@mastra/rag 0.0.2-alpha.7 → 0.0.2-alpha.70

package/CHANGELOG.md

@@ -1,5 +1,490 @@
 # @mastra/rag
 
+## 0.0.2-alpha.70
+
+### Patch Changes
+
+- 327ece7: Updates for ts versions
+- Updated dependencies [327ece7]
+  - @mastra/core@0.1.27-alpha.80
+
+## 0.0.2-alpha.69
+
+### Patch Changes
+
+- 21fe536: add keyword tags for packages and update readmes
+- Updated dependencies [21fe536]
+  - @mastra/core@0.1.27-alpha.79
+
+## 0.0.2-alpha.68
+
+### Patch Changes
+
+- 685108a: Remove syncs and excess rag
+- Updated dependencies [685108a]
+- Updated dependencies [685108a]
+  - @mastra/core@0.1.27-alpha.78
+
+## 0.0.2-alpha.67
+
+### Patch Changes
+
+- 8105fae: Split embed into embed and embedMany to handle different return types
+- ecdee97: Update return type for chunk to Chunk[]
+- Updated dependencies [8105fae]
+  - @mastra/core@0.1.27-alpha.77
+
+## 0.0.2-alpha.66
+
+### Patch Changes
+
+- 9c0d010: Deprecated Reranker in favor of rerank function (BREAKING CHANGE)
+
+## 0.0.2-alpha.65
+
+### Patch Changes
+
+- Updated dependencies [ae7bf94]
+- Updated dependencies [ae7bf94]
+  - @mastra/core@0.1.27-alpha.76
+
+## 0.0.2-alpha.64
+
+### Patch Changes
+
+- Updated dependencies [23dcb23]
+  - @mastra/core@0.1.27-alpha.75
+
+## 0.0.2-alpha.63
+
+### Patch Changes
+
+- Updated dependencies [7b87567]
+  - @mastra/core@0.1.27-alpha.74
+
+## 0.0.2-alpha.62
+
+### Patch Changes
+
+- Updated dependencies [3427b95]
+  - @mastra/core@0.1.27-alpha.73
+
+## 0.0.2-alpha.61
+
+### Patch Changes
+
+- Updated dependencies [e4d4ede]
+- Updated dependencies [06b2c0a]
+  - @mastra/core@0.1.27-alpha.72
+
+## 0.0.2-alpha.60
+
+### Patch Changes
+
+- Updated dependencies [d9c8dd0]
+  - @mastra/core@0.1.27-alpha.71
+
+## 0.0.2-alpha.59
+
+### Patch Changes
+
+- bdaf834: publish packages
+
+## 0.0.2-alpha.58
+
+### Patch Changes
+
+- Updated dependencies [dd6d87f]
+- Updated dependencies [04434b6]
+  - @mastra/core@0.1.27-alpha.70
+
+## 0.0.2-alpha.57
+
+### Patch Changes
+
+- ab1dc59: Add Cloudflare vectorize
+- 4769753: Added turso/libsql support for RAG
+
+## 0.0.2-alpha.56
+
+### Patch Changes
+
+- ee856f3: Updated pg filter function and updated docs and example
+- c3047a7: Added tests
+
+## 0.0.2-alpha.55
+
+### Patch Changes
+
+- 1944807: Unified logger and major step in better logs
+- Updated dependencies [1944807]
+- Updated dependencies [9ade36e]
+  - @mastra/core@0.1.27-alpha.69
+
+## 0.0.2-alpha.54
+
+### Patch Changes
+
+- Updated dependencies [0be7181]
+- Updated dependencies [0be7181]
+  - @mastra/core@0.1.27-alpha.68
+
+## 0.0.2-alpha.53
+
+### Patch Changes
+
+- Updated dependencies [c8ff2f5]
+  - @mastra/core@0.1.27-alpha.67
+
+## 0.0.2-alpha.52
+
+### Patch Changes
+
+- Updated dependencies [14064f2]
+  - @mastra/core@0.1.27-alpha.66
+
+## 0.0.2-alpha.51
+
+### Patch Changes
+
+- Updated dependencies [e66643a]
+  - @mastra/core@0.1.27-alpha.65
+
+## 0.0.2-alpha.50
+
+### Patch Changes
+
+- 1616f70: Added transaction handling to pgvector
+
+## 0.0.2-alpha.49
+
+### Patch Changes
+
+- Updated dependencies [f368477]
+- Updated dependencies [d5ec619]
+  - @mastra/core@0.1.27-alpha.64
