@orq-ai/node 4.5.0-rc.9 → 4.5.2

package/packages/orq-rc/src/models/operations/createdatasource.ts

@@ -0,0 +1,437 @@
+/*
+ * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
+ */
+
+import * as z from "zod/v3";
+import { remap as remap$ } from "../../lib/primitives.js";
+import { safeParse } from "../../lib/schemas.js";
+import { ClosedEnum } from "../../types/enums.js";
+import { Result as SafeParseResult } from "../../types/fp.js";
+import { SDKValidationError } from "../errors/sdkvalidationerror.js";
+
+/**
+ * Provides advanced settings for customizing chunking behavior, enabling fine-grained control to better meet specific data processing needs.
+ */
+export type ChunkingConfiguration2 = {
+  type: "advanced";
+  /**
+   * Defines the absolute maximum character length per chunk. Text elements exceeding this size will be automatically split into multiple chunks.
+   */
+  chunkMaxCharacters?: number | undefined;
+  /**
+   * Specifies the number of characters to overlap between consecutive chunks. This overlap helps maintain semantic continuity when splitting large text elements.
+   */
+  chunkOverlap?: number | undefined;
+};
+
+/**
+ * Optimized chunking strategy focusing on speed and avoiding duplication of content chunks.
+ */
+export type ChunkingConfiguration1 = {
+  type: "default";
+};
+
+/**
+ * The chunking configuration settings for the datasource. Defaults to the system's standard chunking configuration if not specified.
+ */
+export type ChunkingConfiguration =
+  | ChunkingConfiguration1
+  | ChunkingConfiguration2;
+
+/**
+ * The cleanup options applied to the datasource content. All options are enabled by default to ensure enhanced security and optimal chunk quality. Defaults to system-standard cleanup options if not specified.
+ */
+export type ChunkingCleanupOptions = {
+  /**
+   * Removes email addresses from the provided text.
+   */
+  deleteEmails?: boolean | undefined;
+  /**
+   * Removes credit card numbers from the provided text.
+   */
+  deleteCreditCards?: boolean | undefined;
+  /**
+   * Removes phone numbers from the provided text.
+   */
+  deletePhoneNumbers?: boolean | undefined;
+  /**
+   * Removes bullet points formatting from the text.
+   */
+  cleanBulletPoints?: boolean | undefined;
+  /**
+   * Removes numbered list formatting from the text.
+   */
+  cleanNumberedList?: boolean | undefined;
+  /**
+   * Normalizes or removes unnecessary unicode characters from the text.
+   */
+  cleanUnicode?: boolean | undefined;
+  /**
+   * Normalizes or removes various dash characters to standardize the text.
+   */
+  cleanDashes?: boolean | undefined;
+  /**
+   * Trims and normalizes excessive whitespace throughout the text.
+   */
+  cleanWhitespaces?: boolean | undefined;
+};
+
+/**
+ * Configuration options specifying how the datasource file is chunked. Required if `file_id` is specified. Defaults to standard chunking options if omitted.
+ */
+export type ChunkingOptions = {
+  /**
+   * The chunking configuration settings for the datasource. Defaults to the system's standard chunking configuration if not specified.
+   */
+  chunkingConfiguration?:
+    | ChunkingConfiguration1
+    | ChunkingConfiguration2
+    | undefined;
+  /**
+   * The cleanup options applied to the datasource content. All options are enabled by default to ensure enhanced security and optimal chunk quality. Defaults to system-standard cleanup options if not specified.
+   */
+  chunkingCleanupOptions?: ChunkingCleanupOptions | undefined;
+};
+
+export type CreateDatasourceRequestBody = {
+  /**
+   * The display name for the datasource visible in the UI. If omitted, the display name is derived from the uploaded file. When both `display_name` and `file_id` are provided, the provided `display_name` is prioritized.
+   */
+  displayName?: string | undefined;
+  /**
+   * The unique identifier of the file used for datasource creation. If provided, the file is immediately queued for chunking.
+   */
+  fileId?: string | undefined;
+  /**
+   * Configuration options specifying how the datasource file is chunked. Required if `file_id` is specified. Defaults to standard chunking options if omitted.
+   */
+  chunkingOptions?: ChunkingOptions | undefined;
+};
+
+export type CreateDatasourceRequest = {
+  /**
+   * The unique identifier of the knowledge base
+   */
+  knowledgeId: string;
+  requestBody: CreateDatasourceRequestBody;
+};
+
+export const CreateDatasourceStatus = {
+  Pending: "pending",
+  Processing: "processing",
+  Completed: "completed",
+  Failed: "failed",
+  Queued: "queued",
+} as const;
+export type CreateDatasourceStatus = ClosedEnum<typeof CreateDatasourceStatus>;
+
+/**
+ * Datasource successfully created
+ */
+export type CreateDatasourceResponseBody = {
+  /**
+   * The unique identifier of the data source
+   */
+  id: string;
+  /**
+   * The display name of the datasource. Normally the name of the uploaded file
+   */
+  displayName: string;
+  /**
+   * The description of the knowledge base
+   */
+  description?: string | undefined;
+  status: CreateDatasourceStatus;
+  /**
+   * The unique identifier of the file used to create the datasource.
