@lancedb/lancedb 0.14.0-beta.2 → 0.14.1-beta.0

package/dist/merge.js

@@ -0,0 +1,64 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.MergeInsertBuilder = void 0;
+const arrow_1 = require("./arrow");
+/** A builder used to create and run a merge insert operation */
+class MergeInsertBuilder {
+    #native;
+    /** Construct a MergeInsertBuilder. __Internal use only.__ */
+    constructor(native) {
+        this.#native = native;
+    }
+    /**
+     * Rows that exist in both the source table (new data) and
+     * the target table (old data) will be updated, replacing
+     * the old row with the corresponding matching row.
+     *
+     * If there are multiple matches then the behavior is undefined.
+     * Currently this causes multiple copies of the row to be created
+     * but that behavior is subject to change.
+     *
+     * An optional condition may be specified.  If it is, then only
+     * matched rows that satisfy the condtion will be updated.  Any
+     * rows that do not satisfy the condition will be left as they
+     * are.  Failing to satisfy the condition does not cause a
+     * "matched row" to become a "not matched" row.
+     *
+     * The condition should be an SQL string.  Use the prefix
+     * target. to refer to rows in the target table (old data)
+     * and the prefix source. to refer to rows in the source
+     * table (new data).
+     *
+     * For example, "target.last_update < source.last_update"
+     */
+    whenMatchedUpdateAll(options) {
+        return new MergeInsertBuilder(this.#native.whenMatchedUpdateAll(options?.where));
+    }
+    /**
+     * Rows that exist only in the source table (new data) should
+     * be inserted into the target table.
+     */
+    whenNotMatchedInsertAll() {
+        return new MergeInsertBuilder(this.#native.whenNotMatchedInsertAll());
+    }
+    /**
+     * Rows that exist only in the target table (old data) will be
+     * deleted.  An optional condition can be provided to limit what
+     * data is deleted.
+     *
+     * @param options.where - An optional condition to limit what data is deleted
+     */
+    whenNotMatchedBySourceDelete(options) {
+        return new MergeInsertBuilder(this.#native.whenNotMatchedBySourceDelete(options?.where));
+    }
+    /**
+     * Executes the merge insert operation
+     *
+     * Nothing is returned but the `Table` is updated
+     */
+    async execute(data) {
+        const buffer = await (0, arrow_1.fromDataToBuffer)(data);
+        await this.#native.execute(buffer);
+    }
+}
+exports.MergeInsertBuilder = MergeInsertBuilder;

package/dist/native.d.ts

@@ -0,0 +1,340 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/* auto-generated by NAPI-RS */
+
+/** Timeout configuration for remote HTTP client. */
+export interface TimeoutConfig {
+  /**
+   * The timeout for establishing a connection in seconds. Default is 120
+   * seconds (2 minutes). This can also be set via the environment variable
+   * `LANCE_CLIENT_CONNECT_TIMEOUT`, as an integer number of seconds.
+   */
+  connectTimeout?: number
+  /**
+   * The timeout for reading data from the server in seconds. Default is 300
+   * seconds (5 minutes). This can also be set via the environment variable
+   * `LANCE_CLIENT_READ_TIMEOUT`, as an integer number of seconds.
+   */
+  readTimeout?: number
+  /**
+   * The timeout for keeping idle connections in the connection pool in seconds.
+   * Default is 300 seconds (5 minutes). This can also be set via the
+   * environment variable `LANCE_CLIENT_CONNECTION_TIMEOUT`, as an integer
+   * number of seconds.
+   */
+  poolIdleTimeout?: number
+}
+/** Retry configuration for the remote HTTP client. */
+export interface RetryConfig {
+  /**
+   * The maximum number of retries for a request. Default is 3. You can also
+   * set this via the environment variable `LANCE_CLIENT_MAX_RETRIES`.
+   */
+  retries?: number
+  /**
+   * The maximum number of retries for connection errors. Default is 3. You
+   * can also set this via the environment variable `LANCE_CLIENT_CONNECT_RETRIES`.
+   */
+  connectRetries?: number
+  /**
+   * The maximum number of retries for read errors. Default is 3. You can also
+   * set this via the environment variable `LANCE_CLIENT_READ_RETRIES`.