+
+## 0.0.2-alpha.48
+
+### Patch Changes
+
+- 5826db3: Updated reference docs and exports for Reranker and GraphRag
+
+## 0.0.2-alpha.47
+
+### Patch Changes
+
+- Updated dependencies [e097800]
+  - @mastra/core@0.1.27-alpha.63
+
+## 0.0.2-alpha.46
+
+### Patch Changes
+
+- Updated dependencies [93a3719]
+  - @mastra/core@0.1.27-alpha.62
+
+## 0.0.2-alpha.45
+
+### Patch Changes
+
+- Updated dependencies [dc90663]
+  - @mastra/core@0.1.27-alpha.61
+
+## 0.0.2-alpha.44
+
+### Patch Changes
+
+- 3967e69: Added GraphRAG implementation and updated docs
+- Updated dependencies [3967e69]
+  - @mastra/core@0.1.27-alpha.60
+
+## 0.0.2-alpha.43
+
+### Patch Changes
+
+- Updated dependencies [b524c22]
+  - @mastra/core@0.1.27-alpha.59
+
+## 0.0.2-alpha.42
+
+### Patch Changes
+
+- 1874f40: Added re ranking tool to RAG
+- Updated dependencies [1874f40]
+- Updated dependencies [4b1ce2c]
+  - @mastra/core@0.1.27-alpha.58
+
+## 0.0.2-alpha.41
+
+### Patch Changes
+
+- 7de6d71: Update filter for vector query to work with more stores
+- Updated dependencies [fd494a3]
+  - @mastra/core@0.1.27-alpha.57
+
+## 0.0.2-alpha.40
+
+### Patch Changes
+
+- ae638a4: make useFilter option optional
+- Updated dependencies [9f3ab05]
+  - @mastra/core@0.1.27-alpha.56
+
+## 0.0.2-alpha.39
+
+### Patch Changes
+
+- 592e3cf: Add custom rag tools, add vector retrieval, and update docs
+- 837a288: MAJOR Revamp of tools, workflows, syncs.
+- 0b74006: Workflow updates
+- Updated dependencies [592e3cf]
+- Updated dependencies [837a288]
+- Updated dependencies [0b74006]
+  - @mastra/core@0.1.27-alpha.55
+
+## 0.0.2-alpha.38
+
+### Patch Changes
+
+- eb45d76: Updated PG Vector filter and added rag examples in docs
+- Updated dependencies [d2cd535]
+  - @mastra/core@0.1.27-alpha.54
+
+## 0.0.2-alpha.37
+
+### Patch Changes
+
+- Updated dependencies [8e7814f]
+  - @mastra/core@0.1.27-alpha.53
+
+## 0.0.2-alpha.36
+
+### Patch Changes
+
+- Updated dependencies [eedb829]
+  - @mastra/core@0.1.27-alpha.52
+
+## 0.0.2-alpha.35
+
+### Patch Changes
+
+- Updated dependencies [a7b016d]
+- Updated dependencies [da2e8d3]
+- Updated dependencies [538a136]
+  - @mastra/core@0.1.27-alpha.51
+
+## 0.0.2-alpha.34
+
+### Patch Changes
+
+- Updated dependencies [401a4d9]
+  - @mastra/core@0.1.27-alpha.50
+
+## 0.0.2-alpha.33
+
+### Patch Changes
+
+- a621c34: Add validation for indexName in pgVector and dimension for all vector dbs
+- Updated dependencies [79acad0]
+- Updated dependencies [f5dfa20]
+  - @mastra/core@0.1.27-alpha.49
+
+## 0.0.2-alpha.32
+
+### Patch Changes
+
+- Updated dependencies [b726bf5]
+  - @mastra/core@0.1.27-alpha.48
+
+## 0.0.2-alpha.31
+
+### Patch Changes
+
+- Updated dependencies [f6ba259]
+  - @mastra/core@0.1.27-alpha.47
+
+## 0.0.2-alpha.30
+
+### Patch Changes
+
+- 8ae2bbc: Dane publishing
+- 0bd142c: Fixes learned from docs
+- ee4de15: Dane fixes
+- Updated dependencies [8ae2bbc]
+- Updated dependencies [0bd142c]
+- Updated dependencies [ee4de15]
+  - @mastra/core@0.1.27-alpha.46
+
+## 0.0.2-alpha.29
+
+### Patch Changes
+
+- Updated dependencies [e608d8c]
