mirror of
https://github.com/lancedb/lancedb.git
synced 2026-11-13 22:26:53 +00:00
Jack YeandClaude Sonnet 5
de95ed3f6d
A broad documentation pass across the areas LanceDB Enterprise and Embedded diverge on most: **Data Curation** -- GPU Function execution, Slurm scheduling (and what Slurm is, for readers new to it), blob late materialization as its own page, joins, aggregation/profiling, sampling, near-duplicate detection, chunking, distributed shuffle, and IVF-partition clustering. **Feature Engineering** -- computed columns and materialized views, restructured to lead with the Function-based path and show the SQL form side by side with Python throughout; a single Auto Refresh page instead of duplicating scheduling details on every refresh page; adaptive execution; checkpointing; GPU and Slurm placement for refresh workers; a Training Cache page for the PyTorch data loader's automatic cache benefit. **Security & Governance** -- an Audit Log reference (schema, access, grants), Secrets promoted to an ordinary catalog object with their own SQL DDL and a vending/rotation guide, and privilege-table fixes verified against the authorization source. **Deployment & Maintenance** -- Horizontal Scaling and OpenTelemetry moved into a real Deployment area; Automated Cleanup folded into Intelligent Auto-Maintenance (every other maintenance decision already lived there); RTE Compaction and Advanced Conflict Resolution documented in depth. **Landing page** -- the Enterprise feature comparison table reorganized (several redundant or stale rows removed, several new areas added), and the "why Enterprise" bullets replaced with ones tied to a concrete page (Performance, Scale, Fault tolerance, Multicloud deployment, Simplify operations) instead of vague promises. Plus a full pass addressing lancedb-gatekeeper's review: a real test-safety bug (a quickstart test could silently overwrite and delete a deployment's own `frames` table), a fabricated SQL statement with no backing implementation, an actual dedup-guarantee bug in `take_row_ids`, and dozens of documentation-accuracy fixes verified against source rather than taken on faith -- each either fixed, or left with an explicit note on why it needs a feature or deployment owner's sign-off instead of being guessed at. 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_018PXMCbRH6i5w47TsjeEUMT --------- Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
47 lines
13 KiB
Plaintext
47 lines
13 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyAsyncOpenaiEmbeddings = "import lancedb\n\ndb = await lancedb.connect_async(uri)\nfunc = get_registry().get(\"openai\").create(name=\"text-embedding-ada-002\")\n\nclass Words(LanceModel):\n text: str = func.SourceField()\n vector: Vector(func.ndims()) = func.VectorField()\n\ntable = await db.create_table(\"words\", schema=Words, mode=\"overwrite\")\nawait table.add([{\"text\": \"hello world\"}, {\"text\": \"goodbye world\"}])\n\nquery = \"greetings\"\nactual = await (await table.search(query)).limit(1).to_pydantic(Words)[0]\nprint(actual.text)\n";
|
|
|
|
export const PyCreateEmbeddingFunction = "func = get_registry().get(\"openai\").create(\n name=\"text-embedding-3-small\",\n max_retries=7,\n)\n";
|
|
|
|
export const PyEmbeddingFunction = "from functools import cached_property\n\nfrom lancedb.embeddings import TextEmbeddingFunction, register\n\nclass MyEmbeddingModel:\n def __init__(self, model_name: str):\n self.model_name = model_name\n\n def encode(self, texts: list[str]) -> list[list[float]]:\n return [[1.0, 2.0, 3.0] for _ in texts]\n\n@register(\"my-embedder\")\nclass MyTextEmbedder(TextEmbeddingFunction):\n model_name: str = \"my-model\"\n\n def generate_embeddings(self, texts: list[str]) -> list[list[float]]:\n # Your embedding logic here\n return self._model.encode(texts)\n\n def ndims(self) -> int:\n # Return the dimensionality of the embeddings\n return len(self.generate_embeddings([\"test\"])[0])\n\n @cached_property\n def _model(self) -> MyEmbeddingModel:\n # Initialize your model once\n return MyEmbeddingModel(self.model_name)\n";