+   */
+  readRetries?: number
+  /**
+   * The backoff factor to apply between retries. Default is 0.25. Between each retry
+   * the client will wait for the amount of seconds:
+   * `{backoff factor} * (2 ** ({number of previous retries}))`. So for the default
+   * of 0.25, the first retry will wait 0.25 seconds, the second retry will wait 0.5
+   * seconds, the third retry will wait 1 second, etc.
+   *
+   * You can also set this via the environment variable
+   * `LANCE_CLIENT_RETRY_BACKOFF_FACTOR`.
+   */
+  backoffFactor?: number
+  /**
+   * The jitter to apply to the backoff factor, in seconds. Default is 0.25.
+   *
+   * A random value between 0 and `backoff_jitter` will be added to the backoff
+   * factor in seconds. So for the default of 0.25 seconds, between 0 and 250
+   * milliseconds will be added to the sleep between each retry.
+   *
+   * You can also set this via the environment variable
+   * `LANCE_CLIENT_RETRY_BACKOFF_JITTER`.
+   */
+  backoffJitter?: number
+  /**
+   * The HTTP status codes for which to retry the request. Default is
+   * [429, 500, 502, 503].
+   *
+   * You can also set this via the environment variable
+   * `LANCE_CLIENT_RETRY_STATUSES`. Use a comma-separated list of integers.
+   */
+  statuses?: Array<number>
+}
+export interface ClientConfig {
+  userAgent?: string
+  retryConfig?: RetryConfig
+  timeoutConfig?: TimeoutConfig
+}
+/** A description of an index currently configured on a column */
+export interface IndexConfig {
+  /** The name of the index */
+  name: string
+  /** The type of the index */
+  indexType: string
+  /**
+   * The columns in the index
+   *
+   * Currently this is always an array of size 1. In the future there may
+   * be more columns to represent composite indices.
+   */
+  columns: Array<string>
+}
+/** Statistics about a compaction operation. */
+export interface CompactionStats {
+  /** The number of fragments removed */
+  fragmentsRemoved: number
+  /** The number of new, compacted fragments added */
+  fragmentsAdded: number
+  /** The number of data files removed */
+  filesRemoved: number
+  /** The number of new, compacted data files added */
+  filesAdded: number
+}
+/** Statistics about a cleanup operation */
+export interface RemovalStats {
+  /** The number of bytes removed */
+  bytesRemoved: number
+  /** The number of old versions removed */
+  oldVersionsRemoved: number
+}
+/** Statistics about an optimize operation */
+export interface OptimizeStats {
+  /** Statistics about the compaction operation */
+  compaction: CompactionStats
+  /** Statistics about the removal operation */
+  prune: RemovalStats
+}
+/**
+ *  A definition of a column alteration. The alteration changes the column at
+ * `path` to have the new name `name`, to be nullable if `nullable` is true,
+ * and to have the data type `data_type`. At least one of `rename` or `nullable`
+ * must be provided.
+ */
+export interface ColumnAlteration {
+  /**
+   * The path to the column to alter. This is a dot-separated path to the column.
+   * If it is a top-level column then it is just the name of the column. If it is
+   * a nested column then it is the path to the column, e.g. "a.b.c" for a column
+   * `c` nested inside a column `b` nested inside a column `a`.
+   */
+  path: string
+  /**
+   * The new name of the column. If not provided then the name will not be changed.
+   * This must be distinct from the names of all other columns in the table.
+   */
+  rename?: string
+  /**
+   * A new data type for the column. If not provided then the data type will not be changed.
+   * Changing data types is limited to casting to the same general type. For example, these
+   * changes are valid:
+   * * `int32` -> `int64` (integers)
+   * * `double` -> `float` (floats)
+   * * `string` -> `large_string` (strings)
+   * But these changes are not:
+   * * `int32` -> `double` (mix integers and floats)
+   * * `string` -> `int32` (mix strings and integers)
+   */
+  dataType?: string
+  /** Set the new nullability. Note that a nullable column cannot be made non-nullable. */
+  nullable?: boolean
+}
+/** A definition of a new column to add to a table. */
+export interface AddColumnsSql {
+  /** The name of the new column. */
+  name: string
+  /**
+   * The values to populate the new column with, as a SQL expression.
