better-web-search-mcp 0.5.1 → 0.5.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -38,6 +38,25 @@ export declare const TARGET_PASSAGE_CHARS = 500;
38
38
  * is windowed on sentence boundaries.
39
39
  */
40
40
  export declare const MAX_PASSAGE_CHARS = 1200;
41
+ /**
42
+ * Uppercase acronyms appearing in a query, e.g. "TLS" from "What does TLS
43
+ * stand for?".
44
+ */
45
+ export declare function findAcronyms(query: string): string[];
46
+ /**
47
+ * Whether `text` contains a phrase whose initials spell `acronym`.
48
+ *
49
+ * "Transport Layer Security" expands TLS; "Atomicity, Consistency, Isolation,
50
+ * Durability" expands ACID. Separators allow the punctuation these lists are
51
+ * usually written with, and a short connector word may sit between initials
52
+ * so "Cross-Origin Resource Sharing" and similar still match.
53
+ *
54
+ * This exists because the expansion is exactly the text a lexical scorer
55
+ * cannot find: the sentence that answers "what does TLS stand for" frequently
56
+ * never repeats the letters TLS, so it shares no term with the query and is
57
+ * dropped before ranking.
58
+ */
59
+ export declare function expandsAcronym(text: string, acronym: string): boolean;
41
60
  /** Lowercase alphanumeric tokens, stop words removed. */
42
61
  export declare function tokenize(text: string): string[];
43
62
  /**
@@ -1 +1 @@
1
- {"version":3,"file":"passages.d.ts","sourceRoot":"","sources":["../../src/ranking/passages.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,+CAA+C;AAC/C,MAAM,WAAW,OAAO;IACtB,iCAAiC;IACjC,IAAI,EAAE,MAAM,CAAC;IACb,uEAAuE;IACvE,KAAK,EAAE,MAAM,CAAC;IACd,qEAAqE;IACrE,GAAG,EAAE,MAAM,CAAC;IACZ,6DAA6D;IAC7D,KAAK,EAAE,MAAM,CAAC;CACf;AAMD,2EAA2E;AAC3E,eAAO,MAAM,oBAAoB,MAAM,CAAC;AAExC;;;;;;;;GAQG;AACH,eAAO,MAAM,iBAAiB,OAAQ,CAAC;AAUvC,yDAAyD;AACzD,wBAAgB,QAAQ,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAG/C;AAED;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,EAAE,CAsFxD;AAED;;;;;;GAMG;AACH,wBAAgB,YAAY,CAC1B,QAAQ,EAAE,SAAS,OAAO,EAAE,EAC5B,KAAK,EAAE,MAAM,GACZ,OAAO,EAAE,CAqDX;AAED;;;;;;GAMG;AACH,wBAAgB,cAAc,CAC5B,OAAO,EAAE,MAAM,EACf,KAAK,EAAE,MAAM,EACb,KAAK,SAAI,GACR,OAAO,EAAE,CAEX"}
1
+ {"version":3,"file":"passages.d.ts","sourceRoot":"","sources":["../../src/ranking/passages.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,+CAA+C;AAC/C,MAAM,WAAW,OAAO;IACtB,iCAAiC;IACjC,IAAI,EAAE,MAAM,CAAC;IACb,uEAAuE;IACvE,KAAK,EAAE,MAAM,CAAC;IACd,qEAAqE;IACrE,GAAG,EAAE,MAAM,CAAC;IACZ,6DAA6D;IAC7D,KAAK,EAAE,MAAM,CAAC;CACf;AAMD,2EAA2E;AAC3E,eAAO,MAAM,oBAAoB,MAAM,CAAC;AAExC;;;;;;;;GAQG;AACH,eAAO,MAAM,iBAAiB,OAAQ,CAAC;AAgCvC;;;GAGG;AACH,wBAAgB,YAAY,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,EAAE,CAMpD;AAED;;;;;;;;;;;;GAYG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,OAAO,CA2BrE;AAED,yDAAyD;AACzD,wBAAgB,QAAQ,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAG/C;AAED;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,EAAE,CAsFxD;AAED;;;;;;GAMG;AACH,wBAAgB,YAAY,CAC1B,QAAQ,EAAE,SAAS,OAAO,EAAE,EAC5B,KAAK,EAAE,MAAM,GACZ,OAAO,EAAE,CAyFX;AAED;;;;;;GAMG;AACH,wBAAgB,cAAc,CAC5B,OAAO,EAAE,MAAM,EACf,KAAK,EAAE,MAAM,EACb,KAAK,SAAI,GACR,OAAO,EAAE,CAEX"}
@@ -37,6 +37,70 @@ const STOP_WORDS = new Set([
37
37
  "that", "the", "this", "to", "was", "were", "what", "when", "where", "which",
38
38
  "who", "why", "will", "with", "you", "your",
39
39
  ]);
40
+ /**
41
+ * Shortest acronym worth expanding.