|
|
|
|
export const PyImports = "from lancedb.pydantic import LanceModel, Vector\nfrom lancedb.embeddings import get_registry\n";
|
|
|
|
export const PyManualQueryEmbeddings = "import lancedb\n\ndb = lancedb.connect(\"/tmp/db\")\nfunc = get_registry().get(\"openai\").create(name=\"text-embedding-ada-002\")\n\nclass Words(LanceModel):\n text: str = func.SourceField()\n vector: Vector(func.ndims()) = func.VectorField()\n\ntable = db.create_table(\"words\", schema=Words, mode=\"overwrite\")\ntable.add([{\"text\": \"hello world\"}, {\"text\": \"goodbye world\"}])\n\nquery_vector = func.generate_embeddings([\"greetings\"])[0]\n# --8<-- [start:manual_query_search]\n# query_vector is assumed to already be generated by your embedding function\nactual = table.search(query_vector).limit(1).to_pydantic(Words)[0]\nprint(actual.text)\n# --8<-- [end:manual_query_search]\n";
|
|
|
|
export const PyManualQuerySearch = "# query_vector is assumed to already be generated by your embedding function\nactual = table.search(query_vector).limit(1).to_pydantic(Words)[0]\nprint(actual.text)\n";
|
|
|
|
export const PyOpenaiEmbeddings = "import lancedb\n\ndb = lancedb.connect(\"/tmp/db\")\nfunc = get_registry().get(\"openai\").create(name=\"text-embedding-ada-002\")\n\nclass Words(LanceModel):\n text: str = func.SourceField()\n vector: Vector(func.ndims()) = func.VectorField()\n\ntable = db.create_table(\"words\", schema=Words, mode=\"overwrite\")\ntable.add([{\"text\": \"hello world\"}, {\"text\": \"goodbye world\"}])\n\nquery = \"greetings\"\nactual = table.search(query).limit(1).to_pydantic(Words)[0]\nprint(actual.text)\n";
|
|
|
|
export const PyRegisterDevice = "import torch\n\nregistry = get_registry()\nif torch.cuda.is_available():\n registry.set_var(\"device\", \"cuda\")\n\nfunc = registry.get(\"huggingface\").create(device=\"$var:device:cpu\")\n";
|
|
|
|
export const PyRegisterSecret = "registry = get_registry()\nregistry.set_var(\"api_key\", \"sk-...\")\n\nfunc = registry.get(\"openai\").create(api_key=\"$var:api_key\")\n";
|
|
|
|
export const TsCreateEmbeddingFunction = "const func = getRegistry().get(\"openai\")!.create({\n model: \"text-embedding-3-small\",\n});\n";
|
|
|
|
export const TsEmbeddingFunction = "const db = await lancedb.connect(databaseDir);\n\n@register(\"my_embedding\")\nclass MyEmbeddingFunction extends EmbeddingFunction<string> {\n constructor(optionsRaw = {}) {\n super();\n const options = this.resolveVariables(optionsRaw);\n // Initialize using options\n }\n ndims() {\n return 3;\n }\n protected getSensitiveKeys(): string[] {\n return [];\n }\n embeddingDataType(): Float {\n return new Float32();\n }\n async computeQueryEmbeddings(_data: string) {\n // This is a placeholder for a real embedding function\n return [1, 2, 3];\n }\n async computeSourceEmbeddings(data: string[]) {\n // This is a placeholder for a real embedding function\n return Array.from({ length: data.length }).fill([\n 1, 2, 3,\n ]) as number[][];\n }\n}\n\nconst func = new MyEmbeddingFunction();\n\nconst data = [{ text: \"pepperoni\" }, { text: \"pineapple\" }];\n\n// Option 1: manually specify the embedding function\nconst table = await db.createTable(\"vectors\", data, {\n embeddingFunction: {\n function: func,\n sourceColumn: \"text\",\n vectorColumn: \"vector\",\n },\n mode: \"overwrite\",\n});\n\n// Option 2: provide the embedding function through a schema\n\nconst schema = LanceSchema({\n text: func.sourceField(new Utf8()),\n vector: func.vectorField(),\n});\n\nconst table2 = await db.createTable(\"vectors2\", data, {\n schema,\n mode: \"overwrite\",\n});\n";
|
|
|
|