+   * The expression can reference other columns in the table.
+   */
+  valueSql: string
+}
+export interface IndexStatistics {
+  /** The number of rows indexed by the index */
+  numIndexedRows: number
+  /** The number of rows not indexed */
+  numUnindexedRows: number
+  /** The type of the index */
+  indexType: string
+  /**
+   * The type of the distance function used by the index. This is only
+   * present for vector indices. Scalar and full text search indices do
+   * not have a distance function.
+   */
+  distanceType?: string
+  /** The number of parts this index is split into. */
+  numIndices?: number
+}
+export interface Version {
+  version: number
+  timestamp: number
+  metadata: Record<string, string>
+}
+export interface ConnectionOptions {
+  /**
+   * (For LanceDB OSS only): The interval, in seconds, at which to check for
+   * updates to the table from other processes. If None, then consistency is not
+   * checked. For performance reasons, this is the default. For strong
+   * consistency, set this to zero seconds. Then every read will check for
+   * updates from other processes. As a compromise, you can set this to a
+   * non-zero value for eventual consistency. If more than that interval
+   * has passed since the last check, then the table will be checked for updates.
+   * Note: this consistency only applies to read operations. Write operations are
+   * always consistent.
+   */
+  readConsistencyInterval?: number
+  /**
+   * (For LanceDB OSS only): configuration for object storage.
+   *
+   * The available options are described at https://lancedb.github.io/lancedb/guides/storage/
+   */
+  storageOptions?: Record<string, string>
+  /** (For LanceDB cloud only): configuration for the remote HTTP client. */
+  clientConfig?: ClientConfig
+  /**
+   * (For LanceDB cloud only): the API key to use with LanceDB Cloud.
+   *
+   * Can also be set via the environment variable `LANCEDB_API_KEY`.
+   */
+  apiKey?: string
+  /**
+   * (For LanceDB cloud only): the region to use for LanceDB cloud.
+   * Defaults to 'us-east-1'.
+   */
+  region?: string
+  /**
+   * (For LanceDB cloud only): the host to use for LanceDB cloud. Used
+   * for testing purposes.
+   */
+  hostOverride?: string
+}
+/** Write mode for writing a table. */
+export enum WriteMode {
+  Create = 'Create',
+  Append = 'Append',
+  Overwrite = 'Overwrite'
+}
+/** Write options when creating a Table. */
+export interface WriteOptions {
+  /** Write mode for writing to a table. */
+  mode?: WriteMode
+}
+export interface OpenTableOptions {
+  storageOptions?: Record<string, string>
+}
+export class Connection {
+  /** Create a new Connection instance from the given URI. */
+  static new(uri: string, options: ConnectionOptions): Promise<Connection>
+  display(): string
+  isOpen(): boolean
+  close(): void
+  /** List all tables in the dataset. */
+  tableNames(startAfter?: string | undefined | null, limit?: number | undefined | null): Promise<Array<string>>
+  /**
+   * Create table from a Apache Arrow IPC (file) buffer.
+   *
+   * Parameters:
+   * - name: The name of the table.
+   * - buf: The buffer containing the IPC file.
