{"type":47,"value":480},"\n",{"type":42,"tag":461,"props":482,"children":484},{"class":463,"line":483},3,[485],{"type":42,"tag":461,"props":486,"children":487},{},[488],{"type":47,"value":489},"w = WorkspaceClient()\n",{"type":42,"tag":461,"props":491,"children":493},{"class":463,"line":492},4,[494],{"type":42,"tag":461,"props":495,"children":496},{"emptyLinePlaceholder":477},[497],{"type":47,"value":480},{"type":42,"tag":461,"props":499,"children":501},{"class":463,"line":500},5,[502],{"type":42,"tag":461,"props":503,"children":504},{},[505],{"type":47,"value":506},"# Create a standard endpoint\n",{"type":42,"tag":461,"props":508,"children":510},{"class":463,"line":509},6,[511],{"type":42,"tag":461,"props":512,"children":513},{},[514],{"type":47,"value":515},"endpoint = w.vector_search_endpoints.create_endpoint(\n",{"type":42,"tag":461,"props":517,"children":519},{"class":463,"line":518},7,[520],{"type":42,"tag":461,"props":521,"children":522},{},[523],{"type":47,"value":524},"    name=\"my-vs-endpoint\",\n",{"type":42,"tag":461,"props":526,"children":528},{"class":463,"line":527},8,[529],{"type":42,"tag":461,"props":530,"children":531},{},[532],{"type":47,"value":533},"    endpoint_type=\"STANDARD\"  # or \"STORAGE_OPTIMIZED\"\n",{"type":42,"tag":461,"props":535,"children":537},{"class":463,"line":536},9,[538],{"type":42,"tag":461,"props":539,"children":540},{},[541],{"type":47,"value":542},")\n",{"type":42,"tag":461,"props":544,"children":546},{"class":463,"line":545},10,[547],{"type":42,"tag":461,"props":548,"children":549},{},[550],{"type":47,"value":551},"# Note: Endpoint creation is asynchronous; check status with get_endpoint()\n",{"type":42,"tag":443,"props":553,"children":555},{"id":554},"create-delta-sync-index-managed-embeddings",[556],{"type":47,"value":557},"Create Delta Sync Index (Managed Embeddings)",{"type":42,"tag":450,"props":559,"children":561},{"className":452,"code":560,"language":454,"meta":455,"style":455},"# Source table must have: primary key column + text column\nindex = w.vector_search_indexes.create_index(\n    name=\"catalog.schema.my_index\",\n    endpoint_name=\"my-vs-endpoint\",\n    primary_key=\"id\",\n    index_type=\"DELTA_SYNC\",\n    delta_sync_index_spec={\n        \"source_table\": \"catalog.schema.documents\",\n        \"embedding_source_columns\": [\n            {\n                \"name\": \"content\",  # Text column to embed\n                \"embedding_model_endpoint_name\": \"databricks-gte-large-en\"\n            }\n        ],\n        \"pipeline_type\": \"TRIGGERED\"  # or \"CONTINUOUS\"\n    }\n)\n",[562],{"type":42,"tag":62,"props":563,"children":564},{"__ignoreMap":455},[565,573,581,589,597,605,613,621,629,637,645,654,663,672,681,690,699],{"type":42,"tag":461,"props":566,"children":567},{"class":463,"line":464},[568],{"type":42,"tag":461,"props":569,"children":570},{},[571],{"type":47,"value":572},"# Source table must have: primary key column + text column\n",{"type":42,"tag":461,"props":574,"children":575},{"class":463,"line":473},[576],{"type":42,"tag":461,"props":577,"children":578},{},[579],{"type":47,"value":580},"index = w.vector_search_indexes.create_index(\n",{"type":42,"tag":461,"props":582,"children":583},{"class":463,"line":483},[584],{"type":42,"tag":461,"props":585,"children":586},{},[587],{"type":47,"value":588},"    name=\"catalog.schema.my_index\",\n",{"type":42,"tag":461,"props":590,"children":591},{"class":463,"line":492},[592],{"type":42,"tag":461,"props":593,"children":594},{},[595],{"type":47,"value":596},"    endpoint_name=\"my-vs-endpoint\",\n",{"type":42,"tag":461,"props":598,"children":599},{"class":463,"line":500},[600],{"type":42,"tag":461,"props":601,"children":602},{},[603],{"type":47,"value":604},"    primary_key=\"id\",\n",{"type":42,"tag":461,"props":606,"children":607},{"class":463,"line":509},[608],{"type":42,"tag":461,"props":609,"children":610},{},[611],{"type":47,"value":612},"    index_type=\"DELTA_SYNC\",\n",{"type":42,"tag":461,"props":614,"children":615},{"class":463,"line":518},[616],{"type":42,"tag":461,"props":617,"children":618},{},[619],{"type":47,"value":620},"    delta_sync_index_spec={\n",{"type":42,"tag":461,"props":622,"children":623},{"class":463,"line":527},[624],{"type":42,"tag":461,"props":625,"children":626},{},[627],{"type":47,"value":628},"        \"source_table\": \"catalog.schema.documents\",\n",{"type":42,"tag":461,"props":630,"children":631},{"class":463,"line":536},[632],{"type":42,"tag":461,"props":633,"children":634},{},[635],{"type":47,"value":636},"        \"embedding_source_columns\": [\n",{"type":42,"tag":461,"props":638,"children":639},{"class":463,"line":545},[640],{"type":42,"tag":461,"props":641,"children":642},{},[643],{"type":47,"value":644},"            {\n",{"type":42,"tag":461,"props":646,"children":648},{"class":463,"line":647},11,[649],{"type":42,"tag":461,"props":650,"children":651},{},[652],{"type":47,"value":653},"                \"name\": \"content\",  # Text column to embed\n",{"type":42,"tag":461,"props":655,"children":657},{"class":463,"line":656},12,[658],{"type":42,"tag":461,"props":659,"children":660},{},[661],{"type":47,"value":662},"                \"embedding_model_endpoint_name\": \"databricks-gte-large-en\"\n",{"type":42,"tag":461,"props":664,"children":666},{"class":463,"line":665},13,[667],{"type":42,"tag":461,"props":668,"children":669},{},[670],{"type":47,"value":671},"            }\n",{"type":42,"tag":461,"props":673,"children":675},{"class":463,"line":674},14,[676],{"type":42,"tag":461,"props":677,"children":678},{},[679],{"type":47,"value":680},"        ],\n",{"type":42,"tag":461,"props":682,"children":684},{"class":463,"line":683},15,[685],{"type":42,"tag":461,"props":686,"children":687},{},[688],{"type":47,"value":689},"        \"pipeline_type\": \"TRIGGERED\"  # or \"CONTINUOUS\"\n",{"type":42,"tag":461,"props":691,"children":693},{"class":463,"line":692},16,[694],{"type":42,"tag":461,"props":695,"children":696},{},[697],{"type":47,"value":698},"    }\n",{"type":42,"tag":461,"props":700,"children":702},{"class":463,"line":701},17,[703],{"type":42,"tag":461,"props":704,"children":705},{},[706],{"type":47,"value":542},{"type":42,"tag":443,"props":708,"children":710},{"id":709},"query-index",[711],{"type":47,"value":712},"Query Index",{"type":42,"tag":450,"props":714,"children":716},{"className":452,"code":715,"language":454,"meta":455,"style":455},"results = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"content\", \"metadata\"],\n    query_text=\"What is machine learning?\",\n    num_results=5\n)\n\nfor doc in results.result.data_array:\n    score = doc[-1]  # Similarity score is last column\n    print(f\"Score: {score}, Content: {doc[1][:100]}...\")\n",[717],{"type":42,"tag":62,"props":718,"children":719},{"__ignoreMap":455},[720,728,736,744,752,760,767,774,782,790],{"type":42,"tag":461,"props":721,"children":722},{"class":463,"line":464},[723],{"type":42,"tag":461,"props":724,"children":725},{},[726],{"type":47,"value":727},"results = w.vector_search_indexes.query_index(\n",{"type":42,"tag":461,"props":729,"children":730},{"class":463,"line":473},[731],{"type":42,"tag":461,"props":732,"children":733},{},[734],{"type":47,"value":735},"    index_name=\"catalog.schema.my_index\",\n",{"type":42,"tag":461,"props":737,"children":738},{"class":463,"line":483},[739],{"type":42,"tag":461,"props":740,"children":741},{},[742],{"type":47,"value":743},"    columns=[\"id\", \"content\", \"metadata\"],\n",{"type":42,"tag":461,"props":745,"children":746},{"class":463,"line":492},[747],{"type":42,"tag":461,"props":748,"children":749},{},[750],{"type":47,"value":751},"    query_text=\"What is machine learning?\",\n",{"type":42,"tag":461,"props":753,"children":754},{"class":463,"line":500},[755],{"type":42,"tag":461,"props":756,"children":757},{},[758],{"type":47,"value":759},"    num_results=5\n",{"type":42,"tag":461,"props":761,"children":762},{"class":463,"line":509},[763],{"type":42,"tag":461,"props":764,"children":765},{},[766],{"type":47,"value":542},{"type":42,"tag":461,"props":768,"children":769},{"class":463,"line":518},[770],{"type":42,"tag":461,"props":771,"children":772},{"emptyLinePlaceholder":477},[773],{"type":47,"value":480},{"type":42,"tag":461,"props":775,"children":776},{"class":463,"line":527},[777],{"type":42,"tag":461,"props":778,"children":779},{},[780],{"type":47,"value":781},"for doc in results.result.data_array:\n",{"type":42,"tag":461,"props":783,"children":784},{"class":463,"line":536},[785],{"type":42,"tag":461,"props":786,"children":787},{},[788],{"type":47,"value":789},"    score = doc[-1]  # Similarity score is last column\n",{"type":42,"tag":461,"props":791,"children":792},{"class":463,"line":545},[793],{"type":42,"tag":461,"props":794,"children":795},{},[796],{"type":47,"value":797},"    print(f\"Score: {score}, Content: {doc[1][:100]}...