mirror of
https://github.com/lancedb/lancedb.git
synced 2026-11-14 06:36:54 +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>
59 lines
6.3 KiB
Plaintext
59 lines
6.3 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyStorageAzureAccount = "import lancedb\n\ndb = lancedb.connect(\n \"az://my-container/my-database\",\n storage_options={\n \"account_name\": \"some-account\",\n \"account_key\": \"some-key\",\n },\n)\n";
|
|
|
|
export const PyStorageAzureSas = "import lancedb\n\ndb = lancedb.connect(\n \"az://my-container/my-database\",\n storage_options={\n \"azure_storage_account_name\": \"some-account\",\n \"azure_storage_sas_token\": \"<sas-token>\",\n },\n)\n";
|
|
|
|
export const PyStorageConnectAzure = "import lancedb\n\ndb = lancedb.connect(\"az://bucket/path\")\n";
|
|
|
|
export const PyStorageConnectGcs = "import lancedb\n\ndb = lancedb.connect(\"gs://bucket/path\")\n";
|
|
|
|
export const PyStorageConnectS3 = "import lancedb\n\ndb = lancedb.connect(\"s3://bucket/path\")\n";
|
|
|
|
export const PyStorageConnectTimeout = "import lancedb\n\ndb = lancedb.connect(\n \"s3://bucket/path\",\n storage_options={\"timeout\": \"60s\"},\n)\n";
|
|
|
|
export const PyStorageGcsServiceAccount = "import lancedb\n\ndb = lancedb.connect(\n \"gs://my-bucket/my-database\",\n storage_options={\n \"service_account\": \"path/to/service-account.json\",\n },\n)\n";
|
|
|
|
export const PyStorageS3Ddb = "import lancedb\n\ndb = lancedb.connect(\n \"s3+ddb://bucket/path?ddbTableName=my-dynamodb-table\",\n)\n";
|
|
|
|
export const PyStorageS3DdbLocal = "import lancedb\n\ndb = lancedb.connect(\n \"s3+ddb://bucket/path?ddbTableName=my-dynamodb-table\",\n storage_options={\n \"endpoint\": \"http://localhost:4566\",\n \"dynamodb_endpoint\": \"http://localhost:4566\",\n \"allow_http\": \"true\",\n },\n)\n";
|
|
|
|
export const PyStorageS3Express = "import lancedb\n\ndb = lancedb.connect(\n \"s3://my-bucket--use1-az4--x-s3/path\",\n storage_options={\n \"region\": \"us-east-1\",\n \"s3_express\": \"true\",\n },\n)\n";
|
|
|
|
export const PyStorageS3Minio = "import lancedb\n\ndb = lancedb.connect(\n \"s3://bucket/path\",\n storage_options={\n \"region\": \"us-east-1\",\n \"endpoint\": \"http://minio:9000\",\n },\n)\n";
|
|
|
|
export const PyStorageS3SseKms = "import lancedb\n\ndb = lancedb.connect(\n \"s3://bucket/path\",\n storage_options={\n \"aws_server_side_encryption\": \"aws:kms\",\n \"aws_sse_kms_key_id\": \"<your-kms-key-id-or-arn>\",\n },\n)\n";
|
|
|
|
export const PyStorageTableTimeout = "table = db.create_table(\n \"table\",\n [{\"a\": 1, \"b\": 2}],\n storage_options={\"timeout\": \"60s\"},\n)\n";
|
|
|
|
export const PyStorageTigrisConnect = "import lancedb\n\ndb = lancedb.connect(\n \"s3://your-bucket/path\",\n storage_options={\n \"endpoint\": \"https://t3.storage.dev\",\n \"region\": \"auto\",\n },\n)\n";
|
|
|
|
export const TsStorageAzureAccount = "async function storageAzureAccount() {\n const db = await lancedb.connect(\n \"az://my-container/my-database\",\n {\n storageOptions: {\n accountName: \"some-account\",\n accountKey: \"some-key\",\n },\n },\n );\n return db;\n}\n";
|