42
+ *
43
+ * Two-letter sequences match far too much ordinary prose to be a useful
44
+ * signal, so only three letters and up are considered.
45
+ */
46
+ const MIN_ACRONYM_LENGTH = 3;
47
+ /** Longest acronym worth expanding; beyond this the regex is noise. */
48
+ const MAX_ACRONYM_LENGTH = 8;
49
+ /**
50
+ * Weight of an acronym-expansion match, as a multiple of the mean query IDF.
51
+ *
52
+ * Expressed relative to the query's own IDF so it stays comparable to BM25
53
+ * scores instead of being a magic constant tuned to one corpus.
54
+ */
55
+ const ACRONYM_EXPANSION_WEIGHT = 1.5;
56
+ /** Words allowed between expansion initials without breaking the match. */
57
+ const CONNECTORS = "(?:of|and|the|for|in|to|a)";
58
+ /**
59
+ * Uppercase acronyms appearing in a query, e.g. "TLS" from "What does TLS
60
+ * stand for?".
61
+ */
62
+ export function findAcronyms(query) {
63
+ const found = query.match(new RegExp(`\\b[A-Z]{${MIN_ACRONYM_LENGTH},${MAX_ACRONYM_LENGTH}}\\b`, "g")) ?? [];
64
+ return [...new Set(found)];
65
+ }
66
+ /**
67
+ * Whether `text` contains a phrase whose initials spell `acronym`.
68
+ *
69
+ * "Transport Layer Security" expands TLS; "Atomicity, Consistency, Isolation,
70
+ * Durability" expands ACID. Separators allow the punctuation these lists are
71
+ * usually written with, and a short connector word may sit between initials
72
+ * so "Cross-Origin Resource Sharing" and similar still match.
73
+ *
74
+ * This exists because the expansion is exactly the text a lexical scorer
75
+ * cannot find: the sentence that answers "what does TLS stand for" frequently
76
+ * never repeats the letters TLS, so it shares no term with the query and is
77
+ * dropped before ranking.
78
+ */
79
+ export function expandsAcronym(text, acronym) {
80
+ const letters = [...acronym.toUpperCase()];
81
+ if (letters.length < MIN_ACRONYM_LENGTH) {
82
+ return false;
83
+ }
84
+ // Between initials: run out the current word, then optionally a separator
85
+ // and a connector. Letting the separator be optional is what allows a
86
+ // compound word to supply two initials, as "HyperText" does for HTML.
87
+ const gap = `[a-z]*(?:[\\s,;:/()-]+(?:${CONNECTORS}[\\s,;:/()-]+)?)?`;
88
+ const pattern = letters.join(gap) + "[a-z]*";
89
+ const regex = new RegExp(`\\b${pattern}\\b`, "gi");
90
+ // Every gap may be empty, so the pattern also matches the bare acronym —
91
+ // "TLS" itself satisfies T[a-z]*L[a-z]*S[a-z]*. Without this length floor
92
+ // any passage merely mentioning the acronym would count as expanding it,
93
+ // and the bonus would apply everywhere and rank nothing.