+- Updated dependencies [002d6d8]
+  - @mastra/core@0.1.27-alpha.45
+
+## 0.0.2-alpha.28
+
+### Patch Changes
+
+- Updated dependencies [2fa7f53]
+  - @mastra/core@0.1.27-alpha.44
+
+## 0.0.2-alpha.27
+
+### Patch Changes
+
+- Updated dependencies [2e099d2]
+- Updated dependencies [d6d8159]
+  - @mastra/core@0.1.27-alpha.43
+
+## 0.0.2-alpha.26
+
+### Patch Changes
+
+- Updated dependencies [4a54c82]
+  - @mastra/core@0.1.27-alpha.42
+
+## 0.0.2-alpha.25
+
+### Patch Changes
+
+- Updated dependencies [5cdfb88]
+  - @mastra/core@0.1.27-alpha.41
+
+## 0.0.2-alpha.24
+
+### Patch Changes
+
+- Updated dependencies [9029796]
+  - @mastra/core@0.1.27-alpha.40
+
+## 0.0.2-alpha.23
+
+### Patch Changes
+
+- 6101f2d: Fix module incompatibility, and dane cli build
+- Updated dependencies [2b01511]
+  - @mastra/core@0.1.27-alpha.39
+
+## 0.0.2-alpha.22
+
+### Patch Changes
+
+- f031a1f: expose embed from rag, and refactor embed
+- Updated dependencies [f031a1f]
+  - @mastra/core@0.1.27-alpha.38
+
+## 0.0.2-alpha.21
+
+### Patch Changes
+
+- 45fd5b8: rename MastraDocument to MDocument
+- Updated dependencies [c872875]
+- Updated dependencies [f6da688]
+- Updated dependencies [b5393f1]
+  - @mastra/core@0.1.27-alpha.37
+
+## 0.0.2-alpha.20
+
+### Patch Changes
+
+- Updated dependencies [f537e33]
+- Updated dependencies [bc40916]
+- Updated dependencies [f7d1131]
+- Updated dependencies [75bf3f0]
+- Updated dependencies [3c4488b]
+- Updated dependencies [d38f7a6]
+  - @mastra/core@0.1.27-alpha.36
+
+## 0.0.2-alpha.19
+
+### Patch Changes
+
+- 033eda6: More fixes for refactor
+- Updated dependencies [033eda6]
+  - @mastra/core@0.1.27-alpha.35
+
+## 0.0.2-alpha.18
+
+### Patch Changes
+
+- 837a288: MAJOR Revamp of tools, workflows, syncs.
+- 5811de6: Updates spec-writer example to use new workflows constructs. Small improvements to workflow internals. Switch transformer tokenizer for js compatible one.
+- Updated dependencies [837a288]
+- Updated dependencies [5811de6]
+  - @mastra/core@0.1.27-alpha.34
+
+## 0.0.2-alpha.17
+
+### Patch Changes
+
+- e1dd94a: update the api for embeddings
+- Updated dependencies [e1dd94a]
+  - @mastra/core@0.1.27-alpha.33
+
+## 0.0.2-alpha.16
+
+### Patch Changes
+
+- Updated dependencies [2712098]
+  - @mastra/core@0.1.27-alpha.32
+
+## 0.0.2-alpha.15
+
+### Patch Changes
+
+- Updated dependencies [c2dd6b5]
+  - @mastra/core@0.1.27-alpha.31
+
+## 0.0.2-alpha.14
+
+### Patch Changes
+
+- 1c3232a: ChromaDB
+
+## 0.0.2-alpha.13
+
+### Patch Changes
+
+- Updated dependencies [963c15a]
+  - @mastra/core@0.1.27-alpha.30
+
+## 0.0.2-alpha.12
+
+### Patch Changes
+
+- Updated dependencies [7d87a15]
+  - @mastra/core@0.1.27-alpha.29
+
+## 0.0.2-alpha.11
+
+### Patch Changes
+
+- Updated dependencies [1ebd071]
+  - @mastra/core@0.1.27-alpha.28
+
+## 0.0.2-alpha.10
+
+### Patch Changes
+
+- 779702b: Upstash vector
+
+## 0.0.2-alpha.9
+
+### Patch Changes
+
+- Updated dependencies [cd02c56]
+  - @mastra/core@0.1.27-alpha.27
+
+## 0.0.2-alpha.8
+
+### Patch Changes
+
+- Updated dependencies [d5e12de]
+  - @mastra/core@0.1.27-alpha.26
+
 ## 0.0.2-alpha.7
 
