mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-13 15:22:30 +00:00
Jack Ye
f7ed6c6b93
The manual said the SQL dialect's function and type reference was out of scope. It is not: the engine is DataFusion 54 with its default function set registered, so the dialect is documented already and the useful thing is to say which version and point at it. The types are worth being concrete about rather than deferring. Lance's DataFusion table provider returns the dataset's Arrow schema directly — there is no SQL type layer over storage — so DataFusion's type reference describes Lance columns exactly, and a vector column is a FixedSizeList that behaves like one. Two consequences of that mapping are documented because they surprise people. The pseudo-columns the provider can append are real and typed — `_rowid`, `_rowaddr` and `_rowoffset` are nullable UInt64, and the nullability is a reused selection bitmap rather than a missing value, so a null there means nothing. And a blob column's Arrow type depends on how it is read: descriptions by default, binary on request, which changes the schema a query sees. `fts()` is recorded as what it is, a DataFusion TableProvider over the dataset. That explains the parts that otherwise look arbitrary: why it is a table function rather than a predicate, why every column of the table is available in its result, and why projections push into the scan.
357 lines
9.8 KiB
JSON
357 lines
9.8 KiB
JSON
{
|
|
"$schema": "https://mintlify.com/docs.json",
|
|
"appearance": {
|
|
"strict": false
|
|
},
|
|
"theme": "mint",
|
|
"name": "LanceDB",
|
|
"banner": {
|
|
"content": "[Why Multimodal Data Needs a Better Lakehouse? \u2014 Download the Research Study](https://lancedb.com/download/)",
|
|
"dismissible": true
|
|
},
|
|
"colors": {
|
|
"primary": "#FF6B35",
|
|
"light": "#FF8A5C",
|
|
"dark": "#E55A2B"
|
|
},
|
|
"fonts": {
|
|
"family": "Inter"
|
|
},
|
|
"styling": {
|
|
"codeblocks": {
|
|
"theme": {
|
|
"light": "vitesse-light",
|
|
"dark": "catppuccin-mocha"
|
|
}
|
|
}
|
|
},
|
|
"favicon": "/static/favicon.ico",
|
|
"navigation": {
|
|
"tabs": [
|
|
{
|
|
"tab": "Documentation",
|
|
"groups": [
|
|
{
|
|
"group": "Get started",
|
|
"pages": [
|
|
"quickstart",
|
|
{
|
|
"group": "What is LanceDB?",
|
|
"pages": [
|
|
"index",
|
|
"lance",
|
|
"tables-and-namespaces"
|
|
]
|
|
},
|
|
"performance"
|
|
]
|
|
},
|
|
{
|
|
"group": "Model training",
|
|
"pages": [
|
|
"training/why-lancedb",
|
|
"training/index",
|
|
"training/torch",
|
|
"training/object-detection",
|
|
"training/vlm-finetuning"
|
|
]
|
|
},
|
|
{
|
|
"group": "Guides",
|
|
"pages": [
|
|
{
|
|
"group": "Table operations",
|
|
"pages": [
|
|
"tables/index",
|
|
"tables/create",
|
|
"tables/multimodal",
|
|
"tables/schema",
|
|
"tables/update",
|
|
"tables/versioning",
|
|
"tables/branching",
|
|
"tables/consistency"
|
|
]
|
|
},
|
|
{
|
|
"group": "Namespaces",
|
|
"pages": [
|
|
"namespaces/index",
|
|
"namespaces/usage"
|
|
]
|
|
},
|
|
{
|
|
"group": "Embeddings",
|
|
"pages": [
|
|
"embedding/index",
|
|
"embedding/quickstart"
|
|
]
|
|
},
|
|
{
|
|
"group": "Indexing",
|
|
"pages": [
|
|
"indexing/index",
|
|
"indexing/vector-index",
|
|
"indexing/fts-index",
|
|
"indexing/scalar-index",
|
|
"indexing/quantization",
|
|
"indexing/reindexing"
|
|
]
|
|
},
|
|
{
|
|
"group": "Search",
|
|
"pages": [
|
|
"search/index",
|
|
"search/vector-search",
|
|
"search/multivector-search",
|
|
"search/full-text-search",
|
|
"search/fts-examples",
|
|
"search/hybrid-search",
|
|
"search/filtering",
|
|
"search/optimize-queries"
|
|
]
|
|
},
|
|
{
|
|
"group": "Reranking",
|
|
"pages": [
|
|
"reranking/index",
|
|
"reranking/rrf",
|
|
"reranking/linear_combination",
|
|
"reranking/mrr",
|
|
"reranking/cross_encoder",
|
|
"reranking/custom-reranker",
|
|
"reranking/eval"
|
|
]
|
|
},
|
|
{
|
|
"group": "Storage",
|
|
"pages": [
|
|
"storage/index",
|
|
"storage/configuration",
|
|
"storage/monitoring"
|
|
]
|
|
},
|
|
{
|
|
"group": "Build with AI agents",
|
|
"expanded": true,
|
|
"pages": [
|
|
"build-with-ai-agents",
|
|
"agent-branch-experiments"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"group": "Feature engineering",
|
|
"pages": [
|
|
"feature-engineering/index",
|
|
"feature-engineering/computed-columns",
