@botpress/api 0.50.0 → 0.50.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/dist/index.js CHANGED
@@ -292278,38 +292278,50 @@ var state = {
292278
292278
  "type": "object",
292279
292279
  "properties": {
292280
292280
  "parsing": {
292281
- "default": {},
292282
292281
  "type": "object",
292283
292282
  "properties": {
292284
292283
  "minimumParagraphLength": {
292285
- "default": 500,
292286
292284
  "type": "integer",
292287
292285
  "minimum": 50,
292288
- "maximum": 2e3
292286
+ "maximum": 2e3,
292287
+ "description": "The minimum length a standalone paragraph should have. If a paragraph is shorter than this, it will be merged with the next immediate paragraph."
292288
+ },
292289
+ "smartCleanup": {
292290
+ "type": "boolean",
292291
+ "description": "(Team/Enterprise plan only, charged as AI Spend) Enabling this will use a lightweight/inexpensive LLM to clean up the extracted content of PDF files before indexing them to increase the quality of the stored vectors, as PDFs often store raw text in unusual ways which when extracted may result in formatting issues (e.g. broken sentences/paragraphs, unexpected headings, garbled characters, etc.) that can affect retrieval performance for certain user queries if left untouched.\n\nNotes:\n- This feature is only available in Team and Enterprise plans.\n- This feature is only available for PDF files. If the file isn't a PDF, this setting will be ignored and no AI Spend will be incurred.\n- We recommend using this feature for PDFs that have custom layouts or design. For simple text-based PDFs like documents and books, this feature is usually not necessary.\n- The smart cleanup takes some time to perform due to the LLM calls involved, so enabling it will increase the total time it takes to index the file.\n- We take steps to prevent the original text from being fundamentally changed but due to the nature of LLMs this could theoretically still happen so it's recommended to review the passages generated for the file after indexing to ensure the content is still accurate.\n- This feature is limited to the first 30 pages or 20 KB of text in the PDF file (whichever comes first). If the file has more content than these limits then the rest of the file will be indexed as-is without any cleanup. If you need to clean up the content of the entire file, consider splitting it into smaller files."
292289
292292
  }
292290
292293
  },
292291
292294
  "additionalProperties": false
292292
292295
  },
292293
292296
  "chunking": {
292294
- "default": {},
292295
292297
  "type": "object",
292296
292298
  "properties": {
292297
292299
  "maximumChunkLength": {
292298
- "default": 1250,
292299
292300
  "type": "integer",
292300
292301
  "minimum": 100,
292301
- "maximum": 5e3
292302
+ "maximum": 5e3,
292303
+ "description": "The maximum length of a chunk in characters."
292304
+ },
292305
+ "embeddedContextLevels": {
292306
+ "type": "integer",
292307
+ "minimum": 0,
292308
+ "maximum": 3,
292309
+ "description": "The number of surrounding context levels to include in the vector embedding of the chunk."
292310
+ },
292311
+ "embedBreadcrumb": {
292312
+ "type": "boolean",
292313
+ "description": "Include the breadcrumb of the chunk in the vector embedding."
292302
292314
  }
292303
292315
  },
292304
292316
  "additionalProperties": false
292305
292317
  },
292306
292318
  "summarization": {
292307
- "default": {},
292308
292319
  "type": "object",
292309
292320
  "properties": {
292310
292321
  "enable": {
292311
292322
  "default": false,
292312
- "type": "boolean"
292323
+ "type": "boolean",
292324
+ "description": "(Team/Enterprise plan only, charged as AI Spend) Create summaries for this file and index them as standalone vectors. Enabling this option will incur in AI Spend cost (charged to the workspace of the bot) to generate the summaries based on the amount of content in the file and the summarization model used.\n\nPlease note that this feature is only available in Team and Enterprise plans."
292313
292325
  },
292314
292326
  "modelType": {
292315
292327
  "default": "balanced",
@@ -292318,23 +292330,24 @@ var state = {
292318
292330
  "inexpensive",
292319
292331
  "balanced",
292320
292332
  "accurate"
292321
- ]
292333
+ ],
292334
+ "description": "The model type to use for summarization."