+   */
+  fileId?: string | null | undefined;
+  /**
+   * The date and time the datasource was created
+   */
+  created: string;
+  /**
+   * The date and time the datasource was updated
+   */
+  updated: string;
+  /**
+   * The user ID of the creator of the knowledge base
+   */
+  createdById?: string | null | undefined;
+  /**
+   * The user ID of the last user who updated the knowledge base
+   */
+  updateById?: string | null | undefined;
+  /**
+   * The unique identifier of the knowledge base
+   */
+  knowledgeId: string;
+  /**
+   * The number of chunks in the datasource
+   */
+  chunksCount: number;
+};
+
+/** @internal */
+export type ChunkingConfiguration2$Outbound = {
+  type: "advanced";
+  chunk_max_characters: number;
+  chunk_overlap: number;
+};
+
+/** @internal */
+export const ChunkingConfiguration2$outboundSchema: z.ZodType<
+  ChunkingConfiguration2$Outbound,
+  z.ZodTypeDef,
+  ChunkingConfiguration2
+> = z.object({
+  type: z.literal("advanced"),
+  chunkMaxCharacters: z.number().default(500),
+  chunkOverlap: z.number().default(0),
+}).transform((v) => {
+  return remap$(v, {
+    chunkMaxCharacters: "chunk_max_characters",
+    chunkOverlap: "chunk_overlap",
+  });
+});
+
+export function chunkingConfiguration2ToJSON(
+  chunkingConfiguration2: ChunkingConfiguration2,
+): string {
+  return JSON.stringify(
+    ChunkingConfiguration2$outboundSchema.parse(chunkingConfiguration2),
+  );
+}
+
+/** @internal */
+export type ChunkingConfiguration1$Outbound = {
+  type: "default";
+};
+
+/** @internal */
+export const ChunkingConfiguration1$outboundSchema: z.ZodType<
+  ChunkingConfiguration1$Outbound,
+  z.ZodTypeDef,
+  ChunkingConfiguration1
+> = z.object({
+  type: z.literal("default"),
+});
+
+export function chunkingConfiguration1ToJSON(
+  chunkingConfiguration1: ChunkingConfiguration1,
+): string {
+  return JSON.stringify(
+    ChunkingConfiguration1$outboundSchema.parse(chunkingConfiguration1),
+  );
+}
+
+/** @internal */
+export type ChunkingConfiguration$Outbound =
+  | ChunkingConfiguration1$Outbound
+  | ChunkingConfiguration2$Outbound;
+
+/** @internal */
+export const ChunkingConfiguration$outboundSchema: z.ZodType<
+  ChunkingConfiguration$Outbound,
+  z.ZodTypeDef,
+  ChunkingConfiguration
+> = z.union([
+  z.lazy(() => ChunkingConfiguration1$outboundSchema),
+  z.lazy(() => ChunkingConfiguration2$outboundSchema),
+]);
+
+export function chunkingConfigurationToJSON(
+  chunkingConfiguration: ChunkingConfiguration,
+): string {
+  return JSON.stringify(
+    ChunkingConfiguration$outboundSchema.parse(chunkingConfiguration),
+  );
+}
+
+/** @internal */
+export type ChunkingCleanupOptions$Outbound = {
+  delete_emails?: boolean | undefined;
+  delete_credit_cards?: boolean | undefined;
+  delete_phone_numbers?: boolean | undefined;
+  clean_bullet_points?: boolean | undefined;
+  clean_numbered_list?: boolean | undefined;
+  clean_unicode?: boolean | undefined;
+  clean_dashes?: boolean | undefined;
+  clean_whitespaces?: boolean | undefined;
+};
+
+/** @internal */
+export const ChunkingCleanupOptions$outboundSchema: z.ZodType<
+  ChunkingCleanupOptions$Outbound,
+  z.ZodTypeDef,
+  ChunkingCleanupOptions
+> = z.object({
+  deleteEmails: z.boolean().optional(),
+  deleteCreditCards: z.boolean().optional(),
+  deletePhoneNumbers: z.boolean().optional(),
+  cleanBulletPoints: z.boolean().optional(),
+  cleanNumberedList: z.boolean().optional(),
+  cleanUnicode: z.boolean().optional(),
+  cleanDashes: z.boolean().optional(),
+  cleanWhitespaces: z.boolean().optional(),
+}).transform((v) => {
+  return remap$(v, {
+    deleteEmails: "delete_emails",
+    deleteCreditCards: "delete_credit_cards",
+    deletePhoneNumbers: "delete_phone_numbers",
+    cleanBulletPoints: "clean_bullet_points",
+    cleanNumberedList: "clean_numbered_list",
+    cleanUnicode: "clean_unicode",
+    cleanDashes: "clean_dashes",
+    cleanWhitespaces: "clean_whitespaces",
+  });
+});
+
+export function chunkingCleanupOptionsToJSON(
+  chunkingCleanupOptions: ChunkingCleanupOptions,
+): string {
+  return JSON.stringify(
+    ChunkingCleanupOptions$outboundSchema.parse(chunkingCleanupOptions),