\")\n",{"type":42,"tag":75,"props":799,"children":801},{"id":800},"common-patterns",[802],{"type":47,"value":803},"Common Patterns",{"type":42,"tag":443,"props":805,"children":807},{"id":806},"create-storage-optimized-endpoint",[808],{"type":47,"value":809},"Create Storage-Optimized Endpoint",{"type":42,"tag":450,"props":811,"children":813},{"className":452,"code":812,"language":454,"meta":455,"style":455},"# For large-scale, cost-effective deployments\nendpoint = w.vector_search_endpoints.create_endpoint(\n    name=\"my-storage-endpoint\",\n    endpoint_type=\"STORAGE_OPTIMIZED\"\n)\n",[814],{"type":42,"tag":62,"props":815,"children":816},{"__ignoreMap":455},[817,825,832,840,848],{"type":42,"tag":461,"props":818,"children":819},{"class":463,"line":464},[820],{"type":42,"tag":461,"props":821,"children":822},{},[823],{"type":47,"value":824},"# For large-scale, cost-effective deployments\n",{"type":42,"tag":461,"props":826,"children":827},{"class":463,"line":473},[828],{"type":42,"tag":461,"props":829,"children":830},{},[831],{"type":47,"value":515},{"type":42,"tag":461,"props":833,"children":834},{"class":463,"line":483},[835],{"type":42,"tag":461,"props":836,"children":837},{},[838],{"type":47,"value":839},"    name=\"my-storage-endpoint\",\n",{"type":42,"tag":461,"props":841,"children":842},{"class":463,"line":492},[843],{"type":42,"tag":461,"props":844,"children":845},{},[846],{"type":47,"value":847},"    endpoint_type=\"STORAGE_OPTIMIZED\"\n",{"type":42,"tag":461,"props":849,"children":850},{"class":463,"line":500},[851],{"type":42,"tag":461,"props":852,"children":853},{},[854],{"type":47,"value":542},{"type":42,"tag":443,"props":856,"children":858},{"id":857},"delta-sync-with-self-managed-embeddings",[859],{"type":47,"value":860},"Delta Sync with Self-Managed Embeddings",{"type":42,"tag":450,"props":862,"children":864},{"className":452,"code":863,"language":454,"meta":455,"style":455},"# Source table must have: primary key + embedding vector column\nindex = w.vector_search_indexes.create_index(\n    name=\"catalog.schema.my_index\",\n    endpoint_name=\"my-vs-endpoint\",\n    primary_key=\"id\",\n    index_type=\"DELTA_SYNC\",\n    delta_sync_index_spec={\n        \"source_table\": \"catalog.schema.documents\",\n        \"embedding_vector_columns\": [\n            {\n                \"name\": \"embedding\",  # Pre-computed embedding column\n                \"embedding_dimension\": 768\n            }\n        ],\n        \"pipeline_type\": \"TRIGGERED\"\n    }\n)\n",[865],{"type":42,"tag":62,"props":866,"children":867},{"__ignoreMap":455},[868,876,883,890,897,904,911,918,925,933,940,948,956,963,970,978,985],{"type":42,"tag":461,"props":869,"children":870},{"class":463,"line":464},[871],{"type":42,"tag":461,"props":872,"children":873},{},[874],{"type":47,"value":875},"# Source table must have: primary key + embedding vector column\n",{"type":42,"tag":461,"props":877,"children":878},{"class":463,"line":473},[879],{"type":42,"tag":461,"props":880,"children":881},{},[882],{"type":47,"value":580},{"type":42,"tag":461,"props":884,"children":885},{"class":463,"line":483},[886],{"type":42,"tag":461,"props":887,"children":888},{},[889],{"type":47,"value":588},{"type":42,"tag":461,"props":891,"children":892},{"class":463,"line":492},[893],{"type":42,"tag":461,"props":894,"children":895},{},[896],{"type":47,"value":596},{"type":42,"tag":461,"props":898,"children":899},{"class":463,"line":500},[900],{"type":42,"tag":461,"props":901,"children":902},{},[903],{"type":47,"value":604},{"type":42,"tag":461,"props":905,"children":906},{"class":463,"line":509},[907],{"type":42,"tag":461,"props":908,"children":909},{},[910],{"type":47,"value":612},{"type":42,"tag":461,"props":912,"children":913},{"class":463,"line":518},[914],{"type":42,"tag":461,"props":915,"children":916},{},[917],{"type":47,"value":620},{"type":42,"tag":461,"props":919,"children":920},{"class":463,"line":527},[921],{"type":42,"tag":461,"props":922,"children":923},{},[924],{"type":47,"value":628},{"type":42,"tag":461,"props":926,"children":927},{"class":463,"line":536},[928],{"type":42,"tag":461,"props":929,"children":930},{},[931],{"type":47,"value":932},"        \"embedding_vector_columns\": [\n",{"type":42,"tag":461,"props":934,"children":935},{"class":463,"line":545},[936],{"type":42,"tag":461,"props":937,"children":938},{},[939],{"type":47,"value":644},{"type":42,"tag":461,"props":941,"children":942},{"class":463,"line":647},[943],{"type":42,"tag":461,"props":944,"children":945},{},[946],{"type":47,"value":947},"                \"name\": \"embedding\",  # Pre-computed embedding column\n",{"type":42,"tag":461,"props":949,"children":950},{"class":463,"line":656},[951],{"type":42,"tag":461,"props":952,"children":953},{},[954],{"type":47,"value":955},"                \"embedding_dimension\": 768\n",{"type":42,"tag":461,"props":957,"children":958},{"class":463,"line":665},[959],{"type":42,"tag":461,"props":960,"children":961},{},[962],{"type":47,"value":671},{"type":42,"tag":461,"props":964,"children":965},{"class":463,"line":674},[966],{"type":42,"tag":461,"props":967,"children":968},{},[969],{"type":47,"value":680},{"type":42,"tag":461,"props":971,"children":972},{"class":463,"line":683},[973],{"type":42,"tag":461,"props":974,"children":975},{},[976],{"type":47,"value":977},"        \"pipeline_type\": \"TRIGGERED\"\n",{"type":42,"tag":461,"props":979,"children":980},{"class":463,"line":692},[981],{"type":42,"tag":461,"props":982,"children":983},{},[984],{"type":47,"value":698},{"type":42,"tag":461,"props":986,"children":987},{"class":463,"line":701},[988],{"type":42,"tag":461,"props":989,"children":990},{},[991],{"type":47,"value":542},{"type":42,"tag":443,"props":993,"children":995},{"id":994},"direct-access-index",[996],{"type":47,"value":997},"Direct Access Index",{"type":42,"tag":450,"props":999,"children":1001},{"className":452,"code":1000,"language":454,"meta":455,"style":455},"import json\n\n# Create index for manual CRUD\nindex = w.vector_search_indexes.create_index(\n    name=\"catalog.schema.direct_index\",\n    endpoint_name=\"my-vs-endpoint\",\n    primary_key=\"id\",\n    index_type=\"DIRECT_ACCESS\",\n    direct_access_index_spec={\n        \"embedding_vector_columns\": [\n            {\"name\": \"embedding\", \"embedding_dimension\": 768}\n        ],\n        \"schema_json\": json.dumps({\n            \"id\": \"string\",\n            \"text\": \"string\",\n            \"embedding\": \"array\u003Cfloat>\",\n            \"metadata\": \"string\"\n        })\n    }\n)\n\n# Upsert data\nw.vector_search_indexes.upsert_data_vector_index(\n    index_name=\"catalog.schema.direct_index\",\n    inputs_json=json.dumps([\n        {\"id\": \"1\", \"text\": \"Hello\", \"embedding\": [0.1, 0.2, ...], \"metadata\": \"doc1\"},\n        {\"id\": \"2\", \"text\": \"World\", \"embedding\": [0.3, 0.4, ...], \"metadata\": \"doc2\"},\n    ])\n)\n\n# Delete data\nw.vector_search_indexes.delete_data_vector_index(\n    index_name=\"catalog.schema.direct_index\",\n    primary_keys=[\"1\", \"2\"]\n)\n",[1002],{"type":42,"tag":62,"props":1003,"children":1004},{"__ignoreMap":455},[1005,1013,1020,1028,1035,1043,1050,1057,1065,1073,1080,1088,1095,1103,1111,1119,1127,1135,1144,1152,1160,1168,1177,1186,1195,1204,1213,1222,1231,1239,1247,1256,1265,1273,1282],{"type":42,"tag":461,"props":1006,"children":1007},{"class":463,"line":464},[1008],{"type":42,"tag":461,"props":1009,"children":1010},{},[1011],{"type":47,"value":1012},"import json\n",{"type":42,"tag":461,"props":1014,"children":1015},{"class":463,"line":473},[1016],{"type":42,"tag":461,"props":1017,"children":1018},{"emptyLinePlaceholder":477},[1019],{"type":47,"value":480},{"type":42,"tag":461,"props":1021,"children":1022},{"class":463,"line":483},[1023],{"type":42,"tag":461,"props":1024,"children":1025},{},[1026],{"type":47,"value":1027},"# Create index for manual CRUD\n",{"type":42,"tag":461,"props":1029,"children":1030},{"class":463,"line":492},[1031],{"type":42,"tag":461,"props":1032,"children":1033},{},[1034],{"type":47,"value":580},{"type":42,"tag":461,"props":1036,"children":1037},{"class":463,"line":500},[1038],{"type":42,"tag":461,"props":1039,"children":1040},{},[1041],{"type":47,"value":1042},"    name=\"catalog.schema.direct_index\",\n",{"type":42,"tag":461,"props":1044,"children":1045},{"class":463,"line":509},[1046],{"type":42,"tag":461,"props":1047,"children":1048},{},[1049],{"type":47,"value":596},{"type":42,"tag":461,"props":1051,"children":1052},{"class":463,"line":518},[1053],{"type":42,"tag":461,"props":1054,"children":1055},{},[1056],{"type":47,"value":604},{"type":42,"tag":461,"props":1058,"children":1059},{"class":463,"line":527},[1060],{"type":42,"tag":461,"props":1061,"children":1062},{},[1063],{"type":47,"value":1064},"    index_type=\"DIRECT_ACCESS\",\n",{"type":42,"tag":461,"props":1066,"children":1067},{"class":463,"line":536},[1068],{"type":42,"tag":461,"props":1069,"children":1070},{},[1071],{"type":47,"value":1072},"    direct_access_index_spec={\n",{"type":42,"tag":461,"props":1074,"children":1075},{"class":463,"line":545},[1076],{"type":42,"tag":461,"props":1077,"children":1078},{},[1079],{"type":47,"value":932},{"type":42,"tag":461,"props":1081,"children":1082},{"class":463,"line":647},[1083],{"type":42,"tag":461,"props":1084,"children":1085},{},[1086],{"type":47,"value":1087},"            {\"name\": \"embedding\", \"embedding_dimension\": 768}\n",{"type":42,"tag":461,"props":1089,"children":1090},{"class":463,"line":656},[1091],{"type":42,"tag":461,"props":1092,"children":1093},{},[1094],{"type":47,"value":680},{"type":42,"tag":461,"props":1096,"children":1097},{"class":463,"line":665},[1098],{"type":42,"tag":461,"props":1099,"children":1100},{},[1101],{"type":47,"value":1102},"        \"schema_json\": json.dumps({\n",{"type":42,"tag":461,"props":1104,"children":1105},{"class":463,"line":674},[1106],{"type":42,"tag":461,"props":1107,"children":1108},{},[1109],{"type":47,"value":1110},"            \"id\": \"string\",\n",{"type":42,"tag":461,"props":1112,"children":1113},{"class":463,"line":683},[1114],{"type":42,"tag":461,"props":1115,"children":1116},{},[1117],{"type":47,"value":1118},"            \"text\": \"string\",\n",{"type":42,"tag":461,"props":1120,"children":1121},{"class":463,"line":692},[1122],{"type":42,"tag":461,"props":1123,"children":1124},{},[1125],{"type":47,"value":1126},"            \"embedding\": \"array\u003Cfloat>\",\n",{"type":42,"tag":461,"props":1128,"children":1129},{"class":463,"line":701},[1130],{"type":42,"tag":461,"props":1131,"children":1132},{},[1133],{"type":47,"value":1134},"            \"metadata\": \"string\"\n",{"type":42,"tag":461,"props":1136,"children":1138},{"class":463,"line":1137},18,[1139],{"type":42,"tag":461,"props":1140,"children":1141},{},[1142],{"type":47,"value":1143},"        })\n",{"type":42,"tag":461,"props":1145,"children":1147},{"class":463,"line":1146},19,[1148],{"type":42,"tag":461,"props":1149,"children":1150},{},[1151],{"type":47,"value":698},{"type":42,"tag":461,"props":1153,"children":1155},{"class":463,"line":1154},20,[1156],{"type":42,"tag":461,"props":1157,"children":1158},{},[1159],{"type":47,"value":542},{"type":42,"tag":461,"props":1161,"children":1163},{"class":463,"line":1162},21,[1164],{"type":42,"tag":461,"props":1165,"children":1166},{"emptyLinePlaceholder":477},[1167],{"type":47,"value":480},{"type":42,"tag":461,"props":1169,"children":1171},{"class":463,"line":1170},22,[1172],{"type":42,"tag":461,"props":1173,"children":1174},{},[1175],{"type":47,"value":1176},"# Upsert data\n",{"type":42,"tag":461,"props":1178,"children":1180},{"class":463,"line":1179},23,[1181],{"type":42,"tag":461,"props":1182,"children":1183},{},[1184],{"type":47,"value":1185},"w.vector_search_indexes.upsert_data_vector_index(\n",{"type":42,"tag":461,"props":1187,"children":1189},{"class":463,"line":1188},24,[1190],{"type":42,"tag":461,"props":1191,"children":1192},{},[1193],{"type":47,"value":1194},"    index_name=\"catalog.schema.direct_index\",\n",{"type":42,"tag":461,"props":1196,"children":1198},{"class":463,"line":1197},25,[1199],{"type":42,"tag":461,"props":1200,"children":1201},{},[1202],{"type":47,"value":1203},"    inputs_json=json.dumps([\n",{"type":42,"tag":461,"props":1205,"children":1207},{"class":463,"line":1206},26,[1208],{"type":42,"tag":461,"props":1209,"children":1210},{},[1211],{"type":47,"value":1212},"        {\"id\": \"1\", \"text\": \"Hello\", \"embedding\": [0.1, 0.2, ...], \"metadata\": \"doc1\"},\n",{"type":42,"tag":461,"props":1214,"children":1216},{"class":463,"line":1215},27,[1217],{"type":42,"tag":461,"props":1218,"children":1219},{},[1220],{"type":47,"value":1221},"        {\"id\": \"2\", \"text\": \"World\", \"embedding\": [0.3, 0.4, ...], \"metadata\": \"doc2\"},\n",{"type":42,"tag":461,"props":1223,"children":1225},{"class":463,"line":1224},28,[1226],{"type":42,"tag":461,"props":1227,"children":1228},{},[1229],{"type":47,"value":1230},"    ])\n",{"type":42,"tag":461,"props":1232,"children":1234},{"class":463,"line":1233},29,[1235],{"type":42,"tag":461,"props":1236,"children":1237},{},[1238],{"type":47,"value":542},{"type":42,"tag":461,"props":1240,"children":1242},{"class":463,"line":1241},30,[1243],{"type":42,"tag":461,"props":1244,"children":1245},{"emptyLinePlaceholder":477},[1246],{"type":47,"value":480},{"type":42,"tag":461,"props":1248,"children":1250},{"class":463,"line":1249},31,[1251],{"type":42,"tag":461,"props":1252,"children":1253},{},[1254],{"type":47,"value":1255},"# Delete data\n",{"type":42,"tag":461,"props":1257,"children":1259},{"class":463,"line":1258},32,[1260],{"type":42,"tag":461,"props":1261,"children":1262},{},[1263],{"type":47,"value":1264},"w.vector_search_indexes.delete_data_vector_index(\n",{"type":42,"tag":461,"props":1266,"children":1268},{"class":463,"line":1267},33,[1269],{"type":42,"tag":461,"props":1270,"children":1271},{},[1272],{"type":47,"value":1194},{"type":42,"tag":461,"props":1274,"children":1276},{"class":463,"line":1275},34,[1277],{"type":42,"tag":461,"props":1278,"children":1279},{},[1280],{"type":47,"value":1281},"    primary_keys=[\"1\", \"2\"]\n",{"type":42,"tag":461,"props":1283,"children":1285},{"class":463,"line":1284},35,[1286],{"type":42,"tag":461,"props":1287,"children":1288},{},[1289],{"type":47,"value":542},{"type":42,"tag":443,"props":1291,"children":1293},{"id":1292},"query-with-embedding-vector",[1294],{"type":47,"value":1295},"Query with Embedding Vector",{"type":42,"tag":450,"props":1297,"children":1299},{"className":452,"code":1298,"language":454,"meta":455,"style":455},"# When you have pre-computed query embedding\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"text\"],\n    query_vector=[0.1, 0.2, 0.3, ...],  # Your 768-dim vector\n    num_results=10\n)\n",[1300],{"type":42,"tag":62,"props":1301,"children":1302},{"__ignoreMap":455},[1303,1311,1318,1325,1333,1341,1349],{"type":42,"tag":461,"props":1304,"children":1305},{"class":463,"line":464},[1306],{"type":42,"tag":461,"props":1307,"children":1308},{},[1309],{"type":47,"value":1310},"# When you have pre-computed query embedding\n",{"type":42,"tag":461,"props":1312,"children":1313},{"class":463,"line":473},[1314],{"type":42,"tag":461,"props":1315,"children":1316},{},[1317],{"type":47,"value":727},{"type":42,"tag":461,"props":1319,"children":1320},{"class":463,"line":483},[1321],{"type":42,"tag":461,"props":1322,"children":1323},{},[1324],{"type":47,"value":735},{"type":42,"tag":461,"props":1326,"children":1327},{"class":463,"line":492},[1328],{"type":42,"tag":461,"props":1329,"children":1330},{},[1331],{"type":47,"value":1332},"    columns=[\"id\", \"text\"],\n",{"type":42,"tag":461,"props":1334,"children":1335},{"class":463,"line":500},[1336],{"type":42,"tag":461,"props":1337,"children":1338},{},[1339],{"type":47,"value":1340},"    query_vector=[0.1, 0.2, 0.3, ...],  # Your 768-dim vector\n",{"type":42,"tag":461,"props":1342,"children":1343},{"class":463,"line":509},[1344],{"type":42,"tag":461,"props":1345,"children":1346},{},[1347],{"type":47,"value":1348},"    num_results=10\n",{"type":42,"tag":461,"props":1350,"children":1351},{"class":463,"line":518},[1352],{"type":42,"tag":461,"props":1353,"children":1354},{},[1355],{"type":47,"value":542},{"type":42,"tag":443,"props":1357,"children":1359},{"id":1358},"hybrid-search-semantic-keyword",[1360],{"type":47,"value":1361},"Hybrid Search (Semantic + Keyword)",{"type":42,"tag":50,"props":1363,"children":1364},{},[1365,1367,1373],{"type":47,"value":1366},"Hybrid search combines vector similarity (ANN) with BM25 keyword scoring. Use it when queries contain exact terms that must match — SKUs, error codes, proper nouns, or technical terminology — where pure semantic search might miss keyword-specific results. See ",{"type":42,"tag":1368,"props":1369,"children":1371},"a",{"href":1370},"references\u002Fsearch-modes.md",[1372],{"type":47,"value":1370},{"type":47,"value":1374}," for detailed guidance on choosing between ANN and hybrid search.",{"type":42,"tag":450,"props":1376,"children":1378},{"className":452,"code":1377,"language":454,"meta":455,"style":455},"# Combines vector similarity with keyword matching\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"content\"],\n    query_text=\"SPARK-12345 executor memory error\",\n    query_type=\"HYBRID\",\n    num_results=10\n)\n",[1379],{"type":42,"tag":62,"props":1380,"children":1381},{"__ignoreMap":455},[1382,1390,1397,1404,1412,1420,1428,1435],{"type":42,"tag":461,"props":1383,"children":1384},{"class":463,"line":464},[1385],{"type":42,"tag":461,"props":1386,"children":1387},{},[1388],{"type":47,"value":1389},"# Combines vector similarity with keyword matching\n",{"type":42,"tag":461,"props":1391,"children":1392},{"class":463,"line":473},[1393],{"type":42,"tag":461,"props":1394,"children":1395},{},[1396],{"type":47,"value":727},{"type":42,"tag":461,"props":1398,"children":1399},{"class":463,"line":483},[1400],{"type":42,"tag":461,"props":1401,"children":1402},{},[1403],{"type":47,"value":735},{"type":42,"tag":461,"props":1405,"children":1406},{"class":463,"line":492},[1407],{"type":42,"tag":461,"props":1408,"children":1409},{},[1410],{"type":47,"value":1411},"    columns=[\"id\", \"content\"],\n",{"type":42,"tag":461,"props":1413,"children":1414},{"class":463,"line":500},[1415],{"type":42,"tag":461,"props":1416,"children":1417},{},[1418],{"type":47,"value":1419},"    query_text=\"SPARK-12345 