94
+ const minLength = acronym.length * 2;
95
+ for (const match of text.matchAll(regex)) {
96
+ const found = match[0];
97
+ if (found.length >= minLength &&
98
+ found.toUpperCase() !== acronym.toUpperCase()) {
99
+ return true;
100
+ }
101
+ }
102
+ return false;
103
+ }
40
104
  /** Lowercase alphanumeric tokens, stop words removed. */
41
105
  export function tokenize(text) {
42
106
  const tokens = text.toLowerCase().match(/[a-z0-9_]+/g) ?? [];
@@ -141,7 +205,10 @@ export function splitPassages(content) {
141
205
  */
142
206
  export function rankPassages(passages, query) {
143
207
  const queryTerms = tokenize(query);
144
- if (queryTerms.length === 0 || passages.length === 0) {
208
+ const acronyms = findAcronyms(query).filter((acronym) =>
209
+ // An acronym the query also spells out needs no special handling.
210
+ queryTerms.includes(acronym.toLowerCase()));
211
+ if ((queryTerms.length === 0 && acronyms.length === 0) || passages.length === 0) {
145
212
  return [];
146
213
  }
147
214
  const docs = passages.map((passage) => tokenize(passage.text));
@@ -157,6 +224,18 @@ export function rankPassages(passages, query) {
157
224
  }
158
225
  docFreq.set(term, count);
159
226
  }
227
+ // Sized from the query's own IDF so the bonus stays comparable to the BM25
228
+ // scores it is added to, rather than being a constant tuned to one corpus.
229
+ const idfOf = (term) => {
230
+ const n = docFreq.get(term) ?? 0;
231
+ return Math.log(1 + (docs.length - n + 0.5) / (n + 0.5));
232
+ };
233
+ const uniqueTerms = [...new Set(queryTerms)];
234
+ const meanIdf = uniqueTerms.length === 0
235
+ ? 1
236
+ : uniqueTerms.reduce((total, term) => total + idfOf(term), 0) /
237
+ uniqueTerms.length;
238
+ const expansionBonus = ACRONYM_EXPANSION_WEIGHT * meanIdf;
160
239
  const scored = [];
161
240
  passages.forEach((passage, index) => {
162
241
  const doc = docs[index] ?? [];
@@ -168,18 +247,30 @@ export function rankPassages(passages, query) {
168
247
  counts.set(token, (counts.get(token) ?? 0) + 1);
169
248
  }
170
249
  let score = 0;
171
- for (const term of new Set(queryTerms)) {
250
+ for (const term of uniqueTerms) {
172
251
  const freq = counts.get(term);
173
252
  if (freq === undefined) {
174
253
  continue;
175
254
  }
176
- const n = docFreq.get(term) ?? 0;
177
255
  // BM25 IDF, the +1 keeping it positive for terms in every passage.
178
- const idf = Math.log(1 + (docs.length - n + 0.5) / (n + 0.5));
256
+ const idf = idfOf(term);
179
257
  const norm = freq * (K1 + 1);
180
258
  const denom = freq + K1 * (1 - B + (B * doc.length) / (avgLength || 1));
181
259
  score += idf * (norm / denom);
182
260
  }
261
+ // A passage that spells an acronym out is usually the one answering "what
262
+ // does X stand for", but it says the expansion once while pages that merely
263
+ // use the acronym repeat it, so BM25 ranks the answer below the noise.
264
+ //
265
+ // The expansion must sit alongside the acronym itself. The loose gap that
266
+ // lets "HyperText Markup Language" expand HTML also matches ordinary prose
267
+ // — "The lazy squirrel" expands TLS — and requiring the acronym in the same
268
+ // passage removes those without weakening the real case, since the answer
269
+ // sentence almost always names the acronym it is defining.