 ### Patch Changes

package/LICENSE

@@ -0,0 +1,44 @@
+Elastic License 2.0 (ELv2)
+
+**Acceptance**
+By using the software, you agree to all of the terms and conditions below.
+
+**Copyright License**
+The licensor grants you a non-exclusive, royalty-free, worldwide, non-sublicensable, non-transferable license to use, copy, distribute, make available, and prepare derivative works of the software, in each case subject to the limitations and conditions below
+
+**Limitations**
+You may not provide the software to third parties as a hosted or managed service, where the service provides users with access to any substantial set of the features or functionality of the software.
+
+You may not move, change, disable, or circumvent the license key functionality in the software, and you may not remove or obscure any functionality in the software that is protected by the license key.
+
+You may not alter, remove, or obscure any licensing, copyright, or other notices of the licensor in the software. Any use of the licensor’s trademarks is subject to applicable law.
+
+**Patents**
+The licensor grants you a license, under any patent claims the licensor can license, or becomes able to license, to make, have made, use, sell, offer for sale, import and have imported the software, in each case subject to the limitations and conditions in this license. This license does not cover any patent claims that you cause to be infringed by modifications or additions to the software. If you or your company make any written claim that the software infringes or contributes to infringement of any patent, your patent license for the software granted under these terms ends immediately. If your company makes such a claim, your patent license ends immediately for work on behalf of your company.
+
+**Notices**
+You must ensure that anyone who gets a copy of any part of the software from you also gets a copy of these terms.
+
+If you modify the software, you must include in any modified copies of the software prominent notices stating that you have modified the software.
+
+**No Other Rights**
+These terms do not imply any licenses other than those expressly granted in these terms.
+
+**Termination**
+If you use the software in violation of these terms, such use is not licensed, and your licenses will automatically terminate. If the licensor provides you with a notice of your violation, and you cease all violation of this license no later than 30 days after you receive that notice, your licenses will be reinstated retroactively. However, if you violate these terms after such reinstatement, any additional violation of these terms will cause your licenses to terminate automatically and permanently.
+
+**No Liability**
+As far as the law allows, the software comes as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use or nature of the software, under any kind of legal claim.
+
+**Definitions**
+The _licensor_ is the entity offering these terms, and the _software_ is the software the licensor makes available under these terms, including any portion of it.
+
+_you_ refers to the individual or entity agreeing to these terms.
+
+_your company_ is any legal entity, sole proprietorship, or other kind of organization that you work for, plus all organizations that have control over, are under the control of, or are under common control with that organization. _control_ means ownership of substantially all the assets of an entity, or the power to direct its management and policies by vote, contract, or otherwise. Control can be direct or indirect.
+
+_your licenses_ are all the licenses granted to you for the software under these terms.
+
+_use_ means anything you do with the software requiring one of your licenses.
+
+_trademark_ means trademarks, service marks, and similar rights.