|
|
|
export const TsStorageAzureSas = "async function storageAzureSas() {\n const db = await lancedb.connect(\n \"az://my-container/my-database\",\n {\n storageOptions: {\n azureStorageAccountName: \"some-account\",\n azureStorageSasToken: \"<sas-token>\",\n },\n },\n );\n return db;\n}\n";
|
|
|
|
export const TsStorageConnectAzure = "async function storageConnectAzure() {\n const db = await lancedb.connect(\"az://bucket/path\");\n return db;\n}\n";
|
|
|
|
export const TsStorageConnectGcs = "async function storageConnectGcs() {\n const db = await lancedb.connect(\"gs://bucket/path\");\n return db;\n}\n";
|
|
|
|
export const TsStorageConnectS3 = "async function storageConnectS3() {\n const db = await lancedb.connect(\"s3://bucket/path\");\n return db;\n}\n";
|
|
|
|
export const TsStorageConnectTimeout = "async function storageConnectTimeout() {\n const db = await lancedb.connect(\"s3://bucket/path\", {\n storageOptions: { timeout: \"60s\" },\n });\n return db;\n}\n";
|
|
|
|
export const TsStorageGcsServiceAccount = "async function storageGcsServiceAccount() {\n const db = await lancedb.connect(\n \"gs://my-bucket/my-database\",\n {\n storageOptions: {\n serviceAccount: \"path/to/service-account.json\",\n },\n },\n );\n return db;\n}\n";
|
|
|
|
export const TsStorageS3Ddb = "async function storageS3Ddb() {\n const db = await lancedb.connect(\n \"s3+ddb://bucket/path?ddbTableName=my-dynamodb-table\",\n );\n return db;\n}\n";
|
|
|
|
export const TsStorageS3DdbLocal = "async function storageS3DdbLocal() {\n const db = await lancedb.connect(\n \"s3+ddb://bucket/path?ddbTableName=my-dynamodb-table\",\n {\n storageOptions: {\n endpoint: \"http://localhost:4566\",\n dynamodbEndpoint: \"http://localhost:4566\",\n allowHttp: \"true\",\n },\n },\n );\n return db;\n}\n";
|
|
|
|
export const TsStorageS3Express = "async function storageS3Express() {\n const db = await lancedb.connect(\n \"s3://my-bucket--use1-az4--x-s3/path\",\n {\n storageOptions: {\n region: \"us-east-1\",\n s3Express: \"true\",\n },\n },\n );\n return db;\n}\n";
|
|
|
|
export const TsStorageS3Minio = "async function storageS3Minio() {\n const db = await lancedb.connect(\"s3://bucket/path\", {\n storageOptions: {\n region: \"us-east-1\",\n endpoint: \"http://minio:9000\",\n },\n });\n return db;\n}\n";
|
|
|
|
export const TsStorageS3SseKms = "async function storageS3SseKms() {\n const db = await lancedb.connect(\"s3://bucket/path\", {\n storageOptions: {\n awsServerSideEncryption: \"aws:kms\",\n awsSseKmsKeyId: \"<your-kms-key-id-or-arn>\",\n },\n });\n return db;\n}\n";
|
|
|
|
export const TsStorageTableTimeout = "async function storageTableTimeout() {\n const db = await lancedb.connect(\"s3://bucket/path\");\n const table = await db.createTable(\n \"table\",\n [{ a: 1, b: 2 }],\n { storageOptions: { timeout: \"60s\" } },\n );\n return table;\n}\n";
|
|
|
|
export const TsStorageTigrisConnect = "async function storageTigrisConnect() {\n const db = await lancedb.connect(\n \"s3://your-bucket/path\",\n {\n storageOptions: {\n endpoint: \"https://t3.storage.dev\",\n region: \"auto\",\n },\n },\n );\n return db;\n}\n";
|
|
|