|
|
"feature-engineering/materialized-views",
|
|
"feature-engineering/functions"
|
|
]
|
|
},
|
|
{
|
|
"group": "SQL and DataFrame",
|
|
"pages": [
|
|
"sql/index",
|
|
"sql/dataframe",
|
|
"sql/expressions",
|
|
"sql/functions"
|
|
]
|
|
},
|
|
{
|
|
"group": "Support",
|
|
"pages": [
|
|
"troubleshooting",
|
|
{
|
|
"group": "FAQ",
|
|
"pages": [
|
|
"faq/index",
|
|
"faq/faq-oss"
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tab": "Integrations",
|
|
"groups": [
|
|
{
|
|
"group": "Integrations",
|
|
"pages": [
|
|
"integrations/index",
|
|
{
|
|
"group": "Embedding Providers",
|
|
"pages": [
|
|
"integrations/embedding/huggingface",
|
|
"integrations/embedding/aws",
|
|
"integrations/embedding/cohere",
|
|
"integrations/embedding/colpali",
|
|
"integrations/embedding/gemini",
|
|
"integrations/embedding/ibm",
|
|
"integrations/embedding/imagebind",
|
|
"integrations/embedding/instructor",
|
|
"integrations/embedding/jina",
|
|
"integrations/embedding/ollama",
|
|
"integrations/embedding/openai",
|
|
"integrations/embedding/openclip",
|
|
"integrations/embedding/sentence-transformers",
|
|
"integrations/embedding/voyageai",
|
|
"integrations/embedding/superlinked"
|
|
]
|
|
},
|
|
{
|
|
"group": "Rerankers",
|
|
"pages": [
|
|
"integrations/reranking/answerdotai",
|
|
"integrations/reranking/cohere",
|
|
"integrations/reranking/colbert",
|
|
"integrations/reranking/jina",
|
|
"integrations/reranking/openai",
|
|
"integrations/reranking/voyageai",
|
|
"integrations/reranking/watsonx"
|
|
]
|
|
},
|
|
{
|
|
"group": "Data Platforms & Frameworks",
|
|
"expanded": true,
|
|
"pages": [
|
|
"integrations/data/pydantic",
|
|
"integrations/data/duckdb",
|
|
"integrations/data/pandas_and_pyarrow",
|
|
"integrations/data/polars_arrow",
|
|
"integrations/data/dlt",
|
|
"integrations/data/voxel51"
|
|
]
|
|
},
|
|
{
|
|
"group": "AI Platforms & Frameworks",
|
|
"expanded": true,
|
|
"pages": [
|
|
"integrations/ai/agno",
|
|
"integrations/ai/hermes-agent",
|
|
"integrations/ai/huggingface",
|
|
"integrations/ai/langchain",
|
|
"integrations/ai/llamaIndex",
|
|
"integrations/ai/genkit",
|
|
"integrations/ai/kiln",
|
|
"integrations/ai/prompttools",
|
|
"integrations/ai/synthetic-data-kit"
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tab": "Tutorials",
|
|
"groups": [
|
|
{
|
|
"group": "Tutorials",
|
|
"pages": [
|
|
"tutorials/index",
|
|
{
|
|
"group": "Search",
|
|
"expanded": true,
|
|
"pages": [
|
|
"tutorials/search/index",
|
|
"tutorials/search/multivector-needle-in-a-haystack"
|
|
]
|
|
},
|
|
{
|
|
"group": "RAG & Agents",
|
|
"expanded": true,
|
|
"pages": [
|
|
"tutorials/agents/index",
|
|
"tutorials/agents/nvidia-rag-blueprint/index",
|
|
"tutorials/agents/time-travel-rag/index",
|
|
"tutorials/agents/multimodal-agent/index"
|
|
]
|
|
},
|
|
"tutorials/feature-engineering/index"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tab": "Demos",
|
|
"groups": [
|
|
{
|
|
"group": "Demos",
|
|
"pages": [
|
|
"demos/index"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tab": "Use Cases",
|
|
"groups": [
|
|
{
|
|
"group": "Robotics",
|
|
"pages": [
|
|
"integrations/lerobotdataset"
|
|
]
|
|
},
|
|
{
|
|
"group": "World Models",
|
|
"pages": [
|
|
"integrations/stable-worldmodel"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tab": "API Reference",
|
|
"groups": [
|
|
{
|
|
"group": "API Reference",
|
|
"pages": [
|
|
"api-reference/index",
|
|
{
|
|
"group": "REST API",
|
|
"expanded": true,
|
|
"pages": [
|
|
"api-reference/rest/index"
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"logo": {
|
|
"light": "/static/assets/logo/dark-lancedb-logo.svg",
|
|
"dark": "/static/assets/logo/light-lancedb-logo.svg",
|
|
"href": "https://lancedb.com"
|
|
},
|
|
"background": {
|
|
"color": {
|
|
"light": "#FAF5F0",
|
|
"dark": "#000000"
|
|
}
|
|
},
|
|
"navbar": {
|
|
"links": [
|
|
{
|
|
"label": "Support",
|
|
"href": "mailto:contact@lancedb.com"
|
|
}
|
|
]
|
|
},
|
|
"footer": {
|
|
"socials": {
|
|
"github": "https://github.com/lancedb",
|
|
"linkedin": "https://www.linkedin.com/company/lancedb",
|
|
"x": "https://x.com/lancedb",
|
|
"discord": "https://discord.gg/AUEWnJ7Txb"
|
|
}
|
|
},
|
|
"integrations": {
|
|
"ga4": {
|
|
"measurementId": "G-1TMC2PR69E"
|
|
}
|
|
}
|
|
}
|