@cogitator-ai/rag 0.1.9 → 0.2.0

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.
Files changed (95) hide show
  1. package/README.md +66 -31
  2. package/dist/chunkers/create-chunker.js.map +1 -1
  3. package/dist/chunkers/index.d.ts.map +1 -1
  4. package/dist/chunkers/index.js.map +1 -1
  5. package/dist/chunkers/recursive-chunker.d.ts +2 -3
  6. package/dist/chunkers/recursive-chunker.d.ts.map +1 -1
  7. package/dist/chunkers/recursive-chunker.js +89 -118
  8. package/dist/chunkers/recursive-chunker.js.map +1 -1
  9. package/dist/chunkers/semantic-chunker.d.ts +2 -0
  10. package/dist/chunkers/semantic-chunker.d.ts.map +1 -1
  11. package/dist/chunkers/semantic-chunker.js +72 -38
  12. package/dist/chunkers/semantic-chunker.js.map +1 -1
  13. package/dist/index.d.ts +2 -2
  14. package/dist/index.d.ts.map +1 -1
  15. package/dist/index.js +4 -2
  16. package/dist/index.js.map +1 -1
  17. package/dist/loaders/csv-loader.d.ts.map +1 -1
  18. package/dist/loaders/csv-loader.js +12 -4
  19. package/dist/loaders/csv-loader.js.map +1 -1
  20. package/dist/loaders/html-loader.d.ts +4 -0
  21. package/dist/loaders/html-loader.d.ts.map +1 -1
  22. package/dist/loaders/html-loader.js +26 -2
  23. package/dist/loaders/html-loader.js.map +1 -1
  24. package/dist/loaders/index.d.ts.map +1 -1
  25. package/dist/loaders/index.js.map +1 -1
  26. package/dist/loaders/json-loader.d.ts +1 -0
  27. package/dist/loaders/json-loader.d.ts.map +1 -1
  28. package/dist/loaders/json-loader.js +15 -3
  29. package/dist/loaders/json-loader.js.map +1 -1
  30. package/dist/loaders/markdown-loader.d.ts.map +1 -1
  31. package/dist/loaders/markdown-loader.js +8 -4
  32. package/dist/loaders/markdown-loader.js.map +1 -1
  33. package/dist/loaders/pdf-loader.d.ts +1 -0
  34. package/dist/loaders/pdf-loader.d.ts.map +1 -1
  35. package/dist/loaders/pdf-loader.js +22 -3
  36. package/dist/loaders/pdf-loader.js.map +1 -1
  37. package/dist/loaders/text-loader.js +1 -1
  38. package/dist/loaders/text-loader.js.map +1 -1
  39. package/dist/loaders/web-loader.d.ts +33 -0
  40. package/dist/loaders/web-loader.d.ts.map +1 -1
  41. package/dist/loaders/web-loader.js +262 -8
  42. package/dist/loaders/web-loader.js.map +1 -1
  43. package/dist/rag-builder.d.ts +10 -1
  44. package/dist/rag-builder.d.ts.map +1 -1
  45. package/dist/rag-builder.js +71 -6
  46. package/dist/rag-builder.js.map +1 -1
  47. package/dist/rag-pipeline.d.ts +2 -1
  48. package/dist/rag-pipeline.d.ts.map +1 -1
  49. package/dist/rag-pipeline.js +58 -23
  50. package/dist/rag-pipeline.js.map +1 -1
  51. package/dist/rerankers/cohere-reranker.d.ts +2 -2
  52. package/dist/rerankers/cohere-reranker.d.ts.map +1 -1
  53. package/dist/rerankers/cohere-reranker.js +5 -0
  54. package/dist/rerankers/cohere-reranker.js.map +1 -1
  55. package/dist/rerankers/index.d.ts.map +1 -1
  56. package/dist/rerankers/index.js.map +1 -1
  57. package/dist/rerankers/llm-reranker.d.ts +1 -1
  58. package/dist/rerankers/llm-reranker.d.ts.map +1 -1
  59. package/dist/rerankers/llm-reranker.js +26 -13
  60. package/dist/rerankers/llm-reranker.js.map +1 -1
  61. package/dist/retrievers/chunk-indexer.d.ts +19 -0
  62. package/dist/retrievers/chunk-indexer.d.ts.map +1 -0
  63. package/dist/retrievers/chunk-indexer.js +8 -0
  64. package/dist/retrievers/chunk-indexer.js.map +1 -0
  65. package/dist/retrievers/create-retriever.d.ts +2 -0
  66. package/dist/retrievers/create-retriever.d.ts.map +1 -1
  67. package/dist/retrievers/create-retriever.js +6 -0
  68. package/dist/retrievers/create-retriever.js.map +1 -1
  69. package/dist/retrievers/hybrid-retriever.d.ts +8 -1
  70. package/dist/retrievers/hybrid-retriever.d.ts.map +1 -1
  71. package/dist/retrievers/hybrid-retriever.js +18 -5
  72. package/dist/retrievers/hybrid-retriever.js.map +1 -1
  73. package/dist/retrievers/index.d.ts +2 -0
  74. package/dist/retrievers/index.d.ts.map +1 -1
  75. package/dist/retrievers/index.js +1 -0
  76. package/dist/retrievers/index.js.map +1 -1
  77. package/dist/retrievers/mmr-retriever.d.ts +5 -0
  78. package/dist/retrievers/mmr-retriever.d.ts.map +1 -1
  79. package/dist/retrievers/mmr-retriever.js +34 -8
  80. package/dist/retrievers/mmr-retriever.js.map +1 -1
  81. package/dist/retrievers/multi-query-retriever.d.ts +14 -1
  82. package/dist/retrievers/multi-query-retriever.d.ts.map +1 -1
  83. package/dist/retrievers/multi-query-retriever.js +50 -6
  84. package/dist/retrievers/multi-query-retriever.js.map +1 -1
  85. package/dist/retrievers/similarity-retriever.d.ts.map +1 -1
  86. package/dist/retrievers/similarity-retriever.js +2 -1
  87. package/dist/retrievers/similarity-retriever.js.map +1 -1
  88. package/dist/schema.d.ts.map +1 -1
  89. package/dist/schema.js +16 -2
  90. package/dist/schema.js.map +1 -1
  91. package/dist/tools.d.ts +11 -2
  92. package/dist/tools.d.ts.map +1 -1
  93. package/dist/tools.js +43 -9
  94. package/dist/tools.js.map +1 -1
  95. package/package.json +5 -5
@@ -1,10 +1,13 @@
1
1
  import { nanoid } from 'nanoid';
2
2
  function cosineSimilarity(a, b) {
3
- const len = Math.min(a.length, b.length);
3
+ if (a.length !== b.length) {
4
+ throw new Error(`Embedding dimension mismatch: ${a.length} vs ${b.length}. ` +
5
+ 'Ensure all embeddings come from the same model.');
6
+ }
4
7
  let dot = 0;
5
8
  let normA = 0;
6
9
  let normB = 0;
7
- for (let i = 0; i < len; i++) {
10
+ for (let i = 0; i < a.length; i++) {
8
11
  dot += a[i] * b[i];
9
12
  normA += a[i] * a[i];
10
13
  normB += b[i] * b[i];
@@ -12,7 +15,7 @@ function cosineSimilarity(a, b) {
12
15
  const denom = Math.sqrt(normA) * Math.sqrt(normB);
13
16
  return denom === 0 ? 0 : dot / denom;
14
17
  }
15
- const SENTENCE_SPLIT_RE = /(?<=[.?!])\s+/;
18
+ const SENTENCE_SPLIT_RE = /(?<=[.?!])\s+|\n\s*\n/;
16
19
  function splitSentences(text) {
17
20
  return text
18
21
  .split(SENTENCE_SPLIT_RE)
@@ -25,10 +28,19 @@ export class SemanticChunker {
25
28
  minChunkSize;
26
29
  maxChunkSize;
27
30
  constructor(options) {
31
+ if (options.breakpointThreshold !== undefined &&
32
+ (options.breakpointThreshold < 0 || options.breakpointThreshold > 1)) {
33
+ throw new Error('breakpointThreshold must be between 0 and 1');
34
+ }
35
+ const maxChunkSize = options.maxChunkSize ?? 2000;
36
+ const minChunkSize = options.minChunkSize ?? Math.min(100, maxChunkSize);
37
+ if (minChunkSize > maxChunkSize) {
38
+ throw new Error('minChunkSize must not exceed maxChunkSize');
39
+ }
28
40
  this.embeddingService = options.embeddingService;
29
41
  this.breakpointThreshold = options.breakpointThreshold ?? 0.5;
30
- this.minChunkSize = options.minChunkSize ?? 100;
31
- this.maxChunkSize = options.maxChunkSize ?? 2000;
42
+ this.minChunkSize = minChunkSize;
43
+ this.maxChunkSize = maxChunkSize;
32
44
  }
33
45
  async chunk(text, documentId) {
34
46
  if (!text || text.trim().length === 0)
@@ -40,6 +52,9 @@ export class SemanticChunker {
40
52
  return this.buildChunks([sentences], text, documentId);
41
53
  }
42
54
  const embeddings = await this.embeddingService.embedBatch(sentences);
55
+ if (embeddings.length !== sentences.length) {
56
+ throw new Error(`Embedding count mismatch: got ${embeddings.length} vectors for ${sentences.length} sentences`);
57
+ }
43
58
  const similarities = [];
44
59
  for (let i = 0; i < embeddings.length - 1; i++) {
45
60
  similarities.push(cosineSimilarity(embeddings[i], embeddings[i + 1]));
@@ -94,21 +109,25 @@ export class SemanticChunker {
94
109
  }
95
110
  return result;
96
111
  }
112
+ findSentenceOffset(sentence, originalText, searchFrom) {
113
+ const idx = originalText.indexOf(sentence, searchFrom);
114
+ return idx >= 0 ? idx : searchFrom;
115
+ }
97
116
  buildChunks(groups, originalText, documentId) {
98
117
  const chunks = [];
99
118
  let searchFrom = 0;
100
119
  for (const group of groups) {
101
- const content = group.join(' ');
120
+ const startOffset = this.findSentenceOffset(group[0], originalText, searchFrom);
121
+ const lastSentence = group[group.length - 1];
122
+ const lastStart = this.findSentenceOffset(lastSentence, originalText, startOffset);
123
+ const endOffset = lastStart + lastSentence.length;
124
+ const content = originalText.slice(startOffset, endOffset);
102
125
  if (content.length <= this.maxChunkSize) {
103
- const startOffset = originalText.indexOf(group[0], searchFrom);
104
- const lastSentence = group[group.length - 1];
105
- const lastStart = originalText.indexOf(lastSentence, startOffset >= 0 ? startOffset : 0);