package/README.md

@@ -0,0 +1,26 @@
+# @mastra/rag
+
+The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.
+
+## Installation
+
+```bash
+npm install @mastra/rag
+```
+
+## Components
+
+### Document
+
+The `MDocument` class represents text content with associated metadata:
+
+```typescript
+import { MDocument } from '@mastra/rag';
+
+const doc = new MDocument({
+  text: 'Document content',
+  metadata: { source: 'example.txt' },
+});
+```
+
+[Documentation](https://mastra.ai/docs/reference/rag/document)

package/dist/document/document.d.ts

@@ -0,0 +1,32 @@
+import { Document as Chunk } from 'llamaindex';
+import { ChunkOptions, ChunkParams, ExtractParams } from './types';
+export declare class MDocument {
+    private chunks;
+    private type;
+    constructor({ docs, type }: {
+        docs: {
+            text: string;
+            metadata?: Record<string, any>;
+        }[];
+        type: string;
+    });
+    extractMetadata({ title, summary, questions, keywords }: ExtractParams): Promise<MDocument>;
+    static fromText(text: string, metadata?: Record<string, any>): MDocument;
+    static fromHTML(html: string, metadata?: Record<string, any>): MDocument;
+    static fromMarkdown(markdown: string, metadata?: Record<string, any>): MDocument;
+    static fromJSON(jsonString: string, metadata?: Record<string, any>): MDocument;
+    private defaultStrategy;
+    private chunkBy;
+    chunkRecursive(options?: ChunkOptions): Promise<void>;
+    chunkCharacter(options?: ChunkOptions): Promise<void>;
+    chunkHTML(options?: ChunkOptions): Promise<void>;
+    chunkJSON(options?: ChunkOptions): Promise<void>;
+    chunkLatex(options?: ChunkOptions): Promise<void>;
+    chunkToken(options?: ChunkOptions): Promise<void>;
+    chunkMarkdown(options?: ChunkOptions): Promise<void>;
+    chunk(params?: ChunkParams): Promise<Chunk[]>;
+    getDocs(): Chunk[];
+    getText(): string[];
+    getMetadata(): Record<string, any>[];
+}
+//# sourceMappingURL=document.d.ts.map

package/dist/document/document.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"document.d.ts","sourceRoot":"","sources":["../../src/document/document.ts"],"names":[],"mappings":"AAAA,OAAO,EACL,QAAQ,IAAI,KAAK,EAMlB,MAAM,YAAY,CAAC;AAQpB,OAAO,EAAE,YAAY,EAAE,WAAW,EAAiB,aAAa,EAAE,MAAM,SAAS,CAAC;AAElF,qBAAa,SAAS;IACpB,OAAO,CAAC,MAAM,CAAU;IACxB,OAAO,CAAC,IAAI,CAAS;gBAET,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE;QAAE,IAAI,EAAE;YAAE,IAAI,EAAE,MAAM,CAAC;YAAC,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAA;SAAE,EAAE,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE;IAOhG,eAAe,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,SAAS,EAAE,QAAQ,EAAE,EAAE,aAAa,GAAG,OAAO,CAAC,SAAS,CAAC;IAwCjG,MAAM,CAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,GAAG,SAAS;IAYxE,MAAM,CAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,GAAG,SAAS;IAYxE,MAAM,CAAC,YAAY,CAAC,QAAQ,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,GAAG,SAAS;IAYhF,MAAM,CAAC,QAAQ,CAAC,UAAU,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,GAAG,SAAS;IAY9E,OAAO,CAAC,eAAe;YAeT,OAAO;IA4Bf,cAAc,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAiBrD,cAAc,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAUrD,SAAS,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAoBhD,SAAS,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAmBhD,UAAU,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAMjD,UAAU,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAUjD,aAAa,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC;IAapD,KAAK,CAAC,MAAM,CAAC,EAAE,WAAW,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;IAenD,OAAO,IAAI,KAAK,EAAE;IAIlB,OAAO,IAAI,MAAM,EAAE;IAInB,WAAW,IAAI,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,EAAE;CAGrC"}