executor memory error\",\n",{"type":42,"tag":461,"props":1421,"children":1422},{"class":463,"line":509},[1423],{"type":42,"tag":461,"props":1424,"children":1425},{},[1426],{"type":47,"value":1427},"    query_type=\"HYBRID\",\n",{"type":42,"tag":461,"props":1429,"children":1430},{"class":463,"line":518},[1431],{"type":42,"tag":461,"props":1432,"children":1433},{},[1434],{"type":47,"value":1348},{"type":42,"tag":461,"props":1436,"children":1437},{"class":463,"line":527},[1438],{"type":42,"tag":461,"props":1439,"children":1440},{},[1441],{"type":47,"value":542},{"type":42,"tag":75,"props":1443,"children":1445},{"id":1444},"filtering",[1446],{"type":47,"value":1447},"Filtering",{"type":42,"tag":443,"props":1449,"children":1451},{"id":1450},"standard-endpoint-filters-dictionary",[1452],{"type":47,"value":1453},"Standard Endpoint Filters (Dictionary)",{"type":42,"tag":450,"props":1455,"children":1457},{"className":452,"code":1456,"language":454,"meta":455,"style":455},"# filters_json uses dictionary format\nresults = w.vector_search_indexes.query_index(\n    index_name=\"catalog.schema.my_index\",\n    columns=[\"id\", \"content\"],\n    query_text=\"machine learning\",\n    num_results=10,\n    filters_json='{\"category\": \"ai\", \"status\": [\"active\", \"pending\"]}'\n)\n",[1458],{"type":42,"tag":62,"props":1459,"children":1460},{"__ignoreMap":455},[1461,1469,1476,1483,1490,1498,1506,1514],{"type":42,"tag":461,"props":1462,"children":1463},{"class":463,"line":464},[1464],{"type":42,"tag":461,"props":1465,"children":1466},{},[1467],{"type":47,"value":1468},"# filters_json uses dictionary format\n",{"type":42,"tag":461,"props":1470,"children":1471},{"class":463,"line":473},[1472],{"type":42,"tag":461,"props":1473,"children":1474},{},[1475],{"type":47,"value":727},{"type":42,"tag":461,"props":1477,"children":1478},{"class":463,"line":483},[1479],{"type":42,"tag":461,"props":1480,"children":1481},{},[1482],{"type":47,"value":735},{"type":42,"tag":461,"props":1484,"children":1485},{"class":463,"line":492},[1486],{"type":42,"tag":461,"props":1487,"children":1488},{},[1489],{"type":47,"value":1411},{"type":42,"tag":461,"props":1491,"children":1492},{"class":463,"line":500},[1493],{"type":42,"tag":461,"props":1494,"children":1495},{},[1496],{"type":47,"value":1497},"    query_text=\"machine learning\",\n",{"type":42,"tag":461,"props":1499,"children":1500},{"class":463,"line":509},[1501],{"type":42,"tag":461,"props":1502,"children":1503},{},[1504],{"type":47,"value":1505},"    num_results=10,\n",{"type":42,"tag":461,"props":1507,"children":1508},{"class":463,"line":518},[1509],{"type":42,"tag":461,"props":1510,"children":1511},{},[1512],{"type":47,"value":1513},"    filters_json='{\"category\": \"ai\", \"status\": [\"active\", \"pending\"]}'\n",{"type":42,"tag":461,"props":1515,"children":1516},{"class":463,"line":527},[1517],{"type":42,"tag":461,"props":1518,"children":1519},{},[1520],{"type":47,"value":542},{"type":42,"tag":443,"props":1522,"children":1524},{"id":1523},"storage-optimized-filters-sql-like",[1525],{"type":47,"value":1526},"Storage-Optimized Filters (SQL-like)",{"type":42,"tag":50,"props":1528,"children":1529},{},[1530,1532,1538,1540,1546],{"type":47,"value":1531},"Storage-Optimized endpoints use SQL-like filter syntax via the ",{"type":42,"tag":62,"props":1533,"children":1535},{"className":1534},[],[1536],{"type":47,"value":1537},"databricks-vectorsearch",{"type":47,"value":1539}," package's ",{"type":42,"tag":62,"props":1541,"children":1543},{"className":1542},[],[1544],{"type":47,"value":1545},"filters",{"type":47,"value":1547}," parameter (accepts a string):",{"type":42,"tag":450,"props":1549,"children":1551},{"className":452,"code":1550,"language":454,"meta":455,"style":455},"from databricks.vector_search.client import VectorSearchClient\n\nvsc = VectorSearchClient()\nindex = vsc.get_index(endpoint_name=\"my-storage-endpoint\", index_name=\"catalog.schema.my_index\")\n\n# SQL-like filter syntax for storage-optimized endpoints\nresults = index.similarity_search(\n    query_text=\"machine learning\",\n    columns=[\"id\", \"content\"],\n    num_results=10,\n    filters=\"category = 'ai' AND status IN ('active', 'pending')\"\n)\n\n# More filter examples\n# filters=\"price > 100 AND price \u003C 500\"\n# filters=\"department LIKE 'eng%'\"\n# filters=\"created_at >= '2024-01-01'\"\n",[1552],{"type":42,"tag":62,"props":1553,"children":1554},{"__ignoreMap":455},[1555,1563,1570,1578,1586,1593,1601,1609,1616,1623,1630,1638,1645,1652,1660,1668,1676],{"type":42,"tag":461,"props":1556,"children":1557},{"class":463,"line":464},[1558],{"type":42,"tag":461,"props":1559,"children":1560},{},[1561],{"type":47,"value":1562},"from databricks.vector_search.client import VectorSearchClient\n",{"type":42,"tag":461,"props":1564,"children":1565},{"class":463,"line":473},[1566],{"type":42,"tag":461,"props":1567,"children":1568},{"emptyLinePlaceholder":477},[1569],{"type":47,"value":480},{"type":42,"tag":461,"props":1571,"children":1572},{"class":463,"line":483},[1573],{"type":42,"tag":461,"props":1574,"children":1575},{},[1576],{"type":47,"value":1577},"vsc = VectorSearchClient()\n",{"type":42,"tag":461,"props":1579,"children":1580},{"class":463,"line":492},[1581],{"type":42,"tag":461,"props":1582,"children":1583},{},[1584],{"type":47,"value":1585},"index = vsc.get_index(endpoint_name=\"my-storage-endpoint\", index_name=\"catalog.schema.my_index\")\n",{"type":42,"tag":461,"props":1587,"children":1588},{"class":463,"line":500},[1589],{"type":42,"tag":461,"props":1590,"children":1591},{"emptyLinePlaceholder":477},[1592],{"type":47,"value":480},{"type":42,"tag":461,"props":1594,"children":1595},{"class":463,"line":509},[1596],{"type":42,"tag":461,"props":1597,"children":1598},{},[1599],{"type":47,"value":1600},"# SQL-like filter syntax for storage-optimized endpoints\n",{"type":42,"tag":461,"props":1602,"children":1603},{"class":463,"line":518},[1604],{"type":42,"tag":461,"props":1605,"children":1606},{},[1607],{"type":47,"value":1608},"results = index.similarity_search(\n",{"type":42,"tag":461,"props":1610,"children":1611},{"class":463,"line":527},[1612],{"type":42,"tag":461,"props":1613,"children":1614},{},[1615],{"type":47,"value":1497},{"type":42,"tag":461,"props":1617,"children":1618},{"class":463,"line":536},[1619],{"type":42,"tag":461,"props":1620,"children":1621},{},[1622],{"type":47,"value":1411},{"type":42,"tag":461,"props":1624,"children":1625},{"class":463,"line":545},[1626],{"type":42,"tag":461,"props":1627,"children":1628},{},[1629],{"type":47,"value":1505},{"type":42,"tag":461,"props":1631,"children":1632},{"class":463,"line":647},[1633],{"type":42,"tag":461,"props":1634,"children":1635},{},[1636],{"type":47,"value":1637},"    filters=\"category = 'ai' AND status IN ('active', 'pending')\"\n",{"type":42,"tag":461,"props":1639,"children":1640},{"class":463,"line":656},[1641],{"type":42,"tag":461,"props":1642,"children":1643},{},[1644],{"type":47,"value":542},{"type":42,"tag":461,"props":1646,"children":1647},{"class":463,"line":665},[1648],{"type":42,"tag":461,"props":1649,"children":1650},{"emptyLinePlaceholder":477},[1651],{"type":47,"value":480},{"type":42,"tag":461,"props":1653,"children":1654},{"class":463,"line":674},[1655],{"type":42,"tag":461,"props":1656,"children":1657},{},[1658],{"type":47,"value":1659},"# More filter examples\n",{"type":42,"tag":461,"props":1661,"children":1662},{"class":463,"line":683},[1663],{"type":42,"tag":461,"props":1664,"children":1665},{},[1666],{"type":47,"value":1667},"# filters=\"price > 100 AND price \u003C 500\"\n",{"type":42,"tag":461,"props":1669,"children":1670},{"class":463,"line":692},[1671],{"type":42,"tag":461,"props":1672,"children":1673},{},[1674],{"type":47,"value":1675},"# filters=\"department LIKE 'eng%'\"\n",{"type":42,"tag":461,"props":1677,"children":1678},{"class":463,"line":701},[1679],{"type":42,"tag":461,"props":1680,"children":1681},{},[1682],{"type":47,"value":1683},"# filters=\"created_at >= '2024-01-01'\"\n",{"type":42,"tag":443,"props":1685,"children":1687},{"id":1686},"trigger-index-sync",[1688],{"type":47,"value":1689},"Trigger Index Sync",{"type":42,"tag":450,"props":1691,"children":1693},{"className":452,"code":1692,"language":454,"meta":455,"style":455},"# For TRIGGERED pipeline type, manually sync\nw.vector_search_indexes.sync_index(\n    index_name=\"catalog.schema.my_index\"\n)\n",[1694],{"type":42,"tag":62,"props":1695,"children":1696},{"__ignoreMap":455},[1697,1705,1713,1721],{"type":42,"tag":461,"props":1698,"children":1699},{"class":463,"line":464},[1700],{"type":42,"tag":461,"props":1701,"children":1702},{},[1703],{"type":47,"value":1704},"# For TRIGGERED pipeline type, manually sync\n",{"type":42,"tag":461,"props":1706,"children":1707},{"class":463,"line":473},[1708],{"type":42,"tag":461,"props":1709,"children":1710},{},[1711],{"type":47,"value":1712},"w.vector_search_indexes.sync_index(\n",{"type":42,"tag":461,"props":1714,"children":1715},{"class":463,"line":483},[1716],{"type":42,"tag":461,"props":1717,"children":1718},{},[1719],{"type":47,"value":1720},"    