106
- const endOffset = lastStart >= 0 ? lastStart + lastSentence.length : startOffset + content.length;
107
126
  chunks.push({
108
127
  id: nanoid(),
109
128
  documentId,
110
129
  content,
111
- startOffset: Math.max(0, startOffset),
130
+ startOffset,
112
131
  endOffset,
113
132
  order: chunks.length,
114
133
  });
@@ -131,22 +150,35 @@ export class SemanticChunker {
131
150
  let order = startOrder;
132
151
  let offset = searchFrom;
133
152
  for (const sentence of sentences) {
153
+ if (sentence.length > this.maxChunkSize) {
154
+ if (currentSentences.length > 0) {
155
+ const chunk = this.emitSentenceGroup(currentSentences, originalText, documentId, offset, order++);
156
+ chunks.push(chunk);
157
+ offset = chunk.endOffset;
158
+ currentSentences = [];
159
+ currentLength = 0;
160
+ }
161
+ const sentenceStart = this.findSentenceOffset(sentence, originalText, offset);
162
+ for (let pos = 0; pos < sentence.length; pos += this.maxChunkSize) {
163
+ const sliceEnd = Math.min(pos + this.maxChunkSize, sentence.length);
164
+ const slice = sentence.slice(pos, sliceEnd);
165
+ chunks.push({
166
+ id: nanoid(),
167
+ documentId,
168
+ content: slice,
169
+ startOffset: sentenceStart + pos,
170
+ endOffset: sentenceStart + sliceEnd,
171
+ order: order++,
172
+ });
173
+ }
174
+ offset = sentenceStart + sentence.length;
175
+ continue;
176
+ }
134
177
  const newLength = currentLength + (currentSentences.length > 0 ? 1 : 0) + sentence.length;
135
178
  if (newLength > this.maxChunkSize && currentSentences.length > 0) {
136
- const content = currentSentences.join(' ');
137
- const startOffset = originalText.indexOf(currentSentences[0], offset);
138
- const lastSentence = currentSentences[currentSentences.length - 1];
139
- const lastStart = originalText.indexOf(lastSentence, startOffset >= 0 ? startOffset : 0);
140
- const endOffset = lastStart >= 0 ? lastStart + lastSentence.length : startOffset + content.length;
141
- chunks.push({
142
- id: nanoid(),
143
- documentId,
144
- content,
145
- startOffset: Math.max(0, startOffset),
146
- endOffset,
147
- order: order++,
148
- });
149
- offset = endOffset;
179
+ const chunk = this.emitSentenceGroup(currentSentences, originalText, documentId, offset, order++);
180
+ chunks.push(chunk);
181
+ offset = chunk.endOffset;
150
182
  currentSentences = [sentence];
151
183
  currentLength = sentence.length;
152
184
  }
@@ -156,21 +188,23 @@ export class SemanticChunker {
156
188
  }
157
189
  }
158
190
  if (currentSentences.length > 0) {
159
- const content = currentSentences.join(' ');
160
- const startOffset = originalText.indexOf(currentSentences[0], offset);
161
- const lastSentence = currentSentences[currentSentences.length - 1];
162
- const lastStart = originalText.indexOf(lastSentence, startOffset >= 0 ? startOffset : 0);
163
- const endOffset = lastStart >= 0 ? lastStart + lastSentence.length : startOffset + content.length;
164
- chunks.push({
165
- id: nanoid(),
166
- documentId,
167
- content,
168
- startOffset: Math.max(0, startOffset),
169
- endOffset,
170
- order: order++,
171
- });
191
+ chunks.push(this.emitSentenceGroup(currentSentences, originalText, documentId, offset, order++));
172
192
  }
173
193
  return chunks;
174
194
  }
195
+ emitSentenceGroup(sentences, originalText, documentId, searchFrom, order) {
196
+ const startOffset = this.findSentenceOffset(sentences[0], originalText, searchFrom);
197
+ const lastSentence = sentences[sentences.length - 1];
198
+ const lastStart = this.findSentenceOffset(lastSentence, originalText, startOffset);
199
+ const endOffset = lastStart + lastSentence.length;
200
+ return {
201
+ id: nanoid(),
202
+ documentId,
203
+ content: originalText.slice(startOffset, endOffset),
204
+ startOffset,
205
+ endOffset,
206
+ order,
207
+ };
208
+ }
175
209
  }
176
210
  //# sourceMappingURL=semantic-chunker.js.map
@@ -1 +1 @@
1
- {"version":3,"file":"semantic-chunker.js","sourceRoot":"","sources":["../../src/chunkers/semantic-chunker.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAUhC,SAAS,gBAAgB,CAAC,CAAW,EAAE,CAAW;IAChD,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC;IACzC,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC;QAC7B,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACnB,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACrB,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;IACvB,CAAC;IACD,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAClD,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,GAAG,KAAK,CAAC;AACvC,CAAC;AAED,MAAM,iBAAiB,GAAG,eAAe,CAAC;AAE1C,SAAS,cAAc,CAAC,IAAY;IAClC,OAAO,IAAI;SACR,KAAK,CAAC,iBAAiB,CAAC;SACxB,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;SACpB,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;AACjC,CAAC;AAED,MAAM,OAAO,eAAe;IACT,gBAAgB,CAAmB;IACnC,mBAAmB,CAAS;IAC5B,YAAY,CAAS;IACrB,YAAY,CAAS;IAEtC,YAAY,OAA+B;QACzC,IAAI,CAAC,gBAAgB,GAAG,OAAO,CAAC,gBAAgB,CAAC;QACjD,IAAI,CAAC,mBAAmB,GAAG,OAAO,CAAC,mBAAmB,IAAI,GAAG,CAAC;QAC9D,IAAI,CAAC,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,GAAG,CAAC;QAChD,IAAI,CAAC,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,IAAI,CAAC;IACnD,CAAC;IAED,KAAK,CAAC,KAAK,CAAC,IAAY,EAAE,UAAkB;QAC1C,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,EAAE,CAAC;QAEjD,MAAM,SAAS,GAAG,cAAc,CAAC,IAAI,CAAC,CAAC;QACvC,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,EAAE,CAAC;QAEtC,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC3B,OAAO,IAAI,CAAC,WAAW,CAAC,CAAC,SAAS,CAAC,EAAE,IAAI,EAAE,UAAU,CAAC,CAAC;QACzD,CAAC;QAED,MAAM,UAAU,GAAG,MAAM,IAAI,CAAC,gBAAgB,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC;QAErE,MAAM,YAAY,GAAa,EAAE,CAAC;QAClC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;YAC/C,YAAY,CAAC,IAAI,CAAC,gBAAgB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACxE,CAAC;QAED,MAAM,MAAM,GAAe,EAAE,CAAC;QAC9B,IAAI,YAAY,GAAa,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC;QAE5C,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,YAAY,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YAC7C,IAAI,YAAY,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,mBAAmB,EAAE,CAAC;gBAC/C,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;gBAC1B,YAAY,GAAG,CAAC,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACpC,CAAC;iBAAM,CAAC;gBACN,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACtC,CAAC;QACH,CAAC;QACD,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;QAE1B,MAAM,MAAM,GAAG,IAAI,CAAC,gBAAgB,CAAC,MAAM,CAAC,CAAC;QAC7C,OAAO,IAAI,CAAC,WAAW,CAAC,MAAM,EAAE,IAAI,EAAE,UAAU,CAAC,CAAC;IACpD,CAAC;IAEO,gBAAgB,CAAC,MAAkB;QACzC,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC;YAAE,OAAO,MAAM,CAAC;QAEtC,MAAM,MAAM,GAAe,EAAE,CAAC;QAC9B,IAAI,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC;QAExB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACvC,MAAM,WAAW,GAAG,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACtC,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACrC,MAAM,cAAc,GAAG,WAAW,CAAC,MAAM,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM,CAAC;YAEhE,IAAI,WAAW,CAAC,MAAM,GAAG,IAAI,CAAC,YAAY,IAAI,cAAc,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;gBAClF,OAAO,GAAG,CAAC,GAAG,OAAO,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC;YACvC,CAAC;iBAAM,CAAC;gBACN,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;gBACrB,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC;YACtB,CAAC;QACH,CAAC;QAED,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACvB,MAAM,WAAW,GAAG,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACtC,IAAI,WAAW,CAAC,MAAM,GAAG,IAAI,CAAC,YAAY,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAChE,MAAM,IAAI,GAAG,MAAM,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;gBACvC,MAAM,QAAQ,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;gBAChC,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,GAAG,WAAW,CAAC,MAAM,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;oBAClE,MAAM,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,GAAG,CAAC,GAAG,IAAI,EAAE,GAAG,OAAO,CAAC,CAAC;gBACpD,CAAC;qBAAM,CAAC;oBACN,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;gBACvB,CAAC;YACH,CAAC;iBAAM,CAAC;gBACN,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;YACvB,CAAC;QACH,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,WAAW,CACjB,MAAkB,EAClB,YAAoB,EACpB,UAAkB;QAElB,MAAM,MAAM,GAAoB,EAAE,CAAC;QACnC,IAAI,UAAU,GAAG,CAAC,CAAC;QAEnB,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;YAC3B,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YAEhC,IAAI,OAAO,CAAC,MAAM,