270
+ if (acronyms.some((acronym) => counts.has(acronym.toLowerCase()) &&
271
+ expandsAcronym(passage.text, acronym))) {
272
+ score += expansionBonus;
273
+ }
183
274
  if (score > 0) {
184
275
  scored.push({ ...passage, score });
185
276
  }
@@ -1 +1 @@
1
- {"version":3,"file":"passages.js","sourceRoot":"","sources":["../../src/ranking/passages.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAcH,oDAAoD;AACpD,MAAM,EAAE,GAAG,GAAG,CAAC;AACf,MAAM,CAAC,GAAG,IAAI,CAAC;AAEf,2EAA2E;AAC3E,MAAM,CAAC,MAAM,oBAAoB,GAAG,GAAG,CAAC;AAExC;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAG,KAAK,CAAC;AAEvC,gEAAgE;AAChE,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC;IACzB,GAAG,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM;IACrE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,GAAG;IACzE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,OAAO,EAAE,OAAO;IAC5E,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM;CAC5C,CAAC,CAAC;AAEH,yDAAyD;AACzD,MAAM,UAAU,QAAQ,CAAC,IAAY;IACnC,MAAM,MAAM,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,aAAa,CAAC,IAAI,EAAE,CAAC;IAC7D,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;AAC9E,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,aAAa,CAAC,OAAe;IAC3C,MAAM,QAAQ,GAAc,EAAE,CAAC;IAC/B,MAAM,WAAW,GAAG,+BAA+B,CAAC;IAEpD,IAAI,WAAW,GAAG,CAAC,CAAC,CAAC;IACrB,IAAI,SAAS,GAAG,CAAC,CAAC,CAAC;IACnB,IAAI,MAAM,GAAG,EAAE,CAAC;IAEhB;;;;;;OAMG;IACH,MAAM,IAAI,GAAG,CAAC,GAAW,EAAE,KAAa,EAAQ,EAAE;QAChD,MAAM,OAAO,GAAG,GAAG,CAAC,MAAM,GAAG,GAAG,CAAC,SAAS,EAAE,CAAC,MAAM,CAAC;QACpD,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,CAAC;QACxB,IAAI,IAAI,KAAK,EAAE,EAAE,CAAC;YAChB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,KAAK,GAAG,OAAO,CAAC;QAC7B,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,GAAG,IAAI,CAAC,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAC;IAC1E,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG,CAAC,IAAY,EAAE,KAAa,EAAE,GAAW,EAAQ,EAAE;QAC9D,KAAK,GAAG,CAAC;QACT,IAAI,IAAI,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;YACvB,OAAO;QACT,CAAC;QACD,IAAI,IAAI,CAAC,MAAM,IAAI,iBAAiB,EAAE,CAAC;YACrC,IAAI,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;YAClB,OAAO;QACT,CAAC;QACD,oEAAoE;QACpE,wDAAwD;QACxD,IAAI,WAAW,GAAG,CAAC,CAAC;QACpB,OAAO,WAAW,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;YACjC,IAAI,SAAS,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,GAAG,iBAAiB,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC;YACvE,IAAI,SAAS,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;gBAC5B,iEAAiE;gBACjE,wCAAwC;gBACxC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC;gBACjD,MAAM,QAAQ,GAAG,KAAK,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC;gBACzC,MAAM,KAAK,GAAG,KAAK,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;gBACrC,MAAM,GAAG,GAAG,QAAQ,GAAG,iBAAiB,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC;gBACpE,IAAI,GAAG,GAAG,CAAC,EAAE,CAAC;oBACZ,SAAS,GAAG,WAAW,GAAG,GAAG,CAAC;gBAChC,CAAC;YACH,CAAC;YACD,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,EAAE,KAAK,GAAG,WAAW,CAAC,CAAC;YAC9D,WAAW,GAAG,SAAS,CAAC;QAC1B,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,GAAS,EAAE;QACvB,IAAI,CAAC,MAAM