+  );
+}
+
+/** @internal */
+export type ChunkingOptions$Outbound = {
+  chunking_configuration?:
+    | ChunkingConfiguration1$Outbound
+    | ChunkingConfiguration2$Outbound
+    | undefined;
+  chunking_cleanup_options?: ChunkingCleanupOptions$Outbound | undefined;
+};
+
+/** @internal */
+export const ChunkingOptions$outboundSchema: z.ZodType<
+  ChunkingOptions$Outbound,
+  z.ZodTypeDef,
+  ChunkingOptions
+> = z.object({
+  chunkingConfiguration: z.union([
+    z.lazy(() => ChunkingConfiguration1$outboundSchema),
+    z.lazy(() => ChunkingConfiguration2$outboundSchema),
+  ]).optional(),
+  chunkingCleanupOptions: z.lazy(() => ChunkingCleanupOptions$outboundSchema)
+    .optional(),
+}).transform((v) => {
+  return remap$(v, {
+    chunkingConfiguration: "chunking_configuration",
+    chunkingCleanupOptions: "chunking_cleanup_options",
+  });
+});
+
+export function chunkingOptionsToJSON(
+  chunkingOptions: ChunkingOptions,
+): string {
+  return JSON.stringify(ChunkingOptions$outboundSchema.parse(chunkingOptions));
+}
+
+/** @internal */
+export type CreateDatasourceRequestBody$Outbound = {
+  display_name?: string | undefined;
+  file_id?: string | undefined;
+  chunking_options?: ChunkingOptions$Outbound | undefined;
+};
+
+/** @internal */
+export const CreateDatasourceRequestBody$outboundSchema: z.ZodType<
+  CreateDatasourceRequestBody$Outbound,
+  z.ZodTypeDef,
+  CreateDatasourceRequestBody
+> = z.object({
+  displayName: z.string().optional(),
+  fileId: z.string().optional(),
+  chunkingOptions: z.lazy(() => ChunkingOptions$outboundSchema).optional(),
+}).transform((v) => {
+  return remap$(v, {
+    displayName: "display_name",
+    fileId: "file_id",
+    chunkingOptions: "chunking_options",
+  });
+});
+
+export function createDatasourceRequestBodyToJSON(
+  createDatasourceRequestBody: CreateDatasourceRequestBody,
+): string {
+  return JSON.stringify(
+    CreateDatasourceRequestBody$outboundSchema.parse(
+      createDatasourceRequestBody,
+    ),
+  );
+}
+
+/** @internal */
+export type CreateDatasourceRequest$Outbound = {
+  knowledge_id: string;
+  RequestBody: CreateDatasourceRequestBody$Outbound;
+};
+
+/** @internal */
+export const CreateDatasourceRequest$outboundSchema: z.ZodType<
+  CreateDatasourceRequest$Outbound,
+  z.ZodTypeDef,
+  CreateDatasourceRequest
+> = z.object({
+  knowledgeId: z.string(),
+  requestBody: z.lazy(() => CreateDatasourceRequestBody$outboundSchema),
+}).transform((v) => {
+  return remap$(v, {
+    knowledgeId: "knowledge_id",
+    requestBody: "RequestBody",
+  });
+});
+
+export function createDatasourceRequestToJSON(
+  createDatasourceRequest: CreateDatasourceRequest,
+): string {
+  return JSON.stringify(
+    CreateDatasourceRequest$outboundSchema.parse(createDatasourceRequest),
+  );
+}
+
+/** @internal */
+export const CreateDatasourceStatus$inboundSchema: z.ZodNativeEnum<
+  typeof CreateDatasourceStatus
+> = z.nativeEnum(CreateDatasourceStatus);
+
+/** @internal */
+export const CreateDatasourceResponseBody$inboundSchema: z.ZodType<
+  CreateDatasourceResponseBody,
+  z.ZodTypeDef,
+  unknown
+> = z.object({
+  _id: z.string().default("01KKCE2SSA6X4S746DDE3RG6ZP"),
+  display_name: z.string(),
+  description: z.string().optional(),
+  status: CreateDatasourceStatus$inboundSchema,
+  file_id: z.nullable(z.string()).optional(),
+  created: z.string(),
+  updated: z.string(),
+  created_by_id: z.nullable(z.string()).optional(),
+  update_by_id: z.nullable(z.string()).optional(),
+  knowledge_id: z.string(),
+  chunks_count: z.number(),
+}).transform((v) => {
+  return remap$(v, {
+    "_id": "id",
+    "display_name": "displayName",
+    "file_id": "fileId",
+    "created_by_id": "createdById",
+    "update_by_id": "updateById",
+    "knowledge_id": "knowledgeId",
+    "chunks_count": "chunksCount",
+  });
+});
+
+export function createDatasourceResponseBodyFromJSON(
+  jsonString: string,
+): SafeParseResult<CreateDatasourceResponseBody, SDKValidationError> {
+  return safeParse(
+    jsonString,
+    (x) => CreateDatasourceResponseBody$inboundSchema.parse(JSON.parse(x)),
+    `Failed to parse 'CreateDatasourceResponseBody' from JSON`,
+  );
+}