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;gBACxC,MAAM,WAAW,GAAG,YAAY,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC;gBAC/D,MAAM,YAAY,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;gBAC7C,MAAM,SAAS,GAAG,YAAY,CAAC,OAAO,CAAC,YAAY,EAAE,WAAW,IAAI,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACzF,MAAM,SAAS,GACb,SAAS,IAAI,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,CAAC,WAAW,GAAG,OAAO,CAAC,MAAM,CAAC;gBAElF,MAAM,CAAC,IAAI,CAAC;oBACV,EAAE,EAAE,MAAM,EAAE;oBACZ,UAAU;oBACV,OAAO;oBACP,WAAW,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC;oBACrC,SAAS;oBACT,KAAK,EAAE,MAAM,CAAC,MAAM;iBACrB,CAAC,CAAC;gBAEH,UAAU,GAAG,SAAS,CAAC;YACzB,CAAC;iBAAM,CAAC;gBACN,MAAM,SAAS,GAAG,IAAI,CAAC,eAAe,CACpC,KAAK,EACL,YAAY,EACZ,UAAU,EACV,UAAU,EACV,MAAM,CAAC,MAAM,CACd,CAAC;gBACF,MAAM,CAAC,IAAI,CAAC,GAAG,SAAS,CAAC,CAAC;gBAC1B,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACzB,UAAU,GAAG,SAAS,CAAC,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC;gBACzD,CAAC;YACH,CAAC;QACH,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,eAAe,CACrB,SAAmB,EACnB,YAAoB,EACpB,UAAkB,EAClB,UAAkB,EAClB,UAAkB;QAElB,MAAM,MAAM,GAAoB,EAAE,CAAC;QACnC,IAAI,gBAAgB,GAAa,EAAE,CAAC;QACpC,IAAI,aAAa,GAAG,CAAC,CAAC;QACtB,IAAI,KAAK,GAAG,UAAU,CAAC;QACvB,IAAI,MAAM,GAAG,UAAU,CAAC;QAExB,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;YACjC,MAAM,SAAS,GAAG,aAAa,GAAG,CAAC,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,MAAM,CAAC;YAE1F,IAAI,SAAS,GAAG,IAAI,CAAC,YAAY,IAAI,gBAAgB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACjE,MAAM,OAAO,GAAG,gBAAgB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;gBAC3C,MAAM,WAAW,GAAG,YAAY,CAAC,OAAO,CAAC,gBAAgB,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;gBACtE,MAAM,YAAY,GAAG,gBAAgB,CAAC,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;gBACnE,MAAM,SAAS,GAAG,YAAY,CAAC,OAAO,CAAC,YAAY,EAAE,WAAW,IAAI,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACzF,MAAM,SAAS,GACb,SAAS,IAAI,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,CAAC,WAAW,GAAG,OAAO,CAAC,MAAM,CAAC;gBAElF,MAAM,CAAC,IAAI,CAAC;oBACV,EAAE,EAAE,MAAM,EAAE;oBACZ,UAAU;oBACV,OAAO;oBACP,WAAW,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC;oBACrC,SAAS;oBACT,KAAK,EAAE,KAAK,EAAE;iBACf,CAAC,CAAC;gBAEH,MAAM,GAAG,SAAS,CAAC;gBACnB,gBAAgB,GAAG,CAAC,QAAQ,CAAC,CAAC;gBAC9B,aAAa,GAAG,QAAQ,CAAC,MAAM,CAAC;YAClC,CAAC;iBAAM,CAAC;gBACN,gBAAgB,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBAChC,aAAa,GAAG,SAAS,CAAC;YAC5B,CAAC;QACH,CAAC;QAED,IAAI,gBAAgB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAChC,MAAM,OAAO,GAAG,gBAAgB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YAC3C,MAAM,WAAW,GAAG,YAAY,CAAC,OAAO,CAAC,gBAAgB,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;YACtE,MAAM,YAAY,GAAG,gBAAgB,CAAC,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACnE,MAAM,SAAS,GAAG,YAAY,CAAC,OAAO,CAAC,YAAY,EAAE,WAAW,IAAI,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;YACzF,MAAM,SAAS,GACb,SAAS,IAAI,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,CAAC,WAAW,GAAG,OAAO,CAAC,MAAM,CAAC;YAElF,MAAM,CAAC,IAAI,CAAC;gBACV,EAAE,EAAE,MAAM,EAAE;gBACZ,UAAU;gBACV,OAAO;gBACP,WAAW,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC;gBACrC,SAAS;gBACT,KAAK,EAAE,KAAK,EAAE;aACf,CAAC,CAAC;QACL,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;CACF"}
1
+ {"version":3,"file":"semantic-chunker.js","sourceRoot":"","sources":["../../src/chunkers/semantic-chunker.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAUhC,SAAS,gBAAgB,CAAC,CAAW,EAAE,CAAW;IAChD,IAAI,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,MAAM,EAAE,CAAC;QAC1B,MAAM,IAAI,KAAK,CACb,iCAAiC,CAAC,CAAC,MAAM,OAAO,CAAC,CAAC,MAAM,IAAI;YAC1D,iDAAiD,CACpD,CAAC;IACJ,CAAC;IACD,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QAClC,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACnB,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACrB,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;IACvB,CAAC;IACD,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAClD,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,GAAG,KAAK,CAAC;AACvC,CAAC;AAED,MAAM,iBAAiB,GAAG,uBAAuB,CAAC;AAElD,SAAS,cAAc,CAAC,IAAY;IAClC,OAAO,IAAI;SACR,KAAK,CAAC,iBAAiB,CAAC;SACxB,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;SACpB,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;AACjC,CAAC;AAED,MAAM,OAAO,eAAe;IACT,gBAAgB,CAAmB;IACnC,mBAAmB,CAAS;IAC5B,YAAY,CAAS;IACrB,YAAY,CAAS;IAEtC,YAAY,OAA+B;QACzC,IACE,OAAO,CAAC,mBAAmB,KAAK,SAAS;YACzC,CAAC,OAAO,CAAC,mBAAmB,GAAG,CAAC,IAAI,OAAO,CAAC,mBAAmB,GAAG,CAAC,CAAC,EACpE,CAAC;YACD,MAAM,IAAI,KAAK,CAAC,6CAA6C,CAAC,CAAC;QACjE,CAAC;QAED,MAAM,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,IAAI,CAAC;QAClD,MAAM,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,YAAY,CAAC,CAAC;QAEzE,IAAI,YAAY,GAAG,YAAY,EAAE,CAAC;YAChC,MAAM,IAAI,KAAK,CAAC,2CAA2C,CAAC,CAAC;QAC/D,CAAC;QAED,IAAI,CAAC,gBAAgB,GAAG,OAAO,CAAC,gBAAgB,CAAC;QACjD,IAAI,CAAC,mBAAmB,GAAG,OAAO,CAAC,mBAAmB,IAAI,GAAG,CAAC;QAC9D,IAAI,CAAC,YAAY,GAAG,YAAY,CAAC;QACjC,IAAI,CAAC,YAAY,GAAG,YAAY,CAAC;IACnC,CAAC;IAED,KAAK,CAAC,KAAK,CAAC,IAAY,EAAE,UAAkB;QAC1C,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,EAAE,CAAC;QAEjD,MAAM,SAAS,GAAG,cAAc,CAAC,IAAI,CAAC,CAAC;QACvC,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,EAAE,CAAC;QAEtC,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC3B,OAAO,IAAI,CAAC,WAAW,CAAC,CAAC,SAAS,CAAC,EAAE,IAAI,EAAE,UAAU,CAAC,CAAC;QACzD,CAAC;QAED,MAAM,UAAU,GAAG,MAAM,IAAI,CAAC,gBAAgB,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC;QACrE,IAAI,UAAU,CAAC,MAAM,KAAK,SAAS,CAAC,MAAM,EAAE,CAAC;YAC3C,MAAM,IAAI,KAAK,CACb,iCAAiC,UAAU,CAAC,MAAM,gBAAgB,SAAS,CAAC,MAAM,YAAY,CAC/F,CAAC;QACJ,CAAC;QAED,MAAM,YAAY,GAAa,EAAE,CAAC;QAClC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;YAC/C,YAAY,CAAC,IAAI,CAAC,gBAAgB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACxE,CAAC;QAED,MAAM,MAAM,GAAe,EAAE,CAAC;QAC9B,IAAI,YAAY,GAAa,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC;QAE5C,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,YAAY,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YAC7C,IAAI,YAAY,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,mBAAmB,EAAE,CAAC;gBAC/C,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;gBAC1B,YAAY,GAAG,CAAC,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACpC,CAAC;iBAAM,CAAC;gBACN,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACtC,CAAC;QACH,CAAC;QACD,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;QAE1B,MAAM,MAAM,GAAG,IAAI,CAAC,gBAAgB,CAAC,MAAM,CAAC,CAAC;QAC7C,OAAO,IAAI,CAAC,WAAW,CAAC,MAAM,EAAE,IAAI,EAAE,UAAU,CAAC,CAAC;IACpD,CAAC;IAEO,gBAAgB,CAAC,MAAkB;QACzC,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC;YAAE,OAAO,MAAM,CAAC;QAEtC,MAAM,MAAM,GAAe,EAAE,CAAC;QAC9B,IAAI,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC;QAExB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACvC,MAAM,WAAW,GAAG,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACtC,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACrC,MAAM,cAAc,GAAG,WAAW,CAAC,MAAM,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM,CAAC;YAEhE,IAAI,WAAW,CAAC,MAAM,GAAG,IAAI,CAAC,YAAY,IAAI,cAAc,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;gBAClF,OAAO,GAAG,CAAC,GAAG,OAAO,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC;YACvC,CAAC;iBAAM,CAAC;gBACN,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;gBACrB,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC;YACtB,CAAC;QACH,CAAC;QAED,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACvB,MAAM,WAAW,GAAG,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACtC,IAAI,WAAW,CAAC,MAAM,GAAG,IAAI,CAAC,YAAY,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAChE,MAAM,IAAI,GAAG,MAAM,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;gBACvC,MAAM,QAAQ,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;gBAChC,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,GAAG,WAAW,CAAC,MAAM,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;oBAClE,MAAM,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,GAAG,CAAC,GAAG,IAAI,EAAE,GAAG,OAAO,CAAC,CAAC;gBACpD,CAAC;qBAAM,CAAC;oBACN,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;gBACvB,CAAC;YACH,CAAC;iBAAM,CAAC;gBACN,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;YACvB,CAAC;QACH,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,kBAAkB,CAAC,QAAgB,EAAE,YAAoB,EAAE,UAAkB;QACnF,MAAM,GAAG,GAAG,YAAY,CAAC,OAAO,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAC;QACvD,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,UAAU,CAAC;IACrC,CAAC;IAEO,WAAW,CACjB,MAAkB,EAClB,YAAoB