index_name=\"catalog.schema.my_index\"\n",{"type":42,"tag":461,"props":1722,"children":1723},{"class":463,"line":492},[1724],{"type":42,"tag":461,"props":1725,"children":1726},{},[1727],{"type":47,"value":542},{"type":42,"tag":443,"props":1729,"children":1731},{"id":1730},"scan-all-index-entries",[1732],{"type":47,"value":1733},"Scan All Index Entries",{"type":42,"tag":450,"props":1735,"children":1737},{"className":452,"code":1736,"language":454,"meta":455,"style":455},"# Retrieve all vectors (for debugging\u002Fexport)\nscan_result = w.vector_search_indexes.scan_index(\n    index_name=\"catalog.schema.my_index\",\n    num_results=100\n)\n",[1738],{"type":42,"tag":62,"props":1739,"children":1740},{"__ignoreMap":455},[1741,1749,1757,1764,1772],{"type":42,"tag":461,"props":1742,"children":1743},{"class":463,"line":464},[1744],{"type":42,"tag":461,"props":1745,"children":1746},{},[1747],{"type":47,"value":1748},"# Retrieve all vectors (for debugging\u002Fexport)\n",{"type":42,"tag":461,"props":1750,"children":1751},{"class":463,"line":473},[1752],{"type":42,"tag":461,"props":1753,"children":1754},{},[1755],{"type":47,"value":1756},"scan_result = w.vector_search_indexes.scan_index(\n",{"type":42,"tag":461,"props":1758,"children":1759},{"class":463,"line":483},[1760],{"type":42,"tag":461,"props":1761,"children":1762},{},[1763],{"type":47,"value":735},{"type":42,"tag":461,"props":1765,"children":1766},{"class":463,"line":492},[1767],{"type":42,"tag":461,"props":1768,"children":1769},{},[1770],{"type":47,"value":1771},"    num_results=100\n",{"type":42,"tag":461,"props":1773,"children":1774},{"class":463,"line":500},[1775],{"type":42,"tag":461,"props":1776,"children":1777},{},[1778],{"type":47,"value":542},{"type":42,"tag":75,"props":1780,"children":1782},{"id":1781},"reference-files",[1783],{"type":47,"value":1784},"Reference Files",{"type":42,"tag":128,"props":1786,"children":1787},{},[1788,1808],{"type":42,"tag":132,"props":1789,"children":1790},{},[1791],{"type":42,"tag":136,"props":1792,"children":1793},{},[1794,1799,1804],{"type":42,"tag":140,"props":1795,"children":1796},{},[1797],{"type":47,"value":1798},"Topic",{"type":42,"tag":140,"props":1800,"children":1801},{},[1802],{"type":47,"value":1803},"File",{"type":42,"tag":140,"props":1805,"children":1806},{},[1807],{"type":47,"value":149},{"type":42,"tag":151,"props":1809,"children":1810},{},[1811,1831,1852,1872],{"type":42,"tag":136,"props":1812,"children":1813},{},[1814,1818,1826],{"type":42,"tag":158,"props":1815,"children":1816},{},[1817],{"type":47,"value":329},{"type":42,"tag":158,"props":1819,"children":1820},{},[1821],{"type":42,"tag":1368,"props":1822,"children":1824},{"href":1823},"references\u002Findex-types.md",[1825],{"type":47,"value":1823},{"type":42,"tag":158,"props":1827,"children":1828},{},[1829],{"type":47,"value":1830},"Detailed comparison of Delta Sync (managed\u002Fself-managed) vs Direct Access",{"type":42,"tag":136,"props":1832,"children":1833},{},[1834,1839,1847],{"type":42,"tag":158,"props":1835,"children":1836},{},[1837],{"type":47,"value":1838},"End-to-End RAG",{"type":42,"tag":158,"props":1840,"children":1841},{},[1842],{"type":42,"tag":1368,"props":1843,"children":1845},{"href":1844},"references\u002Fend-to-end-rag.md",[1846],{"type":47,"value":1844},{"type":42,"tag":158,"props":1848,"children":1849},{},[1850],{"type":47,"value":1851},"Complete walkthrough: source table → endpoint → index → query → agent integration",{"type":42,"tag":136,"props":1853,"children":1854},{},[1855,1860,1867],{"type":42,"tag":158,"props":1856,"children":1857},{},[1858],{"type":47,"value":1859},"Search Modes",{"type":42,"tag":158,"props":1861,"children":1862},{},[1863],{"type":42,"tag":1368,"props":1864,"children":1865},{"href":1370},[1866],{"type":47,"value":1370},{"type":42,"tag":158,"props":1868,"children":1869},{},[1870],{"type":47,"value":1871},"When to use semantic (ANN) vs hybrid search, decision guide",{"type":42,"tag":136,"props":1873,"children":1874},{},[1875,1880,1888],{"type":42,"tag":158,"props":1876,"children":1877},{},[1878],{"type":47,"value":1879},"Operations",{"type":42,"tag":158,"props":1881,"children":1882},{},[1883],{"type":42,"tag":1368,"props":1884,"children":1886},{"href":1885},"references\u002Ftroubleshooting-and-operations.md",[1887],{"type":47,"value":1885},{"type":42,"tag":158,"props":1889,"children":1890},{},[1891],{"type":47,"value":1892},"Monitoring, cost optimization, capacity planning, migration",{"type":42,"tag":75,"props":1894,"children":1896},{"id":1895},"cli-quick-reference",[1897],{"type":47,"value":1898},"CLI Quick Reference",{"type":42,"tag":450,"props":1900,"children":1904},{"className":1901,"code":1902,"language":1903,"meta":455,"style":455},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# List endpoints\ndatabricks vector-search-endpoints list-endpoints\n\n# Create endpoint (positional args: NAME ENDPOINT_TYPE)\ndatabricks vector-search-endpoints create-endpoint my-endpoint STANDARD\n\n# List indexes on endpoint (positional arg: ENDPOINT_NAME)\ndatabricks vector-search-indexes list-indexes my-endpoint\n\n# Get index status (positional arg: INDEX_NAME)\ndatabricks vector-search-indexes get-index catalog.schema.my_index\n\n# Sync index (positional arg: INDEX_NAME)\ndatabricks vector-search-indexes sync-index catalog.schema.my_index\n\n# Delete index (positional arg: INDEX_NAME)\ndatabricks vector-search-indexes delete-index catalog.schema.my_index\n","bash",[1905],{"type":42,"tag":62,"props":1906,"children":1907},{"__ignoreMap":455},[1908,1917,1936,1943,1951,1977,1984,1992,2014,2021,2029,2050,2057,2065,2085,2092,2100],{"type":42,"tag":461,"props":1909,"children":1910},{"class":463,"line":464},[1911],{"type":42,"tag":461,"props":1912,"children":1914},{"style":1913},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[1915],{"type":47,"value":1916},"# List endpoints\n",{"type":42,"tag":461,"props":1918,"children":1919},{"class":463,"line":473},[1920,1925,1931],{"type":42,"tag":461,"props":1921,"children":1923},{"style":1922},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[1924],{"type":47,"value":8},{"type":42,"tag":461,"props":1926,"children":1928},{"style":1927},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1929],{"type":47,"value":1930}," vector-search-endpoints",{"type":42,"tag":461,"props":1932,"children":1933},{"style":1927},[1934],{"type":47,"value":1935}," list-endpoints\n",{"type":42,"tag":461,"props":1937,"children":1938},{"class":463,"line":483},[1939],{"type":42,"tag":461,"props":1940,"children":1941},{"emptyLinePlaceholder":477},[1942],{"type":47,"value":480},{"type":42,"tag":461,"props":1944,"children":1945},{"class":463,"line":492},[1946],{"type":42,"tag":461,"props":1947,"children":1948},{"style":1913},[1949],{"type":47,"value":1950},"# Create endpoint (positional args: NAME ENDPOINT_TYPE)\n",{"type":42,"tag":461,"props":1952,"children":1953},{"class":463,"line":500},[1954,1958,1962,1967,1972],{"type":42,"tag":461,"props":1955,"children":1956},{"style":1922},[1957],{"type":47,"value":8},{"type":42,"tag":461,"props":1959,"children":1960},{"style":1927},[1961],{"type":47,"value":1930},{"type":42,"tag":461,"props":1963,"children":1964},{"style":1927},[1965],{"type":47,"value":1966}," create-endpoint",{"type":42,"tag":461,"props":1968,"children":1969},{"style":1927},[1970],{"type":47,"value":1971}," my-endpoint",{"type":42,"tag":461,"props":1973,"children":1974},{"style":1927},[1975],{"type":47,"value":1976}," STANDARD\n",{"type":42,"tag":461,"props":1978,"children":1979},{"class":463,"line":509},[1980],{"type":42,"tag":461,"props":1981,"children":1982},{"emptyLinePlaceholder":477},[1983],{"type":47,"value":480},{"type":42,"tag":461,"props":1985,"children":1986},{"class":463,"line":518},[1987],{"type":42,"tag":461,"props":1988,"children":1989},{"style":1913},[1990],{"type":47,"value":1991},"# List indexes on endpoint (positional arg: ENDPOINT_NAME)\n",{"type":42,"tag":461,"props":1993,"children":1994},{"class":463,"line":527},[1995,1999,2004,2009],{"type":42,"tag":461,"props":1996,"children":1997},{"style":1922},[1998],{"type":47,"value":8},{"type":42,"tag":461,"props":2000,"children":2001},{"style":1927},[2002],{"type":47,"value":2003}," vector-search-indexes",{"type":42,"tag":461,"props":2005,"children":2006},{"style":1927},[2007],{"type":47,"value":2008}," list-indexes",{"type":42,"tag":461,"props":2010,"children":2011},{"style":1927},[2012],{"type":47,"value":2013}," my-endpoint\n",{"type":42,"tag":461,"props":2015,"children":2016},{"class":463,"line":536},[2017],{"type":42,"tag":461,"props":2018,"children":2019},{"emptyLinePlaceholder":477},[2020],{"type":47,"value":480},{"type":42,"tag":461,"props":2022,"children":2023},{"class":463,"line":545},[2024],{"type":42,"tag":461,"props":2025,"children":2026},{"style":1913},[2027],{"type":47,"value":2028},"# Get index status (positional arg: INDEX_NAME)\n",{"type":42,"tag":461,"props":2030,"children":2031},{"class":463,"line":647},[2032,2036,2040,2045],{"type":42,"tag":461,"props":2033,"children":2034},{"style":1922},[2035],{"type":47,"value":8},{"type":42,"tag":461,"props":2037,"children":2038},{"style":1927},[2039],{"type":47,"value":2003},{"type":42,"tag":461,"props":2041,"children":2042},{"style":1927},[2043],{"type":47,"value":2044}," get-index",{"type":42,"tag":461,"props":2046,"children":2047},{"style":1927},[2048],{"type":47,"value":2049}," catalog.schema.my_index\n",{"type":42,"tag":461,"props":2051,"children":2052},{"class":463,"line":656},[2053],{"type":42,"tag":461,"props":2054,"children":2055},{"emptyLinePlaceholder":477},[2056],{"type":47,"value":480},{"type":42,"tag":461,"props":2058,"children":2059},{"class":463,"line":665},[2060],{"type":42,"tag":461,"props":2061,"children":2062},{"style":1913},[2063],{"type":47,"value":2064},"# Sync index (positional arg: INDEX_NAME)\n",{"type":42,"tag":461,"props":2066,"children":2067},{"class":463,"line":674},[2068,2072,2076,2081],{"type":42,"tag":461,"props":2069,"children":2070},{"style":1922},[2071],{"type":47,"value":8},{"type":42,"tag":461,"props":2073,"children":2074},{"style":1927},[2075],{"type":47,"value":2003},{"type":42,"tag":461,"props":2077,"children":2078},{"style":1927},[2079],{"type":47,"value":2080}," sync-index",{"type":42,"tag":461,"props":2082,"children":2083},{"style":1927},[2084],{"type":47,"value":2049},{"type":42,"tag":461,"props":2086,"children":2087},{"class":463,"line":683},[2088],{"type":42,"tag":461,"props":2089,"children":2090},{"emptyLinePlaceholder":477},[2091],{"type":47,"value":480},{"type":42,"tag":461,"props":2093,"children":2094},{"class":463,"line":692},[2095],{"type":42,"tag":461,"props":2096,"children":2097},{"style":1913},[2098],{"type":47,"value":2099},"# Delete index (positional arg: INDEX_NAME)\n",{"type":42,"tag":461,"props":2101,"children":2102},{"class":463,"line":701},[2103,2107,2111,2116],{"type":42,"tag":461,"props":2104,"children":2105},{"style":1922},[2106],{"type":47,"value":8},{"type":42,"tag":461,"props":2108,"children":2109},{"style":1927},[2110],{"type":47,"value":2003},{"type":42,"tag":461,"props":2112,"children":2113},{"style":1927},[2114],{"type":47,"value":2115}," delete-index",{"type":42,"tag":461,"props":2117,"children":2118},{"style":1927},[2119],{"type":47,"value":2049},{"type":42,"tag":75,"props":2121,"children":2123},{"id":2122},"common-issues",[2124],{"type":47,"value":2125},"Common Issues",{"type":42,"tag":128,"props":2127,"children":2128},{},[2129,2145],{"type":42,"tag":132,"props":2130,"children":2131},{},[2132],{"type":42,"tag":136,"props":2133,"children":2134},{},[2135,2140],{"type":42,"tag":140,"props":2136,"children":2137},{},[2138],{"type":47,"value":2139},"Issue",{"type":42,"tag":140,"props":2141,"children":2142},{},[2143],{"type":47,"value":2144},"Solution",{"type":42,"tag":151,"props":2146,"children":2147},{},[2148,2164,2180,2209,2225,2241,2257],{"type":42,"tag":136,"props":2149,"children":2150},{},[2151,2159],{"type":42,"tag":158,"props":2152,"children":2153},{},[2154],{"type":42,"tag":54,"props":2155,"children":2156},{},[2157],{"type":47,"value":2158},"Index sync slow",{"type":42,"tag":158,"props":2160,"children":2161},{},[2162],{"type":47,"value":2163},"Use Storage-Optimized endpoints (20x faster indexing)",{"type":42,"tag":136,"props":2165,"children":2166},{},[2167,2175],{"type":42,"tag":158,"props":2168,"children":2169},{},[2170],{"type":42,"tag":54,"props":2171,"children":2172},{},[2173],{"type":47,"value":2174},"Query latency high",{"type":42,"tag":158,"props":2176,"children":2177},{},[2178],{"type":47,"value":2179},"Use Standard endpoint for \u003C100ms latency",{"type":42,"tag":136,"props":2181,"children":2182},{},[2183,2191],{"type":42,"tag":158,"props":2184,"children":2185},{},[2186],{"type":42,"tag":54,"props":2187,"children":2188},{},[2189],{"type":47,"value":2190},"filters_json not working",{"type":42,"tag":158,"props":2192,"children":2193},{},[2194,2196,2201,2202,2207],{"type":47,"value":2195},"Storage-Optimized uses SQL-like string filters via ",{"type":42,"tag":62,"props":2197,"children":2199},{"className":2198},[],[2200],{"type":47,"value":1537},{"type":47,"value":1539},{"type":42,"tag":62,"props":2203,"children":2205},{"className":2204},[],[2206],{"type":47,"value":1545},{"type":47,"value":2208}," parameter",{"type":42,"tag":136,"props":2210,"children":2211},{},[2212,2220],{"type":42,"tag":158,"props":2213,"children":2214},{},[2215],{"type":42,"tag":54,"props":2216,"children":2217},{},[2218],{"type":47,"value":2219},"Embedding dimension mismatch",{"type":42,"tag":158,"props":2221,"children":2222},{},[2223],{"type":47,"value":2224},"Ensure query and index dimensions match",{"type":42,"tag":136,"props":2226,"children":2227},{},[2228,2236],{"type":42,"tag":158,"props":2229,"children":2230},{},[2231],{"type":42,"tag":54,"props":2232,"children":2233},{},[2234],{"type":47,"value":2235},"Index not updating",{"type":42,"tag":158,"props":2237,"children":2238},{},[2239],{"type":47,"value":2240},"Check pipeline_type; use sync_index() for TRIGGERED",{"type":42,"tag":136,"props":2242,"children":2243},{},[2244,2252],{"type":42,"tag":158,"props":2245,"children":2246},{},[2247],{"type":42,"tag":54,"props":2248,"children":2249},{},[2250],{"type":47,"value":2251},"Out of capacity",{"type":42,"tag":158,"props":2253,"children":2254},{},[2255],{"type":47,"value":2256},"Upgrade to Storage-Optimized (1B+ vectors)",{"type":42,"tag":136,"props":2258,"children":2259},{},[2260,2274],{"type":42,"tag":158,"props":2261,"children":2262},{},[2263],{"type":42,"tag":54,"props":2264,"children":2265},{},[2266,2272],{"type":42,"tag":62,"props":2267,"children":2269},{"className":2268},[],[2270],{"type":47,"value":2271},"query_vector",{"type":47,"value":2273}," truncated",{"type":42,"tag":158,"props":2275,"children":2276},{},[2277,2279,2285],{"type":47,"value":2278},"Large vectors (e.g. 1024-dim) can be truncated when serialized as JSON. Use ",{"type":42,"tag":62,"props":2280,"children":2282},{"className":2281},[],[2283],{"type":47,"value":2284},"query_text",{"type":47,"value":2286}," instead (for managed embedding indexes), or use the Databricks SDK to pass raw vectors",{"type":42,"tag":75,"props":2288,"children":2290},{"id":2289},"embedding-models",[2291],{"type":47,"value":2292},"Embedding Models",{"type":42,"tag":50,"props":2294,"children":2295},{},[2296],{"type":47,"value":2297},"Databricks provides built-in embedding models:",{"type":42,"tag":128,"props":2299,"children":2300},{},[2301,2326],{"type":42,"tag":132,"props":2302,"children":2303},{},[2304],{"type":42,"tag":136,"props":2305,"children":2306},{},[2307,2312,2317,2322],{"type":42,"tag":140,"props":2308,"children":2309},{},[2310],{"type":47,"value":2311},"Model",{"type":42,"tag":140,"props":2313,"children":2314},{},[2315],{"type":47,"value":2316},"Dimensions",{"type":42,"tag":140,"props":2318,"children":2319},{},[2320],{"type":47,"value":2321},"Context Window",{"type":42,"tag":140,"props":2323,"children":2324},{},[2325],{"type":47,"value":357},{"type":42,"tag":151,"props":2327,"children":2328},{},[2329,2356],{"type":42,"tag":136,"props":2330,"children":2331},{},[2332,2341,2346,2351],{"type":42,"tag":158,"props":2333,"children":2334},{},[2335],{"type":42,"tag":62,"props":2336,"children":2338},{"className":2337},[],[2339],{"type":47,"value":2340},"databricks-gte-large-en",{"type":42,"tag":158,"props":2342,"children":2343},{},[2344],{"type":47,"value":2345},"1024",{"type":42,"tag":158,"props":2347,"children":2348},{},[2349],{"type":47,"value":2350},"8192 tokens",{"type":42,"tag":158,"props":2352,"children":2353},{},[2354],{"type":47,"value":2355},"English text, high quality",{"type":42,"tag":136,"props":2357,"children":2358},{},[2359,2368,2372,2377],{"type":42,"tag":158,"props":2360,"children":2361},{},[2362],{"type":42,"tag":62,"props":2363,"children":2365},{"className":2364},[],[2366],{"type":47,"value":2367},"databricks-bge-large-en",{"type":42,"tag":158,"props":2369,"children":2370},{},[2371],{"type":47,"value":2345},{"type":42,"tag":158,"props":2373,"children":2374},{},[2375],{"type":47,"value":2376},"512 tokens",{"type":42,"tag":158,"props":2378,"children":2379},{},[2380],{"type":47,"value":2381},"English text, general purpose",{"type":42,"tag":450,"props":2383,"children":2385},{"className":452,"code":2384,"language":454,"meta":455,"style":455},"# Use with managed embeddings\nembedding_source_columns=[\n    {\n        \"name\": \"content\",\n        \"embedding_model_endpoint_name\": \"databricks-gte-large-en\"\n    }\n]\n",[2386],{"type":42,"tag":62,"props":2387,"children":2388},{"__ignoreMap":455},[2389,2397,2405,2413,2421,2429,2436],{"type":42,"tag":461,"props":2390,"children":2391},{"class":463,"line":464},[2392],{"type":42,"tag":461,"props":2393,"children":2394},{},[2395],{"type":47,"value":2396},"# Use with managed embeddings\n",{"type":42,"tag":461,"props":2398,"children":2399},{"class":463,"line":473},[2400],{"type":42,"tag":461,"props":2401,"children":2402},{},[2403],{"type":47,"value":2404},"embedding_source_columns=[\n",{"type":42,"tag":461,"props":2406,"children":2407},{"class":463,"line":483},[2408],{"type":42,"tag":461,"props":2409,"children":2410},{},[2411],{"type":47,"value":2412},"    {\n",{"type":42,"tag":461,"props":2414,"children":2415},{"class":463,"line":492},[2416],{"type":42,"tag":461,"props":2417,"children":2418},{},[2419],{"type":47,"value":2420},"        \"name\": \"content\",\n",{"type":42,"tag":461,"props":2422,"children":2423},{"class":463,"line":500},[2424],{"type":42,"tag":461,"props":2425,"children":2426},{},[2427],{"type":47,"value":2428},"        \"embedding_model_endpoint_name\": \"databricks-gte-large-en\"\n",{"type":42,"tag":461,"props":2430,"children":2431},{"class":463,"line":509},[2432],{"type":42,"tag":461,"props":2433,"children":2434},{},[2435],{"type":47,"value":698},{"type":42,"tag":461,"props":2437,"children":2438},{"class":463,"line":518},[2439],{"type":42,"tag":461,"props":2440,"children":2441},{},[2442],{"type":47,"value":2443},"]\n",{"type":42,"tag":75,"props":2445,"children":2447},{"id":2446},"notes",[2448],{"type":47,"value":2449},"Notes",{"type":42,"tag":87,"props":2451,"children":2452},{},[2453,2463,2473,2483,2499,2522],{"type":42,"tag":91,"props":2454,"children":2455},{},[2456,2461],{"type":42,"tag":54,"props":2457,"children":2458},{},[2459],{"type":47,"value":2460},"Storage-Optimized is newer",{"type":47,"value":2462}," — better for most use cases unless you need \u003C100ms latency",{"type":42,"tag":91,"props":2464,"children":2465},{},[2466,2471],{"type":42,"tag":54,"props":2467,"children":2468},{},[2469],{"type":47,"value":2470},"Delta Sync recommended",{"type":47,"value":2472}," — easier than Direct Access for most scenarios",{"type":42,"tag":91,"props":2474,"children":2475},{},[2476,2481],{"type":42,"tag":54,"props":2477,"children":2478},{},[2479],{"type":47,"value":2480},"Hybrid search",{"type":47,"value":2482}," — available for both Delta Sync and Direct Access indexes",{"type":42,"tag":91,"props":2484,"children":2485},{},[2486,2497],{"type":42,"tag":54,"props":2487,"children":2488},{},[2489,2495],{"type":42,"tag":62,"props":2490,"children":2492},{"className":2491},[],[2493],{"type":47,"value":2494},"columns_to_sync",{"type":47,"value":2496}," matters",{"type":47,"value":2498}," — only synced columns are available in query results; include all columns you need",{"type":42,"tag":91,"props":2500,"children":2501},{},[2502,2507,2509,2514,2515,2520],{"type":42,"tag":54,"props":2503,"children":2504},{},[2505],{"type":47,"value":2506},"Filter syntax differs by endpoint",{"type":47,"value":2508}," — Standard uses dict-format filters, Storage-Optimized uses SQL-like string filters. Use the ",{"type":42,"tag":62,"props":2510,"children":2512},{"className":2511},[],[2513],{"type":47,"value":1537},{"type":47,"value":1539},{"type":42,"tag":62,"props":2516,"children":2518},{"className":2517},[],[2519],{"type":47,"value":1545},{"type":47,"value":2521}," parameter which accepts both formats",{"type":42,"tag":91,"props":2523,"children":2524},{},[2525,2530,2532],{"type":42,"tag":54,"props":2526,"children":2527},{},[2528],{"type":47,"value":2529},"Management vs runtime",{"type":47,"value":2531}," — CLI and SDK handle lifecycle management; for agent tool-calling at runtime, use ",{"type":42,"tag":62,"props":2533,"children":2535},{"className":2534},[],[2536],{"type":47,"value":2537},"VectorSearchRetrieverTool",{"type":42,"tag":75,"props":2539,"children":2541},{"id":2540},"related-skills",[2542],{"type":47,"value":2543},"Related Skills",{"type":42,"tag":87,"props":2545,"children":2546},{},[2547,2557,2571,2585,2599],{"type":42,"tag":91,"props":2548,"children":2549},{},[2550,2555],{"type":42,"tag":54,"props":2551,"children":2552},{},[2553],{"type":47,"value":2554},"databricks-model-serving",{"type":47,"value":2556}," - Deploy agents that use VectorSearchRetrieverTool",{"type":42,"tag":91,"props":2558,"children":2559},{},[2560,2569],{"type":42,"tag":54,"props":2561,"children":2562},{},[2563],{"type":42,"tag":1368,"props":2564,"children":2566},{"href":2565},"..\u002Fdatabricks-agent-bricks\u002FSKILL.md",[2567],{"type":47,"value":2568},"databricks-agent-bricks",{"type":47,"value":2570}," - Knowledge Assistants use RAG over indexed documents",{"type":42,"tag":91,"props":2572,"children":2573},{},[2574,2583],{"type":42,"tag":54,"props":2575,"children":2576},{},[2577],{"type":42,"tag":1368,"props":2578,"children":2580},{"href":2579},"..\u002Fdatabricks-unstructured-pdf-generation\u002FSKILL.md",[2581],{"type":47,"value":2582},"databricks-unstructured-pdf-generation",{"type":47,"value":2584}," - Generate documents to index in Vector Search",{"type":42,"tag":91,"props":2586,"children":2587},{},[2588,2597],{"type":42,"tag":54,"props":2589,"children":2590},{},[2591],{"type":42,"tag":1368,"props":2592,"children":2594},{"href":2593},"..\u002Fdatabricks-unity-catalog\u002FSKILL.md",[2595],{"type":47,"value":2596},"databricks-unity-catalog",{"type":47,"value":2598}," - Manage the catalogs and tables that back Delta Sync indexes",{"type":42,"tag":91,"props":2600,"children":2601},{},[2602,2607],{"type":42,"tag":54,"props":2603,"children":2604},{},[2605],{"type":47,"value":2606},"databricks-pipelines",{"type":47,"value":2608}," - Build Delta tables used as Vector Search sources",{"type":42,"tag":2610,"props":2611,"children":2612},"style",{},[2613],{"type":47,"value":2614},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":2616,"total":1249},[2617,2633,2645,2662,2679,2699,2710,2732,2743,2760,2775,2788],{"slug":2568,"name":2568,"fn":2618,"description":2619,"org":2620,"tags":2621,"stars":23,"repoUrl":24,"updatedAt":2632},"create Databricks Agent Bricks","Create Agent Bricks: Knowledge Assistants (KA) for document Q&A and Supervisor Agents for multi-agent orchestration (MAS).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2622,2625,2626,2629],{"name":2623,"slug":2624,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":2627,"slug":2628,"type":15},"Knowledge Management","knowledge-management",{"name":2630,"slug":2631,"type":15},"Multi-Agent","multi-agent","2026-07-15T05:41:38.548954",{"slug":2634,"name":2634,"fn":2635,"description":2636,"org":2637,"tags":2638,"stars":23,"repoUrl":24,"updatedAt":2644},"databricks-ai-functions","use Databricks built-in AI functions","Use Databricks built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_mask, ai_translate, ai_fix_grammar, ai_gen, ai_analyze_sentiment, ai_similarity, ai_parse_document, ai_prep_search, ai_query, ai_forecast) to add AI capabilities directly to SQL and PySpark pipelines without managing model endpoints. Also covers document parsing and building custom RAG pipelines (parse → prep_search → index → query).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2639,2642,2643],{"name":2640,"slug":2641,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},"2026-07-31T05:53:33.562077",{"slug":2646,"name":2646,"fn":2647,"description":2648,"org":2649,"tags":2650,"stars":23,"repoUrl":24,"updatedAt":2661},"databricks-ai-runtime","submit and manage Databricks GPU workloads","Databricks AI Runtime (`air`) CLI — the command-line tool for submitting and managing GPU training workloads on Databricks serverless compute. Use for: running `air` workloads, custom Docker image setup, environment configuration, and troubleshooting `air` jobs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2651,2654,2655,2658],{"name":2652,"slug":2653,"type":15},"CLI","cli",{"name":9,"slug":8,"type":15},{"name":2656,"slug":2657,"type":15},"Docker","docker",{"name":2659,"slug":2660,"type":15},"Engineering","engineering","2026-07-12T08:04:55.843982",{"slug":2663,"name":2663,"fn":2664,"description":2665,"org":2666,"tags":2667,"stars":23,"repoUrl":24,"updatedAt":2678},"databricks-aibi-dashboards","create Databricks AI\u002FBI dashboards","Create Databricks AI\u002FBI dashboards. Must use when creating, updating, or deploying Lakeview dashboards as Databricks Dashboard have a unique json structure. CRITICAL: You MUST test ALL SQL queries via CLI BEFORE deploying. Follow guidelines strictly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2668,2671,2674,2677],{"name":2669,"slug":2670,"type":15},"Analytics","analytics",{"name":2672,"slug":2673,"type":15},"Dashboards","dashboards",{"name":2675,"slug":2676,"type":15},"Data Visualization","data-visualization",{"name":9,"slug":8,"type":15},"2026-07-12T08:04:25.314591",{"slug":2680,"name":2680,"fn":2681,"description":2682,"org":2683,"tags":2684,"stars":23,"repoUrl":24,"updatedAt":2698},"databricks-app-design","design UX for Databricks AppKit applications","Design the UX of custom-code Databricks Apps (AppKit\u002FReact) data screens — KPI\u002Foverview pages, reports, charts, tables, and Genie\u002Fchat data assistants — mapped to concrete AppKit components. Use when BUILDING or reviewing the UI of an AppKit\u002FReact app that displays data or answers data questions: choosing genre, layout, charts, KPIs, semantic color, required states (loading\u002Fempty\u002Ferror), IBCS notation, and AI-result trust (showing generated SQL\u002Fsources for Genie\u002Fchat). A plain \"create a dashboard\" request means a managed AI\u002FBI (Lakeview) dashboard → use databricks-aibi-dashboards, NOT this skill. Also NOT for non-data frontend (forms, settings, auth, marketing) or scaffolding\u002Fbuild\u002Fdeploy (→ databricks-apps). Complements databricks-apps; use it alongside whenever a custom app has a chart, table, KPI, report, or Genie\u002Fchat\u002FAI surface.