package/dist/document/index.d.ts

@@ -0,0 +1,3 @@
+export * from './document';
+export * from './types';
+//# sourceMappingURL=index.d.ts.map

package/dist/document/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/document/index.ts"],"names":[],"mappings":"AAAA,cAAc,YAAY,CAAC;AAC3B,cAAc,SAAS,CAAC"}

package/dist/document/transformers/character.d.ts

@@ -0,0 +1,45 @@
+import { ChunkOptions, Language } from '../types';
+import { TextTransformer } from './text';
+export declare class CharacterTransformer extends TextTransformer {
+    protected separator: string;
+    protected isSeparatorRegex: boolean;
+    constructor({ separator, isSeparatorRegex, options, }: {
+        separator?: string;
+        isSeparatorRegex?: boolean;
+        options?: {
+            size?: number;
+            overlap?: number;
+            lengthFunction?: (text: string) => number;
+            keepSeparator?: boolean | 'start' | 'end';
+            addStartIndex?: boolean;
+            stripWhitespace?: boolean;
+        };
+    });
+    splitText({ text }: {
+        text: string;
+    }): string[];
+    private __splitChunk;
+}
+export declare class RecursiveCharacterTransformer extends TextTransformer {
+    protected separators: string[];
+    protected isSeparatorRegex: boolean;
+    constructor({ separators, isSeparatorRegex, options, }: {
+        separators?: string[];
+        isSeparatorRegex?: boolean;
+        options?: ChunkOptions;
+    });
+    private _splitText;
+    splitText({ text }: {
+        text: string;
+    }): string[];
+    static fromLanguage(language: Language, options?: {
+        size?: number;
+        chunkOverlap?: number;
+        lengthFunction?: (text: string) => number;
+        keepSeparator?: boolean | 'start' | 'end';
+        addStartIndex?: boolean;
+        stripWhitespace?: boolean;
+    }): RecursiveCharacterTransformer;
+    static getSeparatorsForLanguage(language: Language): string[];
+}
+//# sourceMappingURL=character.d.ts.map

package/dist/document/transformers/character.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"character.d.ts","sourceRoot":"","sources":["../../../src/document/transformers/character.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,QAAQ,EAAE,MAAM,UAAU,CAAC;AAElD,OAAO,EAAE,eAAe,EAAE,MAAM,QAAQ,CAAC;AA+CzC,qBAAa,oBAAqB,SAAQ,eAAe;IACvD,SAAS,CAAC,SAAS,EAAE,MAAM,CAAC;IAC5B,SAAS,CAAC,gBAAgB,EAAE,OAAO,CAAC;gBAExB,EACV,SAAkB,EAClB,gBAAwB,EACxB,OAAY,GACb,EAAE;QACD,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,gBAAgB,CAAC,EAAE,OAAO,CAAC;QAC3B,OAAO,CAAC,EAAE;YACR,IAAI,CAAC,EAAE,MAAM,CAAC;YACd,OAAO,CAAC,EAAE,MAAM,CAAC;YACjB,cAAc,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAC;YAC1C,aAAa,CAAC,EAAE,OAAO,GAAG,OAAO,GAAG,KAAK,CAAC;YAC1C,aAAa,CAAC,EAAE,OAAO,CAAC;YACxB,eAAe,CAAC,EAAE,OAAO,CAAC;SAC3B,CAAC;KACH;IAMD,SAAS,CAAC,EAAE,IAAI,EAAE,EAAE;QAAE,IAAI,EAAE,MAAM,CAAA;KAAE,GAAG,MAAM,EAAE;IAqB/C,OAAO,CAAC,YAAY;CAwBrB;AAED,qBAAa,6BAA8B,SAAQ,eAAe;IAChE,SAAS,CAAC,UAAU,EAAE,MAAM,EAAE,CAAC;IAC/B,SAAS,CAAC,gBAAgB,EAAE,OAAO,CAAC;gBAExB,EACV,UAAU,EACV,gBAAwB,EACxB,OAAY,GACb,EAAE;QACD,UAAU,CAAC,EAAE,MAAM,EAAE,CAAC;QACtB,gBAAgB,CAAC,EAAE,OAAO,CAAC;QAC3B,OAAO,CAAC,EAAE,YAAY,CAAC;KACxB;IAMD,OAAO,CAAC,UAAU;IAuDlB,SAAS,CAAC,EAAE,IAAI,EAAE,EAAE;QAAE,IAAI,EAAE,MAAM,CAAA;KAAE,GAAG,MAAM,EAAE;IAI/C,MAAM,CAAC,YAAY,CACjB,QAAQ,EAAE,QAAQ,EAClB,OAAO,GAAE;QACP,IAAI,CAAC,EAAE,MAAM,CAAC;QACd,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,cAAc,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAC;QAC1C,aAAa,CAAC,EAAE,OAAO,GAAG,OAAO,GAAG,KAAK,CAAC;QAC1C,aAAa,CAAC,EAAE,OAAO,CAAC;QACxB,eAAe,CAAC,EAAE,OAAO,CAAC;KACtB,GACL,6BAA6B;IAKhC,MAAM,CAAC,wBAAwB,CAAC,QAAQ,EAAE,QAAQ,GAAG,MAAM,EAAE;CAgE9D"}