,EACpB,UAAkB;QAElB,MAAM,MAAM,GAAoB,EAAE,CAAC;QACnC,IAAI,UAAU,GAAG,CAAC,CAAC;QAEnB,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;YAC3B,MAAM,WAAW,GAAG,IAAI,CAAC,kBAAkB,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,UAAU,CAAC,CAAC;YAChF,MAAM,YAAY,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YAC7C,MAAM,SAAS,GAAG,IAAI,CAAC,kBAAkB,CAAC,YAAY,EAAE,YAAY,EAAE,WAAW,CAAC,CAAC;YACnF,MAAM,SAAS,GAAG,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC;YAElD,MAAM,OAAO,GAAG,YAAY,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC;YAE3D,IAAI,OAAO,CAAC,MAAM,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;gBACxC,MAAM,CAAC,IAAI,CAAC;oBACV,EAAE,EAAE,MAAM,EAAE;oBACZ,UAAU;oBACV,OAAO;oBACP,WAAW;oBACX,SAAS;oBACT,KAAK,EAAE,MAAM,CAAC,MAAM;iBACrB,CAAC,CAAC;gBACH,UAAU,GAAG,SAAS,CAAC;YACzB,CAAC;iBAAM,CAAC;gBACN,MAAM,SAAS,GAAG,IAAI,CAAC,eAAe,CACpC,KAAK,EACL,YAAY,EACZ,UAAU,EACV,UAAU,EACV,MAAM,CAAC,MAAM,CACd,CAAC;gBACF,MAAM,CAAC,IAAI,CAAC,GAAG,SAAS,CAAC,CAAC;gBAC1B,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACzB,UAAU,GAAG,SAAS,CAAC,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC;gBACzD,CAAC;YACH,CAAC;QACH,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,eAAe,CACrB,SAAmB,EACnB,YAAoB,EACpB,UAAkB,EAClB,UAAkB,EAClB,UAAkB;QAElB,MAAM,MAAM,GAAoB,EAAE,CAAC;QACnC,IAAI,gBAAgB,GAAa,EAAE,CAAC;QACpC,IAAI,aAAa,GAAG,CAAC,CAAC;QACtB,IAAI,KAAK,GAAG,UAAU,CAAC;QACvB,IAAI,MAAM,GAAG,UAAU,CAAC;QAExB,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;YACjC,IAAI,QAAQ,CAAC,MAAM,GAAG,IAAI,CAAC,YAAY,EAAE,CAAC;gBACxC,IAAI,gBAAgB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBAChC,MAAM,KAAK,GAAG,IAAI,CAAC,iBAAiB,CAClC,gBAAgB,EAChB,YAAY,EACZ,UAAU,EACV,MAAM,EACN,KAAK,EAAE,CACR,CAAC;oBACF,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;oBACnB,MAAM,GAAG,KAAK,CAAC,SAAS,CAAC;oBACzB,gBAAgB,GAAG,EAAE,CAAC;oBACtB,aAAa,GAAG,CAAC,CAAC;gBACpB,CAAC;gBAED,MAAM,aAAa,GAAG,IAAI,CAAC,kBAAkB,CAAC,QAAQ,EAAE,YAAY,EAAE,MAAM,CAAC,CAAC;gBAC9E,KAAK,IAAI,GAAG,GAAG,CAAC,EAAE,GAAG,GAAG,QAAQ,CAAC,MAAM,EAAE,GAAG,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;oBAClE,MAAM,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,GAAG,IAAI,CAAC,YAAY,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC;oBACpE,MAAM,KAAK,GAAG,QAAQ,CAAC,KAAK,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAC;oBAC5C,MAAM,CAAC,IAAI,CAAC;wBACV,EAAE,EAAE,MAAM,EAAE;wBACZ,UAAU;wBACV,OAAO,EAAE,KAAK;wBACd,WAAW,EAAE,aAAa,GAAG,GAAG;wBAChC,SAAS,EAAE,aAAa,GAAG,QAAQ;wBACnC,KAAK,EAAE,KAAK,EAAE;qBACf,CAAC,CAAC;gBACL,CAAC;gBACD,MAAM,GAAG,aAAa,GAAG,QAAQ,CAAC,MAAM,CAAC;gBACzC,SAAS;YACX,CAAC;YAED,MAAM,SAAS,GAAG,aAAa,GAAG,CAAC,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,MAAM,CAAC;YAE1F,IAAI,SAAS,GAAG,IAAI,CAAC,YAAY,IAAI,gBAAgB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACjE,MAAM,KAAK,GAAG,IAAI,CAAC,iBAAiB,CAClC,gBAAgB,EAChB,YAAY,EACZ,UAAU,EACV,MAAM,EACN,KAAK,EAAE,CACR,CAAC;gBACF,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;gBACnB,MAAM,GAAG,KAAK,CAAC,SAAS,CAAC;gBACzB,gBAAgB,GAAG,CAAC,QAAQ,CAAC,CAAC;gBAC9B,aAAa,GAAG,QAAQ,CAAC,MAAM,CAAC;YAClC,CAAC;iBAAM,CAAC;gBACN,gBAAgB,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBAChC,aAAa,GAAG,SAAS,CAAC;YAC5B,CAAC;QACH,CAAC;QAED,IAAI,gBAAgB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAChC,MAAM,CAAC,IAAI,CACT,IAAI,CAAC,iBAAiB,CAAC,gBAAgB,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CACpF,CAAC;QACJ,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,iBAAiB,CACvB,SAAmB,EACnB,YAAoB,EACpB,UAAkB,EAClB,UAAkB,EAClB,KAAa;QAEb,MAAM,WAAW,GAAG,IAAI,CAAC,kBAAkB,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,UAAU,CAAC,CAAC;QACpF,MAAM,YAAY,GAAG,SAAS,CAAC,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QACrD,MAAM,SAAS,GAAG,IAAI,CAAC,kBAAkB,CAAC,YAAY,EAAE,YAAY,EAAE,WAAW,CAAC,CAAC;QACnF,MAAM,SAAS,GAAG,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC;QAElD,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,UAAU;YACV,OAAO,EAAE,YAAY,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC;YACnD,WAAW;YACX,SAAS;YACT,KAAK;SACN,CAAC;IACJ,CAAC;CACF"}
package/dist/index.d.ts CHANGED
@@ -1,4 +1,4 @@
1
- export declare const VERSION = "0.1.0";
1
+ export declare const VERSION: string;
2
2
  export { RAGPipeline, type RAGPipelineDeps } from './rag-pipeline.js';
3
3
  export { RAGPipelineBuilder } from './rag-builder.js';
4
4
  export * from './loaders/index.js';
@@ -6,6 +6,6 @@ export * from './chunkers/index.js';
6
6
  export * from './retrievers/index.js';
7
7
  export * from './rerankers/index.js';
8
8
  export * from './schema.js';
9
- export { createSearchTool, createIngestTool, ragTools, type RAGTool } from './tools.js';
9
+ export { createSearchTool, createIngestTool, ragTools, type RAGTool, type IngestToolOptions, } from './tools.js';
10
10
  export type { RAGDocument, DocumentChunk, DocumentLoader, Chunker, AsyncChunker, ChunkingConfig, ChunkingStrategy, Retriever, RetrievalConfig, RetrievalStrategy, RetrievalResult, Reranker, RAGPipelineConfig, EmbeddingService, EmbeddingAdapter, } from '@cogitator-ai/types';
11
11
  //# sourceMappingURL=index.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,OAAO,UAAU,CAAC;AAE/B,OAAO,EAAE,WAAW,EAAE,KAAK,eAAe,EAAE,MAAM,gBAAgB,CAAC;AACnE,OAAO,EAAE,kBAAkB,EAAE,MAAM,eAAe,CAAC;AAEnD,cAAc,WAAW,CAAC;AAC1B,cAAc,YAAY,CAAC;AAC3B,cAAc,cAAc,CAAC;AAC7B,cAAc,aAAa,CAAC;AAE5B,cAAc,UAAU,CAAC;AAEzB,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,QAAQ,EAAE,KAAK,OAAO,EAAE,MAAM,SAAS,CAAC;AAErF,YAAY,EACV,WAAW,EACX,aAAa,EACb,cAAc,EACd,OAAO,EACP,YAAY,EACZ,cAAc,EACd,gBAAgB,EAChB,SAAS,EACT,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,QAAQ,EACR,iBAAiB,EACjB,gBAAgB,EAChB,gBAAgB,GACjB,MAAM,qBAAqB,CAAC"}
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAIA,eAAO,MAAM,OAAO,EAAE,MAA4B,CAAC;AAEnD,OAAO,EAAE,WAAW,EAAE,KAAK,eAAe,EAAE,MAAM,mBAAmB,CAAC;AACtE,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AAEtD,cAAc,oBAAoB,CAAC;AACnC,cAAc,qBAAqB,CAAC;AACpC,cAAc,uBAAuB,CAAC;AACtC,cAAc,sBAAsB,CAAC;AAErC,cAAc,aAAa,CAAC;AAE5B,OAAO,EACL,gBAAgB,EAChB,gBAAgB,EAChB,QAAQ,EACR,KAAK,OAAO,EACZ,KAAK,iBAAiB,GACvB,MAAM,YAAY,CAAC;AAEpB,YAAY,EACV,WAAW,EACX,aAAa,EACb,cAAc,EACd,OAAO,EACP,YAAY,EACZ,cAAc,EACd,gBAAgB,EAChB,SAAS,EACT,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,QAAQ,EACR,iBAAiB,EACjB,gBAAgB,EAChB,gBAAgB,GACjB,MAAM,qBAAqB,CAAC"}
package/dist/index.js CHANGED
@@ -1,4 +1,6 @@
1
- export const VERSION = '0.1.0';
1
+ import { createRequire } from 'node:module';
2
+ const packageJson = createRequire(import.meta.url)('../package.json');
3
+ export const VERSION = packageJson.version;
2
4
  export { RAGPipeline } from './rag-pipeline.js';
3
5
  export { RAGPipelineBuilder } from './rag-builder.js';
4
6
  export * from './loaders/index.js';
@@ -6,5 +8,5 @@ export * from './chunkers/index.js';
6
8
  export * from './retrievers/index.js';
7
9
  export * from './rerankers/index.js';
8
10
  export * from './schema.js';
9
- export { createSearchTool, createIngestTool, ragTools } from './tools.js';
11
+ export { createSearchTool, createIngestTool, ragTools, } from './tools.js';
10
12
  //# sourceMappingURL=index.js.map
package/dist/index.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,OAAO,GAAG,OAAO,CAAC;AAE/B,OAAO,EAAE,WAAW,EAAwB,MAAM,gBAAgB,CAAC;AACnE,OAAO,EAAE,kBAAkB,EAAE,MAAM,eAAe,CAAC;AAEnD,cAAc,WAAW,CAAC;AAC1B,cAAc,YAAY,CAAC;AAC3B,cAAc,cAAc,CAAC;AAC7B,cAAc,aAAa,CAAC;AAE5B,cAAc,UAAU,CAAC;AAEzB,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,QAAQ,EAAgB,MAAM,SAAS,CAAC"}
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,aAAa,CAAC;AAE5C,MAAM,WAAW,GAAG,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,iBAAiB,CAAwB,CAAC;AAE7F,MAAM,CAAC,MAAM,OAAO,GAAW,WAAW,CAAC,OAAO,CAAC;AAEnD,OAAO,EAAE,WAAW,EAAwB,MAAM,mBAAmB,CAAC;AACtE,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AAEtD,cAAc,oBAAoB,CAAC;AACnC,cAAc,qBAAqB,CAAC;AACpC,cAAc,uBAAuB,CAAC;AACtC,cAAc,sBAAsB,CAAC;AAErC,cAAc,aAAa,CAAC;AAE5B,OAAO,EACL,gBAAgB,EAChB,gBAAgB,EAChB,QAAQ,GAGT,MAAM,YAAY,CAAC"}
@@ -1 +1 @@
1
- {"version":3,"file":"csv-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/csv-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAUvE,MAAM,WAAW,gBAAgB;IAC/B,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED,qBAAa,SAAU,YAAW,cAAc;IAC9C,QAAQ,CAAC,cAAc,WAAW;IAClC,OAAO,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAS;IACxC,OAAO,CAAC,QAAQ,CAAC,eAAe,CAAC,CAAW;IAC5C,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAS;gBAExB,OAAO,CAAC,EAAE,gBAAgB;IAMhC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IA4BlD,OAAO,CAAC,eAAe;CAWxB"}