,EAAE,WAAW,EAAE,SAAS,CAAC,CAAC;QACrC,MAAM,GAAG,EAAE,CAAC;QACZ,WAAW,GAAG,CAAC,CAAC,CAAC;QACjB,SAAS,GAAG,CAAC,CAAC,CAAC;IACjB,CAAC,CAAC;IAEF,KAAK,MAAM,KAAK,IAAI,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC,EAAE,CAAC;QAClD,MAAM,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC3B,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,IAAI,CAAC,CAAC;QAC/B,IAAI,SAAS,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;YAC5B,SAAS;QACX,CAAC;QACD,IAAI,MAAM,KAAK,EAAE,EAAE,CAAC;YAClB,WAAW,GAAG,KAAK,CAAC;QACtB,CAAC;aAAM,IAAI,MAAM,CAAC,MAAM,GAAG,SAAS,CAAC,MAAM,GAAG,oBAAoB,EAAE,CAAC;YACnE,KAAK,EAAE,CAAC;YACR,WAAW,GAAG,KAAK,CAAC;QACtB,CAAC;QACD,SAAS,GAAG,KAAK,GAAG,SAAS,CAAC,MAAM,CAAC;QACrC,sEAAsE;QACtE,uEAAuE;QACvE,sEAAsE;QACtE,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC;QAC/C,IAAI,MAAM,CAAC,MAAM,IAAI,oBAAoB,EAAE,CAAC;YAC1C,KAAK,EAAE,CAAC;QACV,CAAC;IACH,CAAC;IACD,KAAK,EAAE,CAAC;IAER,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CAC1B,QAA4B,EAC5B,KAAa;IAEb,MAAM,UAAU,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;IACnC,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACrD,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,MAAM,IAAI,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC;IAC/D,MAAM,SAAS,GACb,IAAI,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,EAAE,CAAC,GAAG,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC;IAEtE,mEAAmE;IACnE,MAAM,OAAO,GAAG,IAAI,GAAG,EAAkB,CAAC;IAC1C,KAAK,MAAM,IAAI,IAAI,IAAI,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QACvC,IAAI,KAAK,GAAG,CAAC,CAAC;QACd,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,IAAI,GAAG,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;gBACvB,KAAK,IAAI,CAAC,CAAC;YACb,CAAC;QACH,CAAC;QACD,OAAO,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;IAC3B,CAAC;IAED,MAAM,MAAM,GAAc,EAAE,CAAC;IAC7B,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,KAAK,EAAE,EAAE;QAClC,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;QAC9B,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACrB,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;QACzC,KAAK,MAAM,KAAK,IAAI,GAAG,EAAE,CAAC;YACxB,MAAM,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QAClD,CAAC;QAED,IAAI,KAAK,GAAG,CAAC,CAAC;QACd,KAAK,MAAM,IAAI,IAAI,IAAI,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;YACvC,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YAC9B,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;gBACvB,SAAS;YACX,CAAC;YACD,MAAM,CAAC,GAAG,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YACjC,mEAAmE;YACnE,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC;YAC9D,MAAM,IAAI,GAAG,IAAI,GAAG,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;YAC7B,MAAM,KAAK,GAAG,IAAI,GAAG,EAAE,GAAG,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,SAAS,IAAI,CAAC,CAAC,CAAC,CAAC;YACxE,KAAK,IAAI,GAAG,GAAG,CAAC,IAAI,GAAG,KAAK,CAAC,CAAC;QAChC,CAAC;QAED,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;YACd,MAAM,CAAC,IAAI,CAAC,EAAE,GAAG,OAAO,EAAE,KAAK,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,OAAO,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC;AAClD,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,cAAc,CAC5B,OAAe,EACf,KAAa,EACb,KAAK,GAAG,CAAC;IAET,OAAO,YAAY,CAAC,aAAa,CAAC,OAAO,CAAC,EAAE,KAAK,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;AACrE,CAAC"}