export const TsImports = "import * as lancedb from \"@lancedb/lancedb\";\nimport \"@lancedb/lancedb/embedding/openai\";\nimport { LanceSchema, getRegistry, register } from \"@lancedb/lancedb/embedding\";\nimport { EmbeddingFunction } from \"@lancedb/lancedb/embedding\";\nimport { type Float, Float32, Utf8 } from \"apache-arrow\";\n";
|
|
|
|
export const TsManualQueryEmbeddings = "const db = await lancedb.connect(databaseDir);\nconst func = getRegistry()\n .get(\"openai\")\n ?.create({ model: \"text-embedding-ada-002\" }) as EmbeddingFunction;\n\nconst wordsSchema = LanceSchema({\n text: func.sourceField(new Utf8()),\n vector: func.vectorField(),\n});\nconst tbl = await db.createEmptyTable(\"words\", wordsSchema, {\n mode: \"overwrite\",\n});\nawait tbl.add([{ text: \"hello world\" }, { text: \"goodbye world\" }]);\n\nconst queryVector = await func.computeQueryEmbeddings(\"greetings\");\n// --8<-- [start:manual_query_search]\n// queryVector is assumed to already be generated by your embedding function\nconst actual = (await tbl.search(queryVector).limit(1).toArray())[0];\n// --8<-- [end:manual_query_search]\n";
|
|
|
|
export const TsManualQuerySearch = "// queryVector is assumed to already be generated by your embedding function\nconst actual = (await tbl.search(queryVector).limit(1).toArray())[0];\n";
|
|
|
|
export const TsOpenaiEmbeddings = "const db = await lancedb.connect(databaseDir);\nconst func = getRegistry()\n .get(\"openai\")\n ?.create({ model: \"text-embedding-ada-002\" }) as EmbeddingFunction;\n\nconst wordsSchema = LanceSchema({\n text: func.sourceField(new Utf8()),\n vector: func.vectorField(),\n});\nconst tbl = await db.createEmptyTable(\"words\", wordsSchema, {\n mode: \"overwrite\",\n});\nawait tbl.add([{ text: \"hello world\" }, { text: \"goodbye world\" }]);\n\nconst query = \"greetings\";\nconst actual = (await tbl.search(query).limit(1).toArray())[0];\n";
|
|
|
|
export const TsRegisterModelFallback = "const registry = getRegistry();\nregistry.setVar(\"openai_model\", \"text-embedding-3-large\");\n\nconst func = registry.get(\"openai\")!.create({\n model: \"$var:openai_model:text-embedding-3-small\",\n});\n";
|
|
|
|
export const TsRegisterSecret = "const registry = getRegistry();\nregistry.setVar(\"api_key\", \"sk-...\");\n\nconst func = registry.get(\"openai\")!.create({\n apiKey: \"$var:api_key\",\n});\n";
|
|
|
|
export const RsCreateEmbeddingFunction = "use std::sync::Arc;\n\nuse lancedb::embeddings::openai::OpenAIEmbeddingFunction;\n\nlet api_key = \"your-openai-api-key\".to_string();\nlet embedding = Arc::new(\n OpenAIEmbeddingFunction::new_with_model(api_key, \"text-embedding-3-small\")\n .expect(\"failed to create OpenAI embedding function\"),\n);\n";
|
|
|
|
export const RsEmbeddingFunction = "use std::{borrow::Cow, sync::Arc};\n\nuse arrow_array::{Array, FixedSizeListArray, Float32Array};\nuse arrow_schema::{DataType, Field, Schema};\nuse lancedb::{\n connect,\n embeddings::{EmbeddingDefinition, EmbeddingFunction},\n Result,\n};\n\n#[derive(Debug, Clone)]\nstruct MyTextEmbedder {\n dim: usize,\n}\n\nimpl EmbeddingFunction for MyTextEmbedder {\n fn name(&self) -> &str {\n \"my-embedder\"\n }\n\n fn source_type(&self) -> Result<Cow<'_, DataType>> {\n Ok(Cow::Owned(DataType::Utf8))\n }\n\n fn dest_type(&self) -> Result<Cow<'_, DataType>> {\n Ok(Cow::Owned(DataType::new_fixed_size_list(\n DataType::Float32,\n self.dim as i32,\n true,\n )))\n }\n\n fn compute_source_embeddings(&self, source: Arc<dyn Array>) -> Result<Arc<dyn Array>> {\n let values = Arc::new(Float32Array::from(vec![1.0f32; source.len() * self.dim]));\n let field = Arc::new(Field::new(\"item\", DataType::Float32, true));\n Ok(Arc::new(FixedSizeListArray::new(\n field,\n self.dim as i32,\n values,\n None,\n )))\n }\n\n fn compute_query_embeddings(&self, _input: Arc<dyn Array>) -> Result<Arc<dyn Array>> {\n unimplemented!()\n }\n}\n\n#[tokio::main]\nasync fn main() -> Result<()> {\n let db = connect(\"./mydb\").execute().await?;\n db.embedding_registry()\n .register(\"my-embedder\", Arc::new(MyTextEmbedder { dim: 3 }))?;\n\n let schema = Arc::new(Schema::new(vec![Field::new(\"text\", DataType::Utf8, false)]));\n db.create_empty_table(\"mytable\", schema)\n .add_embedding(EmbeddingDefinition::new(\n \"text\",\n \"my-embedder\",\n Some(\"vector\"),\n ))?\n .execute()\n .await?;\n\n Ok(())\n}\n";