+   *
+   */
+  createTable(name: string, buf: Buffer, mode: string, storageOptions?: Record<string, string> | undefined | null, dataStorageOptions?: string | undefined | null, enableV2ManifestPaths?: boolean | undefined | null): Promise<Table>
+  createEmptyTable(name: string, schemaBuf: Buffer, mode: string, storageOptions?: Record<string, string> | undefined | null, dataStorageOptions?: string | undefined | null, enableV2ManifestPaths?: boolean | undefined | null): Promise<Table>
+  openTable(name: string, storageOptions?: Record<string, string> | undefined | null, indexCacheSize?: number | undefined | null): Promise<Table>
+  /** Drop table with the name. Or raise an error if the table does not exist. */
+  dropTable(name: string): Promise<void>
+}
+export class Index {
+  static ivfPq(distanceType?: string | undefined | null, numPartitions?: number | undefined | null, numSubVectors?: number | undefined | null, maxIterations?: number | undefined | null, sampleRate?: number | undefined | null): Index
+  static btree(): Index
+  static bitmap(): Index
+  static labelList(): Index
+  static fts(withPosition?: boolean | undefined | null): Index
+  static hnswPq(distanceType?: string | undefined | null, numPartitions?: number | undefined | null, numSubVectors?: number | undefined | null, maxIterations?: number | undefined | null, sampleRate?: number | undefined | null, m?: number | undefined | null, efConstruction?: number | undefined | null): Index
+  static hnswSq(distanceType?: string | undefined | null, numPartitions?: number | undefined | null, maxIterations?: number | undefined | null, sampleRate?: number | undefined | null, m?: number | undefined | null, efConstruction?: number | undefined | null): Index
+}
+/** Typescript-style Async Iterator over RecordBatches  */
+export class RecordBatchIterator {
+  next(): Promise<Buffer | null>
+}
+/** A builder used to create and run a merge insert operation */
+export class NativeMergeInsertBuilder {
+  whenMatchedUpdateAll(condition?: string | undefined | null): NativeMergeInsertBuilder
+  whenNotMatchedInsertAll(): NativeMergeInsertBuilder
+  whenNotMatchedBySourceDelete(filter?: string | undefined | null): NativeMergeInsertBuilder
+  execute(buf: Buffer): Promise<void>
+}
+export class Query {
+  onlyIf(predicate: string): void
+  fullTextSearch(query: string, columns?: Array<string> | undefined | null): void
+  select(columns: Array<[string, string]>): void
+  selectColumns(columns: Array<string>): void
+  limit(limit: number): void
+  offset(offset: number): void
+  nearestTo(vector: Float32Array): VectorQuery
+  fastSearch(): void
+  withRowId(): void
+  execute(maxBatchLength?: number | undefined | null): Promise<RecordBatchIterator>
+  explainPlan(verbose: boolean): Promise<string>
+}
+export class VectorQuery {
+  column(column: string): void
+  addQueryVector(vector: Float32Array): void
+  distanceType(distanceType: string): void
+  postfilter(): void
+  refineFactor(refineFactor: number): void
+  nprobes(nprobe: number): void
+  ef(ef: number): void
+  bypassVectorIndex(): void
+  onlyIf(predicate: string): void
+  fullTextSearch(query: string, columns?: Array<string> | undefined | null): void
+  select(columns: Array<[string, string]>): void
+  selectColumns(columns: Array<string>): void
+  limit(limit: number): void
+  offset(offset: number): void
+  fastSearch(): void
+  withRowId(): void
+  execute(maxBatchLength?: number | undefined | null): Promise<RecordBatchIterator>
+  explainPlan(verbose: boolean): Promise<string>
+}
+export class Table {
+  name: string
+  display(): string
+  isOpen(): boolean
+  close(): void
+  /** Return Schema as empty Arrow IPC file. */
+  schema(): Promise<Buffer>
+  add(buf: Buffer, mode: string): Promise<void>
+  countRows(filter?: string | undefined | null): Promise<number>
+  delete(predicate: string): Promise<void>
+  createIndex(index: Index | undefined | null, column: string, replace?: boolean | undefined | null): Promise<void>
+  update(onlyIf: string | undefined | null, columns: Array<[string, string]>): Promise<bigint>
+  query(): Query
+  vectorSearch(vector: Float32Array): VectorQuery
+  addColumns(transforms: Array<AddColumnsSql>): Promise<void>
+  alterColumns(alterations: Array<ColumnAlteration>): Promise<void>
+  dropColumns(columns: Array<string>): Promise<void>
+  version(): Promise<number>
+  checkout(version: number): Promise<void>
+  checkoutLatest(): Promise<void>
+  listVersions(): Promise<Array<Version>>
+  restore(): Promise<void>
+  optimize(olderThanMs?: number | undefined | null, deleteUnverified?: boolean | undefined | null): Promise<OptimizeStats>
+  listIndices(): Promise<Array<IndexConfig>>
+  indexStats(indexName: string): Promise<IndexStatistics | null>
+  mergeInsert(on: Array<string>): NativeMergeInsertBuilder
+  usesV2ManifestPaths(): Promise<boolean>
+  migrateManifestPathsV2(): Promise<void>
+}