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2685,2686,2689,2692,2695],{"name":9,"slug":8,"type":15},{"name":2687,"slug":2688,"type":15},"Design","design",{"name":2690,"slug":2691,"type":15},"Frontend","frontend",{"name":2693,"slug":2694,"type":15},"React","react",{"name":2696,"slug":2697,"type":15},"UI Components","ui-components","2026-07-12T08:04:02.02398",{"slug":2700,"name":2700,"fn":2701,"description":2702,"org":2703,"tags":2704,"stars":23,"repoUrl":24,"updatedAt":2709},"databricks-apps","build applications on Databricks Apps","Build apps on Databricks Apps platform. Use when asked to create data apps, analytics tools, or custom interactive visualizations. A plain \"create a dashboard\" request means a managed AI\u002FBI (Lakeview) dashboard → use databricks-aibi-dashboards, not this skill. Evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding. Invoke BEFORE starting implementation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2705,2706,2707,2708],{"name":2669,"slug":2670,"type":15},{"name":2672,"slug":2673,"type":15},{"name":2640,"slug":2641,"type":15},{"name":9,"slug":8,"type":15},"2026-07-12T08:03:59.061458",{"slug":2711,"name":2711,"fn":2712,"description":2713,"org":2714,"tags":2715,"stars":23,"repoUrl":24,"updatedAt":2731},"databricks-apps-python","build Python backends for Databricks Apps","Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. **Default for a new Databricks App is `databricks-apps` (AppKit — Node\u002FTypeScript\u002FReact) — reach for it first.** Use this skill only when the user asks for a Python backend, extends an existing Python app, or the team is Python-only. Covers OAuth auth, app resources, SQL warehouse and Lakebase connectivity, foundation-model \u002F Vector Search \u002F model-serving APIs (via `databricks-python-sdk`), and deployment via CLI or DABs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2716,2717,2720,2723,2726,2728],{"name":9,"slug":8,"type":15},{"name":2718,"slug":2719,"type":15},"FastAPI","fastapi",{"name":2721,"slug":2722,"type":15},"Flask","flask",{"name":2724,"slug":2725,"type":15},"Gradio","gradio",{"name":2727,"slug":454,"type":15},"Python",{"name":2729,"slug":2730,"type":15},"Streamlit","streamlit","2026-07-12T08:04:10.970845",{"slug":37,"name":37,"fn":2733,"description":2734,"org":2735,"tags":2736,"stars":23,"repoUrl":24,"updatedAt":2742},"configure Databricks CLI and authentication","Databricks CLI operations and the parent\u002Fentry-point skill for Databricks CLI use: authentication, profile selection, and bundles. Load this first for CLI, auth, profile, and bundle tasks, then load the matching product skill. For finding or exploring data, answering questions about the data, or generating SQL, load the databricks-data-discovery skill (it routes to Genie One). Contains up-to-date guidelines for Databricks-related CLI tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2737,2740,2741],{"name":2738,"slug":2739,"type":15},"Authentication","authentication",{"name":2652,"slug":2653,"type":15},{"name":9,"slug":8,"type":15},"2026-07-18T05:11:05.45506",{"slug":2744,"name":2744,"fn":2745,"description":2746,"org":2747,"tags":2748,"stars":23,"repoUrl":24,"updatedAt":2759},"databricks-dabs","manage Databricks Declarative Automation Bundles","Create, configure, validate, deploy, run, and manage Declarative Automation Bundles (DABs, formerly Databricks Asset Bundles). Use when working with Databricks resources via DABs including dashboards, jobs, pipelines, alerts, volumes, and apps.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2749,2752,2755,2756],{"name":2750,"slug":2751,"type":15},"Automation","automation",{"name":2753,"slug":2754,"type":15},"Configuration","configuration",{"name":9,"slug":8,"type":15},{"name":2757,"slug":2758,"type":15},"Deployment","deployment","2026-07-15T05:41:35.930355",{"slug":2761,"name":2761,"fn":2762,"description":2763,"org":2764,"tags":2765,"stars":23,"repoUrl":24,"updatedAt":2774},"databricks-data-discovery","discover and query Databricks data","Discover, explore, and query Databricks data via Genie — the CLI equivalent of the Genie One MCP. MUST be invoked whenever the user asks to find or locate data ('what tables are in X', 'where does X live', 'which catalog\u002Fschema has Y'), answer a natural-language question about the data, or write a SQL query.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2766,2767,2770,2771],{"name":2640,"slug":2641,"type":15},{"name":2768,"slug":2769,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":2772,"slug":2773,"type":15},"SQL","sql","2026-07-31T05:53:32.561877",{"slug":2776,"name":2776,"fn":2777,"description":2778,"org":2779,"tags":2780,"stars":23,"repoUrl":24,"updatedAt":2787},"databricks-dbsql","query and script Databricks SQL warehouses","Databricks SQL (DBSQL) advanced features and SQL warehouse capabilities. This skill MUST be invoked when the user mentions: \"DBSQL\", \"Databricks SQL\", \"SQL warehouse\", \"SQL scripting\", \"stored procedure\", \"CALL procedure\", \"materialized view\", \"CREATE MATERIALIZED VIEW\", \"pipe syntax\", \"|>\", \"geospatial\", \"H3\", \"ST_\", \"spatial SQL\", \"collation\", \"COLLATE\", \"ai_query\", \"ai_classify\", \"ai_extract\", \"ai_gen\", \"AI function\", \"http_request\", \"remote_query\", \"read_files\", \"Lakehouse Federation\", \"recursive CTE\", \"WITH RECURSIVE\", \"multi-statement transaction\", \"temp table\", \"temporary view\", \"pipe operator\". SHOULD also invoke when the user asks about SQL best practices, data modeling patterns, or advanced SQL features on Databricks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2781,2782,2785,2786],{"name":2640,"slug":2641,"type":15},{"name":2783,"slug":2784,"type":15},"Database","database",{"name":9,"slug":8,"type":15},{"name":2772,"slug":2773,"type":15},"2026-07-12T08:04:08.678282",{"slug":2789,"name":2789,"fn":2790,"description":2791,"org":2792,"tags":2793,"stars":23,"repoUrl":24,"updatedAt":2801},"databricks-docs","search Databricks documentation","Databricks documentation reference via llms.txt index. Use when other skills do not cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs on APIs, configurations, or platform capabilities.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2794,2795,2798],{"name":9,"slug":8,"type":15},{"name":2796,"slug":2797,"type":15},"Documentation","documentation",{"name":2799,"slug":2800,"type":15},"Reference","reference","2026-07-15T05:41:34.697746",{"items":2803,"total":1249},[2804,2811,2817,2824,2831,2839,2846],{"slug":2568,"name":2568,"fn":2618,"description":2619,"org":2805,"tags":2806,"stars":23,"repoUrl":24,"updatedAt":2632},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2807,2808,2809,2810],{"name":2623,"slug":2624,"type":15},{"name":9,"slug":8,"type":15},{"name":2627,"slug":2628,"type":15},{"name":2630,"slug":2631,"type":15},{"slug":2634,"name":2634,"fn":2635,"description":2636,"org":2812,"tags":2813,"stars":23,"repoUrl":24,"updatedAt":2644},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2814,2815,2816],{"name":2640,"slug":2641,"type":15},{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"slug":2646,"name":2646,"fn":2647,"description":2648,"org":2818,"tags":2819,"stars":23,"repoUrl":24,"updatedAt":2661},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2820,2821,2822,2823],{"name":2652,"slug":2653,"type":15},{"name":9,"slug":8,"type":15},{"name":2656,"slug":2657,"type":15},{"name":2659,"slug":2660,"type":15},{"slug":2663,"name":2663,"fn":2664,"description":2665,"org":2825,"tags":2826,"stars":23,"repoUrl":24,"updatedAt":2678},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2827,2828,2829,2830],{"name":2669,"slug":2670,"type":15},{"name":2672,"slug":2673,"type":15},{"name":2675,"slug":2676,"type":15},{"name":9,"slug":8,"type":15},{"slug":2680,"name":2680,"fn":2681,"description":2682,"org":2832,"tags":2833,"stars":23,"repoUrl":24,"updatedAt":2698},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2834,2835,2836,2837,2838],{"name":9,"slug":8,"type":15},{"name":2687,"slug":2688,"type":15},{"name":2690,"slug":2691,"type":15},{"name":2693,"slug":2694,"type":15},{"name":2696,"slug":2697,"type":15},{"slug":2700,"name":2700,"fn":2701,"description":2702,"org":2840,"tags":2841,"stars":23,"repoUrl":24,"updatedAt":2709},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2842,2843,2844,2845],{"name":2669,"slug":2670,"type":15},{"name":2672,"slug":2673,"type":15},{"name":2640,"slug":2641,"type":15},{"name":9,"slug":8,"type":15},{"slug":2711,"name":2711,"fn":2712,"description":2713,"org":2847,"tags":2848,"stars":23,"repoUrl":24,"updatedAt":2731},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2849,2850,2851,2852,2853,2854],{"name":9,"slug":8,"type":15},{"name":2718,"slug":2719,"type":15},{"name":2721,"slug":2722,"type":15},{"name":2724,"slug":2725,"type":15},{"name":2727,"slug":454,"type":15},{"name":2729,"slug":2730,"type":15}]