1
+ {"version":3,"file":"csv-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/csv-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAevE,MAAM,WAAW,gBAAgB;IAC/B,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED,qBAAa,SAAU,YAAW,cAAc;IAC9C,QAAQ,CAAC,cAAc,WAAW;IAClC,OAAO,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAS;IACxC,OAAO,CAAC,QAAQ,CAAC,eAAe,CAAC,CAAW;IAC5C,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAS;gBAExB,OAAO,CAAC,EAAE,gBAAgB;IAMhC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IAmClD,OAAO,CAAC,eAAe;CAWxB"}
@@ -2,12 +2,15 @@ import { readFile } from 'node:fs/promises';
2
2
  import { resolve } from 'node:path';
3
3
  import { nanoid } from 'nanoid';
4
4
  async function loadPapaparse() {
5
+ let mod;
5
6
  try {
6
- return await import('papaparse');
7
+ mod = (await import('papaparse'));
7
8
  }
8
9
  catch {
9
10
  throw new Error('papaparse is required for CSVLoader. Install it: pnpm add papaparse');
10
11
  }
12
+ const interop = mod.default;
13
+ return interop && typeof interop.parse === 'function' ? interop : mod;
11
14
  }
12
15
  export class CSVLoader {
13
16
  supportedTypes = ['csv'];
@@ -30,15 +33,20 @@ export class CSVLoader {
30
33
  });
31
34
  const headers = result.meta.fields ?? [];
32
35
  const contentCol = this.contentColumn ?? headers[0];
33
- return result.data.map((row) => {
36
+ if (contentCol === undefined)
37
+ return [];
38
+ if (this.contentColumn && !headers.includes(this.contentColumn)) {
39
+ throw new Error(`CSVLoader: contentColumn "${this.contentColumn}" not found in CSV headers: ${headers.join(', ')}`);
40
+ }
41
+ return result.data.map((row, index) => {
34
42
  const content = row[contentCol] ?? '';
35
- const metadata = this.extractMetadata(row);
43
+ const metadata = { ...this.extractMetadata(row), row: index + 1 };
36
44
  return {
37
45
  id: nanoid(),
38
46
  content,
39
47
  source: filePath,
40
48
  sourceType: 'csv',
41
- ...(metadata && Object.keys(metadata).length > 0 && { metadata }),
49
+ metadata,
42
50
  };
43
51
  });
44
52
  }
@@ -1 +1 @@
1
- {"version":3,"file":"csv-loader.js","sourceRoot":"","sources":["../../src/loaders/csv-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,KAAK,UAAU,aAAa;IAC1B,IAAI,CAAC;QACH,OAAO,MAAM,MAAM,CAAC,WAAW,CAAC,CAAC;IACnC,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAC;IACzF,CAAC;AACH,CAAC;AAQD,MAAM,OAAO,SAAS;IACX,cAAc,GAAG,CAAC,KAAK,CAAC,CAAC;IACjB,aAAa,CAAU;IACvB,eAAe,CAAY;IAC3B,SAAS,CAAU;IAEpC,YAAY,OAA0B;QACpC,IAAI,CAAC,aAAa,GAAG,OAAO,EAAE,aAAa,CAAC;QAC5C,IAAI,CAAC,eAAe,GAAG,OAAO,EAAE,eAAe,CAAC;QAChD,IAAI,CAAC,SAAS,GAAG,OAAO,EAAE,SAAS,CAAC;IACtC,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,IAAI,GAAG,MAAM,aAAa,EAAE,CAAC;QACnC,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAE9C,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAyB,GAAG,EAAE;YACrD,MAAM,EAAE,IAAI;YACZ,cAAc,EAAE,IAAI;YACpB,SAAS,EAAE,IAAI,CAAC,SAAS;SAC1B,CAAC,CAAC;QAEH,MAAM,OAAO,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,IAAI,EAAE,CAAC;QACzC,MAAM,UAAU,GAAG,IAAI,CAAC,aAAa,IAAI,OAAO,CAAC,CAAC,CAAC,CAAC;QAEpD,OAAO,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YAC7B,MAAM,OAAO,GAAG,GAAG,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC;YACtC,MAAM,QAAQ,GAAG,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC;YAE3C,OAAO;gBACL,EAAE,EAAE,MAAM,EAAE;gBACZ,OAAO;gBACP,MAAM,EAAE,QAAQ;gBAChB,UAAU,EAAE,KAAc;gBAC1B,GAAG,CAAC,QAAQ,IAAI,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,QAAQ,EAAE,CAAC;aAClE,CAAC;QACJ,CAAC,CAAC,CAAC;IACL,CAAC;IAEO,eAAe,CAAC,GAA2B;QACjD,IAAI,CAAC,IAAI,CAAC,eAAe;YAAE,OAAO,SAAS,CAAC;QAE5C,MAAM,QAAQ,GAA4B,EAAE,CAAC;QAC7C,KAAK,MAAM,GAAG,IAAI,IAAI,CAAC,eAAe,EAAE,CAAC;YACvC,IAAI,GAAG,IAAI,GAAG,EAAE,CAAC;gBACf,QAAQ,CAAC,GAAG,CAAC,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC;YAC3B,CAAC;QACH,CAAC;QACD,OAAO,QAAQ,CAAC;IAClB,CAAC;CACF"}
1
+ {"version":3,"file":"csv-loader.js","sourceRoot":"","sources":["../../src/loaders/csv-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAKhC,KAAK,UAAU,aAAa;IAC1B,IAAI,GAA8B,CAAC;IACnC,IAAI,CAAC;QACH,GAAG,GAAG,CAAC,MAAM,MAAM,CAAC,WAAW,CAAC,CAA8B,CAAC;IACjE,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAC;IACzF,CAAC;IACD,MAAM,OAAO,GAAG,GAAG,CAAC,OAAO,CAAC;IAC5B,OAAO,OAAO,IAAI,OAAO,OAAO,CAAC,KAAK,KAAK,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,CAAC;AACxE,CAAC;AAQD,MAAM,OAAO,SAAS;IACX,cAAc,GAAG,CAAC,KAAK,CAAC,CAAC;IACjB,aAAa,CAAU;IACvB,eAAe,CAAY;IAC3B,SAAS,CAAU;IAEpC,YAAY,OAA0B;QACpC,IAAI,CAAC,aAAa,GAAG,OAAO,EAAE,aAAa,CAAC;QAC5C,IAAI,CAAC,eAAe,GAAG,OAAO,EAAE,eAAe,CAAC;QAChD,IAAI,CAAC,SAAS,GAAG,OAAO,EAAE,SAAS,CAAC;IACtC,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,IAAI,GAAG,MAAM,aAAa,EAAE,CAAC;QACnC,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAE9C,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAyB,GAAG,EAAE;YACrD,MAAM,EAAE,IAAI;YACZ,cAAc,EAAE,IAAI;YACpB,SAAS,EAAE,IAAI,CAAC,SAAS;SAC1B,CAAC,CAAC;QAEH,MAAM,OAAO,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,IAAI,EAAE,CAAC;QACzC,MAAM,UAAU,GAAG,IAAI,CAAC,aAAa,IAAI,OAAO,CAAC,CAAC,CAAC,CAAC;QACpD,IAAI,UAAU,KAAK,SAAS;YAAE,OAAO,EAAE,CAAC;QAExC,IAAI,IAAI,CAAC,aAAa,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC,aAAa,CAAC,EAAE,CAAC;YAChE,MAAM,IAAI,KAAK,CACb,6BAA6B,IAAI,CAAC,aAAa,+BAA+B,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CACnG,CAAC;QACJ,CAAC;QAED,OAAO,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,EAAE;YACpC,MAAM,OAAO,GAAG,GAAG,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC;YACtC,MAAM,QAAQ,GAAG,EAAE,GAAG,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC,EAAE,GAAG,EAAE,KAAK,GAAG,CAAC,EAAE,CAAC;YAElE,OAAO;gBACL,EAAE,EAAE,MAAM,EAAE;gBACZ,OAAO;gBACP,MAAM,EAAE,QAAQ;gBAChB,UAAU,EAAE,KAAc;gBAC1B,QAAQ;aACT,CAAC;QACJ,CAAC,CAAC,CAAC;IACL,CAAC;IAEO,eAAe,CAAC,GAA2B;QACjD,IAAI,CAAC,IAAI,CAAC,eAAe;YAAE,OAAO,SAAS,CAAC;QAE5C,MAAM,QAAQ,GAA4B,EAAE,CAAC;QAC7C,KAAK,MAAM,GAAG,IAAI,IAAI,CAAC,eAAe,EAAE,CAAC;YACvC,IAAI,GAAG,IAAI,GAAG,EAAE,CAAC;gBACf,QAAQ,CAAC,GAAG,CAAC,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC;YAC3B,CAAC;QACH,CAAC;QACD,OAAO,QAAQ,CAAC;IAClB,CAAC;CACF"}
@@ -2,6 +2,10 @@ import type { DocumentLoader, RAGDocument } from '@cogitator-ai/types';
2
2
  export interface HTMLLoaderOptions {
3
3
  selector?: string;
4
4
  }
5
+ /**
6
+ * Extracts readable text from HTML: scripts, styles and other non-content elements are
7
+ * dropped, block elements become line breaks and whitespace is normalized.
8
+ */
5
9
  export declare class HTMLLoader implements DocumentLoader {
6
10
  readonly supportedTypes: string[];
7
11
  readonly selector: string;
@@ -1 +1 @@
1
- {"version":3,"file":"html-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/html-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAUvE,MAAM,WAAW,iBAAiB;IAChC,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,qBAAa,UAAW,YAAW,cAAc;IAC/C,QAAQ,CAAC,cAAc,WAAmB;IAC1C,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;gBAEd,OAAO,CAAC,EAAE,iBAAiB;IAIjC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IAM5C,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,GAAG,KAAK,GAAG,OAAO,CAAC,WAAW,CAAC;CAkBhG"}
1
+ {"version":3,"file":"html-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/html-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAUvE,MAAM,WAAW,iBAAiB;IAChC,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAgBD;;;GAGG;AACH,qBAAa,UAAW,YAAW,cAAc;IAC/C,QAAQ,CAAC,cAAc,WAAmB;IAC1C,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;gBAEd,OAAO,CAAC,EAAE,iBAAiB;IAIjC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IAM5C,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,GAAG,KAAK,GAAG,OAAO,CAAC,WAAW,CAAC;CA+BhG"}
@@ -9,6 +9,21 @@ async function loadCheerio() {
9
9
  throw new Error('cheerio is required for HTMLLoader. Install it: pnpm add cheerio');
10
10
  }
11
11
  }
12
+ const NON_CONTENT_SELECTOR = 'script, style, noscript, template, svg, iframe, object, head';
13
+ const BLOCK_SELECTOR = 'address, article, aside, blockquote, dd, div, dl, dt, fieldset, figcaption, figure, footer, ' +
14
+ 'form, h1, h2, h3, h4, h5, h6, header, hr, li, main, nav, ol, p, pre, section, table, tr, ul';
15
+ function normalizeWhitespace(text) {
16
+ return text
17
+ .replace(/\r\n?/g, '\n')
18
+ .replace(/[^\S\n]+/g, ' ')
19
+ .replace(/ *\n */g, '\n')
20
+ .replace(/\n{3,}/g, '\n\n')
21
+ .trim();
22
+ }
23
+ /**
24
+ * Extracts readable text from HTML: scripts, styles and other non-content elements are
25
+ * dropped, block elements become line breaks and whitespace is normalized.