|
|
|
|
export const RsManualQueryEmbeddings = "use std::{iter::once, sync::Arc};\n\nuse arrow_array::{record_batch, StringArray};\nuse arrow_schema::{DataType, Field, Schema};\nuse futures::StreamExt;\nuse lancedb::{\n connect,\n embeddings::{openai::OpenAIEmbeddingFunction, EmbeddingDefinition, EmbeddingFunction},\n query::{ExecutableQuery, QueryBase},\n Result,\n};\n\n#[tokio::main]\nasync fn main() -> Result<()> {\n let db = connect(\"./mydb\").execute().await?;\n let api_key = \"your-openai-api-key\".to_string();\n let embedding = Arc::new(OpenAIEmbeddingFunction::new_with_model(\n api_key,\n \"text-embedding-3-large\",\n )?);\n db.embedding_registry().register(\"openai\", embedding.clone())?;\n\n let schema = Arc::new(Schema::new(vec![Field::new(\"text\", DataType::Utf8, false)]));\n let table = db\n .create_empty_table(\"mytable\", schema)\n .add_embedding(EmbeddingDefinition::new(\"text\", \"openai\", Some(\"vector\")))?\n .execute()\n .await?;\n\n table\n .add(record_batch!((\"text\", Utf8, [\"This is a test.\", \"Another example.\"]))?)\n .execute()\n .await?;\n\n // Manually generate embeddings for the query (Enterprise path)\n let query = Arc::new(StringArray::from_iter_values(once(\"test example\")));\n let query_vector = embedding.compute_query_embeddings(query)?;\n // --8<-- [start:manual_query_search]\n // query_vector is assumed to already be generated by your embedding function\n let mut results = table.vector_search(query_vector)?.limit(5).execute().await?;\n\n while let Some(batch) = results.next().await {\n println!(\"{:?}\", batch?);\n }\n // --8<-- [end:manual_query_search]\n\n Ok(())\n}\n";
|
|
|
|
export const RsManualQuerySearch = "// query_vector is assumed to already be generated by your embedding function\nlet mut results = table.vector_search(query_vector)?.limit(5).execute().await?;\n\nwhile let Some(batch) = results.next().await {\n println!(\"{:?}\", batch?);\n}\n";
|
|
|
|
export const RsOpenaiEmbeddings = "use std::{iter::once, sync::Arc};\n\nuse arrow_array::{record_batch, StringArray};\nuse arrow_schema::{DataType, Field, Schema};\nuse futures::StreamExt;\nuse lancedb::{\n connect,\n embeddings::{openai::OpenAIEmbeddingFunction, EmbeddingDefinition, EmbeddingFunction},\n query::{ExecutableQuery, QueryBase},\n Result,\n};\n\n#[tokio::main]\nasync fn main() -> Result<()> {\n let db = connect(\"./mydb\").execute().await?;\n let api_key = \"your-openai-api-key\".to_string();\n let embedding = Arc::new(OpenAIEmbeddingFunction::new_with_model(\n api_key,\n \"text-embedding-3-large\",\n )?);\n\n db.embedding_registry().register(\"openai\", embedding.clone())?;\n\n let schema = Arc::new(Schema::new(vec![Field::new(\"text\", DataType::Utf8, false)]));\n let table = db\n .create_empty_table(\"mytable\", schema)\n .add_embedding(EmbeddingDefinition::new(\"text\", \"openai\", Some(\"vector\")))?\n .execute()\n .await?;\n\n table\n .add(record_batch!((\"text\", Utf8, [\"This is a test.\", \"Another example.\"]))?)\n .execute()\n .await?;\n\n let query = Arc::new(StringArray::from_iter_values(once(\"test example\")));\n let query_vector = embedding.compute_query_embeddings(query)?;\n let mut results = table.vector_search(query_vector)?.limit(5).execute().await?;\n\n while let Some(batch) = results.next().await {\n println!(\"{:?}\", batch?);\n }\n\n Ok(())\n}\n";
|
|
|