package/dist/document/transformers/html.d.ts

@@ -0,0 +1,24 @@
+import { Document } from 'llamaindex';
+export declare class HTMLHeaderTransformer {
+    private headersToSplitOn;
+    private returnEachElement;
+    constructor(headersToSplitOn: [string, string][], returnEachElement?: boolean);
+    splitText({ text }: {
+        text: string;
+    }): Document[];
+    private getXPath;
+    private aggregateElementsToChunks;
+    createDocuments(texts: string[], metadatas?: Record<string, any>[]): Document[];
+    transformDocuments(documents: Document[]): Document[];
+}
+export declare class HTMLSectionTransformer {
+    private headersToSplitOn;
+    private options;
+    constructor(headersToSplitOn: [string, string][], options?: Record<string, any>);
+    splitText(text: string): Document[];
+    splitDocuments(documents: Document[]): Promise<Document[]>;
+    createDocuments(texts: string[], metadatas?: Record<string, any>[]): Document[];
+    private splitHtmlByHeaders;
+    transformDocuments(documents: Document[]): Document[];
+}
+//# sourceMappingURL=html.d.ts.map

package/dist/document/transformers/html.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"html.d.ts","sourceRoot":"","sources":["../../../src/document/transformers/html.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,QAAQ,EAAE,MAAM,YAAY,CAAC;AAWtC,qBAAa,qBAAqB;IAChC,OAAO,CAAC,gBAAgB,CAAqB;IAC7C,OAAO,CAAC,iBAAiB,CAAU;gBAEvB,gBAAgB,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,EAAE,iBAAiB,GAAE,OAAe;IAKpF,SAAS,CAAC,EAAE,IAAI,EAAE,EAAE;QAAE,IAAI,EAAE,MAAM,CAAA;KAAE,GAAG,QAAQ,EAAE;IAwCjD,OAAO,CAAC,QAAQ;IAkBhB,OAAO,CAAC,yBAAyB;IAyBjC,eAAe,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,SAAS,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,EAAE,GAAG,QAAQ,EAAE;IA+B/E,kBAAkB,CAAC,SAAS,EAAE,QAAQ,EAAE,GAAG,QAAQ,EAAE;CAWtD;AAED,qBAAa,sBAAsB;IACjC,OAAO,CAAC,gBAAgB,CAAyB;IACjD,OAAO,CAAC,OAAO,CAAsB;gBAEzB,gBAAgB,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,EAAE,OAAO,GAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAM;IAKnF,SAAS,CAAC,IAAI,EAAE,MAAM,GAAG,QAAQ,EAAE;IAc7B,cAAc,CAAC,SAAS,EAAE,QAAQ,EAAE,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC;IAchE,eAAe,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,SAAS,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,EAAE,GAAG,QAAQ,EAAE;IA+B/E,OAAO,CAAC,kBAAkB;IAuD1B,kBAAkB,CAAC,SAAS,EAAE,QAAQ,EAAE,GAAG,QAAQ,EAAE;CAWtD"}