26
+ */
12
27
  export class HTMLLoader {
13
28
  supportedTypes = ['html', 'htm'];
14
29
  selector;
@@ -23,8 +38,17 @@ export class HTMLLoader {
23
38
  async parseHTML(html, source, sourceType) {
24
39
  const cheerio = await loadCheerio();
25
40
  const $ = cheerio.load(html);
26
- const content = $(this.selector).text().trim();
27
- const title = $('title').text().trim() || undefined;
41
+ const title = $('title').first().text().trim() || undefined;
42
+ $(NON_CONTENT_SELECTOR).remove();
43
+ $('br').replaceWith('\n');
44
+ $(BLOCK_SELECTOR).each((_, element) => {
45
+ $(element).before('\n').after('\n');
46
+ });
47
+ $('td, th').after(' ');
48
+ const content = normalizeWhitespace($(this.selector)
49
+ .map((_, element) => $(element).text())
50
+ .get()
51
+ .join('\n\n'));
28
52
  const metadata = {};
29
53
  if (title)
30
54
  metadata.title = title;
@@ -1 +1 @@
1
- {"version":3,"file":"html-loader.js","sourceRoot":"","sources":["../../src/loaders/html-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,KAAK,UAAU,WAAW;IACxB,IAAI,CAAC;QACH,OAAO,MAAM,MAAM,CAAC,SAAS,CAAC,CAAC;IACjC,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,kEAAkE,CAAC,CAAC;IACtF,CAAC;AACH,CAAC;AAMD,MAAM,OAAO,UAAU;IACZ,cAAc,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;IACjC,QAAQ,CAAS;IAE1B,YAAY,OAA2B;QACrC,IAAI,CAAC,QAAQ,GAAG,OAAO,EAAE,QAAQ,IAAI,MAAM,CAAC;IAC9C,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAC/C,OAAO,CAAC,MAAM,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,QAAQ,EAAE,MAAM,CAAC,CAAC,CAAC;IACxD,CAAC;IAED,KAAK,CAAC,SAAS,CAAC,IAAY,EAAE,MAAc,EAAE,UAA0B;QACtE,MAAM,OAAO,GAAG,MAAM,WAAW,EAAE,CAAC;QACpC,MAAM,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAE7B,MAAM,OAAO,GAAG,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,IAAI,EAAE,CAAC;QAC/C,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,SAAS,CAAC;QAEpD,MAAM,QAAQ,GAA4B,EAAE,CAAC;QAC7C,IAAI,KAAK;YAAE,QAAQ,CAAC,KAAK,GAAG,KAAK,CAAC;QAElC,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM;YACN,UAAU;YACV,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,QAAQ,EAAE,CAAC;SACtD,CAAC;IACJ,CAAC;CACF"}
1
+ {"version":3,"file":"html-loader.js","sourceRoot":"","sources":["../../src/loaders/html-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,KAAK,UAAU,WAAW;IACxB,IAAI,CAAC;QACH,OAAO,MAAM,MAAM,CAAC,SAAS,CAAC,CAAC;IACjC,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,kEAAkE,CAAC,CAAC;IACtF,CAAC;AACH,CAAC;AAMD,MAAM,oBAAoB,GAAG,8DAA8D,CAAC;AAC5F,MAAM,cAAc,GAClB,8FAA8F;IAC9F,6FAA6F,CAAC;AAEhG,SAAS,mBAAmB,CAAC,IAAY;IACvC,OAAO,IAAI;SACR,OAAO,CAAC,QAAQ,EAAE,IAAI,CAAC;SACvB,OAAO,CAAC,WAAW,EAAE,GAAG,CAAC;SACzB,OAAO,CAAC,SAAS,EAAE,IAAI,CAAC;SACxB,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC;SAC1B,IAAI,EAAE,CAAC;AACZ,CAAC;AAED;;;GAGG;AACH,MAAM,OAAO,UAAU;IACZ,cAAc,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;IACjC,QAAQ,CAAS;IAE1B,YAAY,OAA2B;QACrC,IAAI,CAAC,QAAQ,GAAG,OAAO,EAAE,QAAQ,IAAI,MAAM,CAAC;IAC9C,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAC/C,OAAO,CAAC,MAAM,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,QAAQ,EAAE,MAAM,CAAC,CAAC,CAAC;IACxD,CAAC;IAED,KAAK,CAAC,SAAS,CAAC,IAAY,EAAE,MAAc,EAAE,UAA0B;QACtE,MAAM,OAAO,GAAG,MAAM,WAAW,EAAE,CAAC;QACpC,MAAM,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAE7B,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,CAAC,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,SAAS,CAAC;QAE5D,CAAC,CAAC,oBAAoB,CAAC,CAAC,MAAM,EAAE,CAAC;QACjC,CAAC,CAAC,IAAI,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC;QAC1B,CAAC,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,EAAE;YACpC,CAAC,CAAC,OAAO,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACtC,CAAC,CAAC,CAAC;QACH,CAAC,CAAC,QAAQ,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QAEvB,MAAM,OAAO,GAAG,mBAAmB,CACjC,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC;aACb,GAAG,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,CAAC;aACtC,GAAG,EAAE;aACL,IAAI,CAAC,MAAM,CAAC,CAChB,CAAC;QAEF,MAAM,QAAQ,GAA4B,EAAE,CAAC;QAC7C,IAAI,KAAK;YAAE,QAAQ,CAAC,KAAK,GAAG,KAAK,CAAC;QAElC,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM;YACN,UAAU;YACV,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,QAAQ,EAAE,CAAC;SACtD,CAAC;IACJ,CAAC;CACF"}
@@ -1 +1 @@
1
- {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/loaders/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAC3C,OAAO,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AACnD,YAAY,EAAE,qBAAqB,EAAE,MAAM,mBAAmB,CAAC;AAC/D,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAC3C,YAAY,EAAE,iBAAiB,EAAE,MAAM,eAAe,CAAC;AACvD,OAAO,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AACzC,YAAY,EAAE,gBAAgB,EAAE,MAAM,cAAc,CAAC;AACrD,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAC3C,YAAY,EAAE,iBAAiB,EAAE,MAAM,eAAe,CAAC;AACvD,OAAO,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AACzC,YAAY,EAAE,gBAAgB,EAAE,MAAM,cAAc,CAAC;AACrD,OAAO,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AACzC,YAAY,EAAE,gBAAgB,EAAE,MAAM,cAAc,CAAC"}
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/loaders/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,YAAY,EAAE,qBAAqB,EAAE,MAAM,sBAAsB,CAAC;AAClE,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,YAAY,EAAE,iBAAiB,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAC5C,YAAY,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AACxD,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,YAAY,EAAE,iBAAiB,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAC5C,YAAY,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AACxD,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAC5C,YAAY,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC"}
@@ -1 +1 @@
1
- {"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/loaders/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAC3C,OAAO,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAEnD,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAE3C,OAAO,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAEzC,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAE3C,OAAO,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAEzC,OAAO,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC"}
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/loaders/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAEtD,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAE9C,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAE5C,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAE9C,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAE5C,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC"}
@@ -11,6 +11,7 @@ export declare class JSONLoader implements DocumentLoader {
11
11
  load(source: string): Promise<RAGDocument[]>;
12
12
  private itemToDocument;
13
13
  private extractContent;
14
+ private valueToString;
14
15
  private extractMetadata;
15
16
  }
16
17
  //# sourceMappingURL=json-loader.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"json-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/json-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAIvE,MAAM,WAAW,iBAAiB;IAChC,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;CAC3B;AAED,qBAAa,UAAW,YAAW,cAAc;IAC/C,QAAQ,CAAC,cAAc,WAAY;IACnC,OAAO,CAAC,QAAQ,CAAC,YAAY,CAAC,CAAS;IACvC,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAC,CAAW;gBAE/B,OAAO,CAAC,EAAE,iBAAiB;IAKjC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IASlD,OAAO,CAAC,cAAc;IAsBtB,OAAO,CAAC,cAAc;IActB,OAAO,CAAC,eAAe;CAWxB"}
1
+ {"version":3,"file":"json-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/json-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAIvE,MAAM,WAAW,iBAAiB;IAChC,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;CAC3B;AAED,qBAAa,UAAW,YAAW,cAAc;IAC/C,QAAQ,CAAC,cAAc,WAAY;IACnC,OAAO,CAAC,QAAQ,CAAC,YAAY,CAAC,CAAS;IACvC,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAC,CAAW;gBAE/B,OAAO,CAAC,EAAE,iBAAiB;IAKjC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IAgBlD,OAAO,CAAC,cAAc;IAsBtB,OAAO,CAAC,cAAc;IActB,OAAO,CAAC,aAAa;IAKrB,OAAO,CAAC,eAAe;CAWxB"}
@@ -13,7 +13,14 @@ export class JSONLoader {
13
13
  async load(source) {
14
14
  const filePath = resolve(source);
15
15
  const raw = await readFile(filePath, 'utf-8');
16
- const data = JSON.parse(raw);
16
+ let data;
17
+ try {
18
+ data = JSON.parse(raw);
19
+ }
20
+ catch (err) {
21
+ const message = err instanceof Error ? err.message : String(err);
22
+ throw new Error(`JSONLoader: failed to parse "${filePath}": ${message}`);
23
+ }
17
24
  const items = Array.isArray(data) ? data : [data];
18
25
  return items.map((item) => this.itemToDocument(item, filePath));
19
26
  }
@@ -39,15 +46,20 @@ export class JSONLoader {
39
46
  }
40
47
  extractContent(obj) {
41
48
  if (this.contentField && this.contentField in obj) {
42
- return String(obj[this.contentField]);
49
+ return this.valueToString(obj[this.contentField]);
43
50
  }
44
51
  for (const field of CONTENT_FIELDS) {
45
52
  if (field in obj) {
46
- return String(obj[field]);
53
+ return this.valueToString(obj[field]);
47
54
  }
48
55
  }
49
56
  return JSON.stringify(obj, null, 2);
50
57
  }
58
+ valueToString(value) {
59
+ if (typeof value === 'string')
60
+ return value;
61
+ return JSON.stringify(value, null, 2);
62
+ }
51
63
  extractMetadata(obj) {
52
64
  if (!this.metadataFields)
53
65
  return undefined;
@@ -1 +1 @@
1