292322
292335
  },
292323
292336
  "minimumInputLength": {
292324
- "default": 3e3,
292325
292337
  "type": "integer",
292326
292338
  "minimum": 1e3,
292327
- "maximum": 1e4
292339
+ "maximum": 1e4,
292340
+ "description": "The minimum length a section of the file should have to create a summary of it."
292328
292341
  },
292329
292342
  "outputTokenLimit": {
292330
- "default": 2e3,
292331
292343
  "type": "integer",
292332
292344
  "minimum": 1e3,
292333
- "maximum": 1e4
292345
+ "maximum": 1e4,
292346
+ "description": "The maximum length of a summary (in tokens)."
292334
292347
  },
292335
292348
  "generateMasterSummary": {
292336
- "default": true,
292337
- "type": "boolean"
292349
+ "type": "boolean",
292350
+ "description": "Generate a summary of the entire file and index it as a standalone vector."
292338
292351
  }
292339
292352
  },
292340
292353
  "additionalProperties": false
@@ -294155,7 +294168,7 @@ var state = {
294155
294168
  "title": "Botpress API",
294156
294169
  "description": "API for Botpress Cloud",
294157
294170
  "server": "https://api.botpress.cloud",
294158
- "version": "0.50.0",
294171
+ "version": "0.50.2",
294159
294172
  "prefix": "v1"
294160
294173
  },
294161
294174
  "errors": [
@@ -9264,59 +9264,72 @@ export declare const state: {
9264
9264
  type: "object";
9265
9265
  properties: {
9266
9266
  parsing: {
9267
- default: {};
9268
9267
  type: "object";
9269
9268
  properties: {
9270
9269
  minimumParagraphLength: {
9271
- default: number;
9272
9270
  type: "integer";
9273
9271
  minimum: number;
9274
9272
  maximum: number;
9273
+ description: string;
9274
+ };
9275
+ smartCleanup: {
9276
+ type: "boolean";
9277
+ description: string;
9275
9278
  };
9276
9279
  };
9277
9280
  additionalProperties: false;
9278
9281
  };
9279
9282
  chunking: {
9280
- default: {};
9281
9283
  type: "object";
9282
9284
  properties: {
9283
9285
  maximumChunkLength: {
9284
- default: number;
9285
9286
  type: "integer";
9286
9287
  minimum: number;
9287
9288
  maximum: number;
9289
+ description: string;
9290
+ };
9291
+ embeddedContextLevels: {
9292
+ type: "integer";
9293
+ minimum: number;
9294
+ maximum: number;
9295
+ description: string;
9296
+ };
9297
+ embedBreadcrumb: {
9298
+ type: "boolean";
9299
+ description: string;
9288
9300
  };
9289
9301
  };
9290
9302
  additionalProperties: false;
9291
9303
  };
9292
9304
  summarization: {
9293
- default: {};
9294
9305
  type: "object";
9295
9306
  properties: {
9296
9307
  enable: {
9297
9308
  default: boolean;
9298
9309
  type: "boolean";
9310
+ description: string;
9299
9311
  };
9300
9312
  modelType: {
9301
9313
  default: string;
9302
9314
  type: "string";
9303
9315
  enum: string[];
9316
+ description: string;
9304
9317
  };
9305
9318
  minimumInputLength: {
9306
- default: number;
9307
9319
  type: "integer";
9308
9320
  minimum: number;
9309
9321
  maximum: number;
9322
+ description: string;
9310
9323
  };
9311
9324
  outputTokenLimit: {
9312
- default: number;
9313
9325
  type: "integer";
9314
9326
  minimum: number;
9315
9327
  maximum: number;
9328
+ description: string;
9316
9329
  };
9317
9330
  generateMasterSummary: {
9318
- default: boolean;
9319
9331
  type: "boolean";
9332
+ description: string;
9320
9333
  };
9321
9334
  };
9322
9335
  additionalProperties: false;
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@botpress/api",
3
- "version": "0.50.0",
3
+ "version": "0.50.2",
4
4
  "main": "dist/index.js",
5
5
  "types": "dist/src/index.d.ts",
6
6
  "scripts": {