- {"version":3,"file":"json-loader.js","sourceRoot":"","sources":["../../src/loaders/json-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,MAAM,cAAc,GAAG,CAAC,SAAS,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC;AAOnD,MAAM,OAAO,UAAU;IACZ,cAAc,GAAG,CAAC,MAAM,CAAC,CAAC;IAClB,YAAY,CAAU;IACtB,cAAc,CAAY;IAE3C,YAAY,OAA2B;QACrC,IAAI,CAAC,YAAY,GAAG,OAAO,EAAE,YAAY,CAAC;QAC1C,IAAI,CAAC,cAAc,GAAG,OAAO,EAAE,cAAc,CAAC;IAChD,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAC9C,MAAM,IAAI,GAAY,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QAEtC,MAAM,KAAK,GAAG,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC;QAClD,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,cAAc,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC;IAClE,CAAC;IAEO,cAAc,CAAC,IAAa,EAAE,MAAc;QAClD,IAAI,OAAO,IAAI,KAAK,QAAQ,IAAI,IAAI,KAAK,IAAI,IAAI,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,EAAE,CAAC;YACrE,OAAO;gBACL,EAAE,EAAE,MAAM,EAAE;gBACZ,OAAO,EAAE,MAAM,CAAC,IAAI,CAAC;gBACrB,MAAM;gBACN,UAAU,EAAE,MAAM;aACnB,CAAC;QACJ,CAAC;QACD,MAAM,GAAG,GAAG,IAA+B,CAAC;QAC5C,MAAM,OAAO,GAAG,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,CAAC;QACzC,MAAM,QAAQ,GAAG,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC;QAE3C,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM;YACN,UAAU,EAAE,MAAM;YAClB,GAAG,CAAC,QAAQ,IAAI,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,QAAQ,EAAE,CAAC;SAClE,CAAC;IACJ,CAAC;IAEO,cAAc,CAAC,GAA4B;QACjD,IAAI,IAAI,CAAC,YAAY,IAAI,IAAI,CAAC,YAAY,IAAI,GAAG,EAAE,CAAC;YAClD,OAAO,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC;QACxC,CAAC;QAED,KAAK,MAAM,KAAK,IAAI,cAAc,EAAE,CAAC;YACnC,IAAI,KAAK,IAAI,GAAG,EAAE,CAAC;gBACjB,OAAO,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;YAC5B,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC,SAAS,CAAC,GAAG,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;IACtC,CAAC;IAEO,eAAe,CAAC,GAA4B;QAClD,IAAI,CAAC,IAAI,CAAC,cAAc;YAAE,OAAO,SAAS,CAAC;QAE3C,MAAM,QAAQ,GAA4B,EAAE,CAAC;QAC7C,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,cAAc,EAAE,CAAC;YACxC,IAAI,KAAK,IAAI,GAAG,EAAE,CAAC;gBACjB,QAAQ,CAAC,KAAK,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,CAAC;YAC/B,CAAC;QACH,CAAC;QACD,OAAO,QAAQ,CAAC;IAClB,CAAC;CACF"}
1
+ {"version":3,"file":"json-loader.js","sourceRoot":"","sources":["../../src/loaders/json-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,MAAM,cAAc,GAAG,CAAC,SAAS,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC;AAOnD,MAAM,OAAO,UAAU;IACZ,cAAc,GAAG,CAAC,MAAM,CAAC,CAAC;IAClB,YAAY,CAAU;IACtB,cAAc,CAAY;IAE3C,YAAY,OAA2B;QACrC,IAAI,CAAC,YAAY,GAAG,OAAO,EAAE,YAAY,CAAC;QAC1C,IAAI,CAAC,cAAc,GAAG,OAAO,EAAE,cAAc,CAAC;IAChD,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAE9C,IAAI,IAAa,CAAC;QAClB,IAAI,CAAC;YACH,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QACzB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,MAAM,OAAO,GAAG,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;YACjE,MAAM,IAAI,KAAK,CAAC,gCAAgC,QAAQ,MAAM,OAAO,EAAE,CAAC,CAAC;QAC3E,CAAC;QAED,MAAM,KAAK,GAAG,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC;QAClD,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,cAAc,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC;IAClE,CAAC;IAEO,cAAc,CAAC,IAAa,EAAE,MAAc;QAClD,IAAI,OAAO,IAAI,KAAK,QAAQ,IAAI,IAAI,KAAK,IAAI,IAAI,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,EAAE,CAAC;YACrE,OAAO;gBACL,EAAE,EAAE,MAAM,EAAE;gBACZ,OAAO,EAAE,MAAM,CAAC,IAAI,CAAC;gBACrB,MAAM;gBACN,UAAU,EAAE,MAAM;aACnB,CAAC;QACJ,CAAC;QACD,MAAM,GAAG,GAAG,IAA+B,CAAC;QAC5C,MAAM,OAAO,GAAG,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,CAAC;QACzC,MAAM,QAAQ,GAAG,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC;QAE3C,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM;YACN,UAAU,EAAE,MAAM;YAClB,GAAG,CAAC,QAAQ,IAAI,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,QAAQ,EAAE,CAAC;SAClE,CAAC;IACJ,CAAC;IAEO,cAAc,CAAC,GAA4B;QACjD,IAAI,IAAI,CAAC,YAAY,IAAI,IAAI,CAAC,YAAY,IAAI,GAAG,EAAE,CAAC;YAClD,OAAO,IAAI,CAAC,aAAa,CAAC,GAAG,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC;QACpD,CAAC;QAED,KAAK,MAAM,KAAK,IAAI,cAAc,EAAE,CAAC;YACnC,IAAI,KAAK,IAAI,GAAG,EAAE,CAAC;gBACjB,OAAO,IAAI,CAAC,aAAa,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;YACxC,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC,SAAS,CAAC,GAAG,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;IACtC,CAAC;IAEO,aAAa,CAAC,KAAc;QAClC,IAAI,OAAO,KAAK,KAAK,QAAQ;YAAE,OAAO,KAAK,CAAC;QAC5C,OAAO,IAAI,CAAC,SAAS,CAAC,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;IACxC,CAAC;IAEO,eAAe,CAAC,GAA4B;QAClD,IAAI,CAAC,IAAI,CAAC,cAAc;YAAE,OAAO,SAAS,CAAC;QAE3C,MAAM,QAAQ,GAA4B,EAAE,CAAC;QAC7C,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,cAAc,EAAE,CAAC;YACxC,IAAI,KAAK,IAAI,GAAG,EAAE,CAAC;gBACjB,QAAQ,CAAC,KAAK,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,CAAC;YAC/B,CAAC;QACH,CAAC;QACD,OAAO,QAAQ,CAAC;IAClB,CAAC;CACF"}
@@ -1 +1 @@
1
- {"version":3,"file":"markdown-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/markdown-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAMvE,MAAM,WAAW,qBAAqB;IACpC,gBAAgB,CAAC,EAAE,OAAO,CAAC;CAC5B;AAED,qBAAa,cAAe,YAAW,cAAc;IACnD,QAAQ,CAAC,cAAc,WAAiB;IACxC,OAAO,CAAC,QAAQ,CAAC,gBAAgB,CAAU;gBAE/B,OAAO,CAAC,EAAE,qBAAqB;IAIrC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;YAWpC,QAAQ;IAsBtB,OAAO,CAAC,gBAAgB;YAWV,aAAa;CAiB5B"}
1
+ {"version":3,"file":"markdown-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/markdown-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAWvE,MAAM,WAAW,qBAAqB;IACpC,gBAAgB,CAAC,EAAE,OAAO,CAAC;CAC5B;AAED,qBAAa,cAAe,YAAW,cAAc;IACnD,QAAQ,CAAC,cAAc,WAAiB;IACxC,OAAO,CAAC,QAAQ,CAAC,gBAAgB,CAAU;gBAE/B,OAAO,CAAC,EAAE,qBAAqB;IAIrC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;YAWpC,QAAQ;IAsBtB,OAAO,CAAC,gBAAgB;YAWV,aAAa;CAiB5B"}
@@ -2,7 +2,11 @@ import { readFile, readdir, stat } from 'node:fs/promises';
2
2
  import { join, resolve } from 'node:path';
3
3
  import { nanoid } from 'nanoid';
4
4
  const MD_EXTENSIONS = new Set(['md', 'mdx']);
5
- const FRONTMATTER_RE = /^---\r?\n([\s\S]*?)\r?\n---\r?\n/;
5
+ const FRONTMATTER_RE = /^---\r?\n([\s\S]*?)\r?\n---(?:\r?\n|$)/;
6
+ function unquote(value) {
7
+ const quoted = /^(['"])(.*)\1$/.exec(value);
8
+ return quoted ? quoted[2] : value;
9
+ }
6
10
  export class MarkdownLoader {
7
11
  supportedTypes = ['md', 'mdx'];
8
12
  stripFrontmatter;
@@ -38,16 +42,16 @@ export class MarkdownLoader {
38
42
  }
39
43
  parseFrontmatter(raw) {
40
44
  const result = {};
41
- for (const line of raw.split('\n')) {
45
+ for (const line of raw.split(/\r?\n/)) {
42
46
  const match = /^(\w[\w\s-]*?):\s*(.+)$/.exec(line);
43
47
  if (match) {
44
- result[match[1].trim()] = match[2].trim();
48
+ result[match[1].trim()] = unquote(match[2].trim());
45
49
  }
46
50
  }
47
51
  return result;
48
52
  }
49
53
  async loadDirectory(dirPath) {
50
- const entries = await readdir(dirPath);
54
+ const entries = (await readdir(dirPath)).sort();
51
55
  const docs = [];
52
56
  for (const entry of entries) {
53
57
  const ext = entry.split('.').pop()?.toLowerCase() ?? '';
@@ -1 +1 @@
1
- {"version":3,"file":"markdown-loader.js","sourceRoot":"","sources":["../../src/loaders/markdown-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AAC3D,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,MAAM,aAAa,GAAG,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC;AAE7C,MAAM,cAAc,GAAG,kCAAkC,CAAC;AAM1D,MAAM,OAAO,cAAc;IAChB,cAAc,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;IACvB,gBAAgB,CAAU;IAE3C,YAAY,OAA+B;QACzC,IAAI,CAAC,gBAAgB,GAAG,OAAO,EAAE,gBAAgB,IAAI,KAAK,CAAC;IAC7D,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,CAAC;QAElC,IAAI,IAAI,CAAC,WAAW,EAAE,EAAE,CAAC;YACvB,OAAO,IAAI,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC;QACtC,CAAC;QAED,OAAO,CAAC,MAAM,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;IACzC,CAAC;IAEO,KAAK,CAAC,QAAQ,CAAC,QAAgB;QACrC,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAC9C,IAAI,OAAO,GAAG,GAAG,CAAC;QAClB,IAAI,QAA6C,CAAC;QAElD,IAAI,IAAI,CAAC,gBAAgB,EAAE,CAAC;YAC1B,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACvC,IAAI,KAAK,EAAE,CAAC;gBACV,QAAQ,GAAG,IAAI,CAAC,gBAAgB,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;gBAC3C,OAAO,GAAG,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YACvC,CAAC;QACH,CAAC;QAED,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM,EAAE,QAAQ;YAChB,UAAU,EAAE,UAAU;YACtB,GAAG,CAAC,QAAQ,IAAI,EAAE,QAAQ,EAAE,CAAC;SAC9B,CAAC;IACJ,CAAC;IAEO,gBAAgB,CAAC,GAAW;QAClC,MAAM,MAAM,GAA4B,EAAE,CAAC;QAC3C,KAAK,MAAM,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;YACnC,MAAM,KAAK,GAAG,yBAAyB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YACnD,IAAI,KAAK,EAAE,CAAC;gBACV,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;YAC5C,CAAC;QACH,CAAC;QACD,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,KAAK,CAAC,aAAa,CAAC,OAAe;QACzC,MAAM,OAAO,GAAG,MAAM,OAAO,CAAC,OAAO,CAAC,CAAC;QACvC,MAAM,IAAI,GAAkB,EAAE,CAAC;QAE/B,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;YAC5B,MAAM,GAAG,GAAG,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC;YACxD,IAAI,CAAC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC;gBAAE,SAAS;YAEtC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;YACtC,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,CAAC;YAClC,IAAI,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;gBAClB,IAAI,CAAC,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;YAC3C,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC;IACd,CAAC;CACF"}
1
+ {"version":3,"file":"markdown-loader.js","sourceRoot":"","sources":["../../src/loaders/markdown-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AAC3D,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGhC,MAAM,aAAa,GAAG,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC;AAE7C,MAAM,cAAc,GAAG,wCAAwC,CAAC;AAEhE,SAAS,OAAO,CAAC,KAAa;IAC5B,MAAM,MAAM,GAAG,gBAAgB,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAC5C,OAAO,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC,CAAC,KAAK,CAAC;AACrC,CAAC;AAMD,MAAM,OAAO,cAAc;IAChB,cAAc,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;IACvB,gBAAgB,CAAU;IAE3C,YAAY,OAA+B;QACzC,IAAI,CAAC,gBAAgB,GAAG,OAAO,EAAE,gBAAgB,IAAI,KAAK,CAAC;IAC7D,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,CAAC;QAElC,IAAI,IAAI,CAAC,WAAW,EAAE,EAAE,CAAC;YACvB,OAAO,IAAI,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC;QACtC,CAAC;QAED,OAAO,CAAC,MAAM,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;IACzC,CAAC;IAEO,KAAK,CAAC,QAAQ,CAAC,QAAgB;QACrC,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;QAC9C,IAAI,OAAO,GAAG,GAAG,CAAC;QAClB,IAAI,QAA6C,CAAC;QAElD,IAAI,IAAI,CAAC,gBAAgB,EAAE,CAAC;YAC1B,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACvC,IAAI,KAAK,EAAE,CAAC;gBACV,QAAQ,GAAG,IAAI,CAAC,gBAAgB,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;gBAC3C,OAAO,GAAG,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YACvC,CAAC;QACH,CAAC;QAED,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM,EAAE,QAAQ;YAChB,UAAU,EAAE,UAAU;YACtB,GAAG,CAAC,QAAQ,IAAI,EAAE,QAAQ,EAAE,CAAC;SAC9B,CAAC;IACJ,CAAC;IAEO,gBAAgB,CAAC,GAAW;QAClC,MAAM,MAAM,GAA4B,EAAE,CAAC;QAC3C,KAAK,MAAM,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,EAAE,CAAC;YACtC,MAAM,KAAK,GAAG,yBAAyB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YACnD,IAAI,KAAK,EAAE,CAAC;gBACV,MAAM,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,CAAC,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,CAAC,CAAC;YACvD,CAAC;QACH,CAAC;QACD,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,KAAK,CAAC,aAAa,CAAC,OAAe;QACzC,MAAM,OAAO,GAAG,CAAC,MAAM,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QAChD,MAAM,IAAI,GAAkB,EAAE,CAAC;QAE/B,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;YAC5B,MAAM,GAAG,GAAG,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC;YACxD,IAAI,CAAC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC;gBAAE,SAAS;YAEtC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;YACtC,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,CAAC;YAClC,IAAI,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;gBAClB,IAAI,CAAC,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;YAC3C,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC;IACd,CAAC;CACF"}
@@ -9,6 +9,7 @@ export declare class PDFLoader implements DocumentLoader {
9
9
  load(source: string): Promise<RAGDocument[]>;
10
10
  private loadSingleDocument;
11
11
  private loadSplitPages;
12
+ private parseWithErrorContext;
12
13
  private buildPageDoc;
13
14
  }
14
15
  //# sourceMappingURL=pdf-loader.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"pdf-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/pdf-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAuBvE,MAAM,WAAW,gBAAgB;IAC/B,UAAU,CAAC,EAAE,OAAO,CAAC;CACtB;AAED,qBAAa,SAAU,YAAW,cAAc;IAC9C,QAAQ,CAAC,cAAc,WAAW;IAClC,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAU;gBAEzB,OAAO,CAAC,EAAE,gBAAgB;IAIhC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;YAYpC,kBAAkB;YAsBlB,cAAc;IAmB5B,OAAO,CAAC,YAAY;CAkBrB"}
1
+ {"version":3,"file":"pdf-loader.d.ts","sourceRoot":"","sources":["../../src/loaders/pdf-loader.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AA4BvE,MAAM,WAAW,gBAAgB;IAC/B,UAAU,CAAC,EAAE,OAAO,CAAC;CACtB;AAED,qBAAa,SAAU,YAAW,cAAc;IAC9C,QAAQ,CAAC,cAAc,WAAW;IAClC,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAU;gBAEzB,OAAO,CAAC,EAAE,gBAAgB;IAIhC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;YAYpC,kBAAkB;YAsBlB,cAAc;YA6Bd,qBAAqB;IAcnC,OAAO,CAAC,YAAY;CAkBrB"}
@@ -26,7 +26,7 @@ export class PDFLoader {
26
26
  return this.loadSingleDocument(pdfParse, buffer, filePath);
27
27
  }
28
28
  async loadSingleDocument(pdfParse, buffer, source) {
29
- const result = await pdfParse(buffer);
29
+ const result = await this.parseWithErrorContext(pdfParse, buffer, source);
30
30
  const title = result.info?.Title;
31
31
  const metadata = { pages: result.numpages };
32
32
  if (title)
@@ -42,14 +42,33 @@ export class PDFLoader {
42
42
  ];
43
43
  }
44
44
  async loadSplitPages(pdfParse, buffer, source) {
45
- const result = await pdfParse(buffer);
45
+ const pageTexts = [];
46
+ const result = await this.parseWithErrorContext(pdfParse, buffer, source, {
47
+ pagerender: async (pageData) => {
48
+ if (typeof pageData.getTextContent !== 'function')
49
+ return '';
50
+ const textContent = await pageData.getTextContent();
51
+ const text = textContent.items.map((item) => item.str).join('');
52
+ pageTexts.push(text);
53
+ return text;
54
+ },
55
+ });
46
56
  const title = result.info?.Title;
47
- const pages = result.text.split(/\f/).filter((p) => p.trim().length > 0);
57
+ const pages = pageTexts.filter((p) => p.trim().length > 0);
48
58
  if (pages.length === 0) {
49
59
  return [this.buildPageDoc(result.text, source, 1, result.numpages, title)];
50
60
  }
51
61
  return pages.map((text, i) => this.buildPageDoc(text.trim(), source, i + 1, result.numpages, title));
52
62
  }
63
+ async parseWithErrorContext(pdfParse, buffer, source, options) {
64
+ try {
65
+ return await pdfParse(buffer, options);
66
+ }
67
+ catch (err) {
68
+ const message = err instanceof Error ? err.message : String(err);
69
+ throw new Error(`PDFLoader: failed to parse "${source}": ${message}`);
70
+ }
71
+ }
53
72
  buildPageDoc(content, source, pageNumber, totalPages, title) {
54
73
  const metadata = { pageNumber, totalPages };
55
74
  if (title)
@@ -1 +1 @@
1
- {"version":3,"file":"pdf-loader.js","sourceRoot":"","sources":["../../src/loaders/pdf-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAehC,KAAK,UAAU,YAAY;IACzB,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,MAAM,CAAC,WAAW,CAAC,CAAC;QACtC,OAAO,GAAG,CAAC,OAAgC,CAAC;IAC9C,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAC;IACzF,CAAC;AACH,CAAC;AAMD,MAAM,OAAO,SAAS;IACX,cAAc,GAAG,CAAC,KAAK,CAAC,CAAC;IACjB,UAAU,CAAU;IAErC,YAAY,OAA0B;QACpC,IAAI,CAAC,UAAU,GAAG,OAAO,EAAE,UAAU,IAAI,KAAK,CAAC;IACjD,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,MAAM,YAAY,EAAE,CAAC;QACtC,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,QAAQ,CAAC,CAAC;QAExC,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;YACpB,OAAO,IAAI,CAAC,cAAc,CAAC,QAAQ,EAAE,MAAM,EAAE,QAAQ,CAAC,CAAC;QACzD,CAAC;QAED,OAAO,IAAI,CAAC,kBAAkB,CAAC,QAAQ,EAAE,MAAM,EAAE,QAAQ,CAAC,CAAC;IAC7D,CAAC;IAEO,KAAK,CAAC,kBAAkB,CAC9B,QAAoB,EACpB,MAAc,EACd,MAAc;QAEd,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,MAAM,CAAC,CAAC;QACtC,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC;QAEjC,MAAM,QAAQ,GAA4B,EAAE,KAAK,EAAE,MAAM,CAAC,QAAQ,EAAE,CAAC;QACrE,IAAI,KAAK;YAAE,QAAQ,CAAC,KAAK,GAAG,KAAK,CAAC;QAElC,OAAO;YACL;gBACE,EAAE,EAAE,MAAM,EAAE;gBACZ,OAAO,EAAE,MAAM,CAAC,IAAI;gBACpB,MAAM;gBACN,UAAU,EAAE,KAAK;gBACjB,QAAQ;aACT;SACF,CAAC;IACJ,CAAC;IAEO,KAAK,CAAC,cAAc,CAC1B,QAAoB,EACpB,MAAc,EACd,MAAc;QAEd,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,MAAM,CAAC,CAAC;QACtC,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC;QAEjC,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAEzE,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,CAAC,IAAI,CAAC,YAAY,CAAC,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE,MAAM,CAAC,QAAQ,EAAE,KAAK,CAAC,CAAC,CAAC;QAC7E,CAAC;QAED,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,EAAE,CAC3B,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,EAAE,MAAM,EAAE,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC,QAAQ,EAAE,KAAK,CAAC,CACtE,CAAC;IACJ,CAAC;IAEO,YAAY,CAClB,OAAe,EACf,MAAc,EACd,UAAkB,EAClB,UAAkB,EAClB,KAAc;QAEd,MAAM,QAAQ,GAA4B,EAAE,UAAU,EAAE,UAAU,EAAE,CAAC;QACrE,IAAI,KAAK;YAAE,QAAQ,CAAC,KAAK,GAAG,KAAK,CAAC;QAElC,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM;YACN,UAAU,EAAE,KAAK;YACjB,QAAQ;SACT,CAAC;IACJ,CAAC;CACF"}
1
+ {"version":3,"file":"pdf-loader.js","sourceRoot":"","sources":["../../src/loaders/pdf-loader.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAoBhC,KAAK,UAAU,YAAY;IACzB,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,MAAM,CAAC,WAAW,CAAC,CAAC;QACtC,OAAO,GAAG,CAAC,OAAgC,CAAC;IAC9C,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAC;IACzF,CAAC;AACH,CAAC;AAMD,MAAM,OAAO,SAAS;IACX,cAAc,GAAG,CAAC,KAAK,CAAC,CAAC;IACjB,UAAU,CAAU;IAErC,YAAY,OAA0B;QACpC,IAAI,CAAC,UAAU,GAAG,OAAO,EAAE,UAAU,IAAI,KAAK,CAAC;IACjD,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,MAAc;QACvB,MAAM,QAAQ,GAAG,MAAM,YAAY,EAAE,CAAC;QACtC,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;QACjC,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,QAAQ,CAAC,CAAC;QAExC,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;YACpB,OAAO,IAAI,CAAC,cAAc,CAAC,QAAQ,EAAE,MAAM,EAAE,QAAQ,CAAC,CAAC;QACzD,CAAC;QAED,OAAO,IAAI,CAAC,kBAAkB,CAAC,QAAQ,EAAE,MAAM,EAAE,QAAQ,CAAC,CAAC;IAC7D,CAAC;IAEO,KAAK,CAAC,kBAAkB,CAC9B,QAAoB,EACpB,MAAc,EACd,MAAc;QAEd,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,qBAAqB,CAAC,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC;QAC1E,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC;QAEjC,MAAM,QAAQ,GAA4B,EAAE,KAAK,EAAE,MAAM,CAAC,QAAQ,EAAE,CAAC;QACrE,IAAI,KAAK;YAAE,QAAQ,CAAC,KAAK,GAAG,KAAK,CAAC;QAElC,OAAO;YACL;gBACE,EAAE,EAAE,MAAM,EAAE;gBACZ,OAAO,EAAE,MAAM,CAAC,IAAI;gBACpB,MAAM;gBACN,UAAU,EAAE,KAAK;gBACjB,QAAQ;aACT;SACF,CAAC;IACJ,CAAC;IAEO,KAAK,CAAC,cAAc,CAC1B,QAAoB,EACpB,MAAc,EACd,MAAc;QAEd,MAAM,SAAS,GAAa,EAAE,CAAC;QAE/B,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,qBAAqB,CAAC,QAAQ,EAAE,MAAM,EAAE,MAAM,EAAE;YACxE,UAAU,EAAE,KAAK,EAAE,QAAqB,EAAE,EAAE;gBAC1C,IAAI,OAAO,QAAQ,CAAC,cAAc,KAAK,UAAU;oBAAE,OAAO,EAAE,CAAC;gBAC7D,MAAM,WAAW,GAAG,MAAM,QAAQ,CAAC,cAAc,EAAE,CAAC;gBACpD,MAAM,IAAI,GAAG,WAAW,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBAChE,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;gBACrB,OAAO,IAAI,CAAC;YACd,CAAC;SACF,CAAC,CAAC;QAEH,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC;QACjC,MAAM,KAAK,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAE3D,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,CAAC,IAAI,CAAC,YAAY,CAAC,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE,MAAM,CAAC,QAAQ,EAAE,KAAK,CAAC,CAAC,CAAC;QAC7E,CAAC;QAED,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,EAAE,CAC3B,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,EAAE,MAAM,EAAE,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC,QAAQ,EAAE,KAAK,CAAC,CACtE,CAAC;IACJ,CAAC;IAEO,KAAK,CAAC,qBAAqB,CACjC,QAAoB,EACpB,MAAc,EACd,MAAc,EACd,OAAmC;QAEnC,IAAI,CAAC;YACH,OAAO,MAAM,QAAQ,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;QACzC,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,MAAM,OAAO,GAAG,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;YACjE,MAAM,IAAI,KAAK,CAAC,+BAA+B,MAAM,MAAM,OAAO,EAAE,CAAC,CAAC;QACxE,CAAC;IACH,CAAC;IAEO,YAAY,CAClB,OAAe,EACf,MAAc,EACd,UAAkB,EAClB,UAAkB,EAClB,KAAc;QAEd,MAAM,QAAQ,GAA4B,EAAE,UAAU,EAAE,UAAU,EAAE,CAAC;QACrE,IAAI,KAAK;YAAE,QAAQ,CAAC,KAAK,GAAG,KAAK,CAAC;QAElC,OAAO;YACL,EAAE,EAAE,MAAM,EAAE;YACZ,OAAO;YACP,MAAM;YACN,UAAU,EAAE,KAAK;YACjB,QAAQ;SACT,CAAC;IACJ,CAAC;CACF"}