1
+ {"version":3,"file":"passages.js","sourceRoot":"","sources":["../../src/ranking/passages.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAcH,oDAAoD;AACpD,MAAM,EAAE,GAAG,GAAG,CAAC;AACf,MAAM,CAAC,GAAG,IAAI,CAAC;AAEf,2EAA2E;AAC3E,MAAM,CAAC,MAAM,oBAAoB,GAAG,GAAG,CAAC;AAExC;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAG,KAAK,CAAC;AAEvC,gEAAgE;AAChE,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC;IACzB,GAAG,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM;IACrE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,GAAG;IACzE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,OAAO,EAAE,OAAO;IAC5E,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM;CAC5C,CAAC,CAAC;AAEH;;;;;GAKG;AACH,MAAM,kBAAkB,GAAG,CAAC,CAAC;AAE7B,uEAAuE;AACvE,MAAM,kBAAkB,GAAG,CAAC,CAAC;AAE7B;;;;;GAKG;AACH,MAAM,wBAAwB,GAAG,GAAG,CAAC;AAErC,2EAA2E;AAC3E,MAAM,UAAU,GAAG,4BAA4B,CAAC;AAEhD;;;GAGG;AACH,MAAM,UAAU,YAAY,CAAC,KAAa;IACxC,MAAM,KAAK,GACT,KAAK,CAAC,KAAK,CACT,IAAI,MAAM,CAAC,YAAY,kBAAkB,IAAI,kBAAkB,MAAM,EAAE,GAAG,CAAC,CAC5E,IAAI,EAAE,CAAC;IACV,OAAO,CAAC,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;AAC7B,CAAC;AAED;;;;;;;;;;;;GAYG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY,EAAE,OAAe;IAC1D,MAAM,OAAO,GAAG,CAAC,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC;IAC3C,IAAI,OAAO,CAAC,MAAM,GAAG,kBAAkB,EAAE,CAAC;QACxC,OAAO,KAAK,CAAC;IACf,CAAC;IACD,0EAA0E;IAC1E,sEAAsE;IACtE,sEAAsE;IACtE,MAAM,GAAG,GAAG,4BAA4B,UAAU,mBAAmB,CAAC;IACtE,MAAM,OAAO,GAAG,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,QAAQ,CAAC;IAC7C,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,MAAM,OAAO,KAAK,EAAE,IAAI,CAAC,CAAC;IAEnD,yEAAyE;IACzE,0EAA0E;IAC1E,yEAAyE;IACzE,yDAAyD;IACzD,MAAM,SAAS,GAAG,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC;IACrC,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;QACzC,MAAM,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACvB,IACE,KAAK,CAAC,MAAM,IAAI,SAAS;YACzB,KAAK,CAAC,WAAW,EAAE,KAAK,OAAO,CAAC,WAAW,EAAE,EAC7C,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,yDAAyD;AACzD,MAAM,UAAU,QAAQ,CAAC,IAAY;IACnC,MAAM,MAAM,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,aAAa,CAAC,IAAI,EAAE,CAAC;IAC7D,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;AAC9E,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,aAAa,CAAC,OAAe;IAC3C,MAAM,QAAQ,GAAc,EAAE,CAAC;IAC/B,MAAM,WAAW,GAAG,+BAA+B,CAAC;IAEpD,IAAI,WAAW,GAAG,CAAC,CAAC,CAAC;IACrB,IAAI,SAAS,GAAG,CAAC,CAAC,CAAC;IACnB,IAAI,MAAM,GAAG,EAAE,CAAC;IAEhB;;;;;;OAMG;IACH,MAAM,IAAI,GAAG,CAAC,GAAW,EAAE,KAAa,EAAQ,EAAE;QAChD,MAAM,OAAO,GAAG,GAAG,CAAC,MAAM,GAAG,GAAG,CAAC,SAAS,EAAE,CAAC,MAAM,CAAC;QACpD,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,CAAC;QACxB,IAAI,IAAI,KAAK,EAAE,EAAE,CAAC;YAChB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,KAAK,GAAG,OAAO,CAAC;QAC7B,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,GAAG,IAAI,CAAC,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAC;IAC1E,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG,CAAC,IAAY,EAAE,KAAa,EAAE,GAAW,EAAQ,EAAE;QAC9D,KAAK,GAAG,CAAC;QACT,IAAI,IAAI,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;YACvB,OAAO;QACT,CAAC;QACD,IAAI,IAAI,CAAC,MAAM,IAAI,iBAAiB,EAAE,CAAC;YACrC,IAAI,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;YAClB,OAAO;QACT,CAAC;QACD,oEAAoE;QACpE,wDAAwD;QACxD,IAAI,WAAW,GAAG,CAAC,CAAC;QACpB,OAAO,WAAW,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;YACjC,IAAI,SAAS,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,GAAG,iBAAiB,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC;YACvE,IAAI,SAAS,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;gBAC5B,iEAAiE;gBACjE,wCAAwC;gBACxC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC;gBACjD,MAAM,QAAQ,GAAG,KAAK,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC;gBACzC,MAAM,KAAK,GAAG,KAAK,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;gBACrC,MAAM,GAAG,GAAG,QAAQ,GAAG,iBAAiB,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC;gBACpE,IAAI,GAAG,GAAG,CAAC,EAAE,CAAC;oBACZ,SAAS,GAAG,WAAW,GAAG,GAAG,CAAC;gBAChC,CAAC;YACH,CAAC;YACD,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,EAAE,KAAK,GAAG,WAAW,CAAC,CAAC;YAC9D,WAAW,GAAG,SAAS,CAAC;QAC1B,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,GAAS,EAAE;QACvB,IAAI,CAAC,MAAM,EAAE,WAAW,EAAE,SAAS,CAAC,CAAC;QACrC,MAAM,GAAG,EAAE,CAAC;QACZ,WAAW,GAAG,CAAC,CAAC,CAAC;QACjB,SAAS,GAAG,CAAC,CAAC,CAAC;IACjB,CAAC,CAAC;IAEF,KAAK,MAAM,KAAK,IAAI,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC,EAAE,CAAC;QAClD,MAAM,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC3B,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,IAAI,CAAC,CAAC;QAC/B,IAAI,SAAS,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;YAC5B,SAAS;QACX,CAAC;QACD,IAAI,MAAM,KAAK,EAAE,EAAE,CAAC;YAClB,WAAW,GAAG,KAAK,CAAC;QACtB,CAAC;aAAM,IAAI,MAAM,CAAC,MAAM,GAAG,SAAS,CAAC,MAAM,GAAG,oBAAoB,EAAE,CAAC;YACnE,KAAK,EAAE,CAAC;YACR,WAAW,GAAG,KAAK,CAAC;QACtB,CAAC;QACD,SAAS,GAAG,KAAK,GAAG,SAAS,CAAC,MAAM,CAAC;QACrC,sEAAsE;QACtE,uEAAuE;QACvE,sEAAsE;QACtE,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC;QAC/C,IAAI,MAAM,CAAC,MAAM,IAAI,oBAAoB,EAAE,CAAC;YAC1C,KAAK,EAAE,CAAC;QACV,CAAC;IACH,CAAC;IACD,KAAK,EAAE,CAAC;IAER,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CAC1B,QAA4B,EAC5B,KAAa;IAEb,MAAM,UAAU,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;IACnC,MAAM,QAAQ,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE;IACtD,kEAAkE;IAClE,UAAU,CAAC,QAAQ,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,CAC3C,CAAC;IACF,IAAI,CAAC,UAAU,CAAC,MAAM,KAAK,CAAC,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,CAAC,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAChF,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,MAAM,IAAI,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC;IAC/D,MAAM,SAAS,GACb,IAAI,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,EAAE,CAAC,GAAG,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC;IAEtE,mEAAmE;IACnE,MAAM,OAAO,GAAG,IAAI,GAAG,EAAkB,CAAC;IAC1C,KAAK,MAAM,IAAI,IAAI,IAAI,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QACvC,IAAI,KAAK,GAAG,CAAC,CAAC;QACd,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,IAAI,GAAG,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;gBACvB,KAAK,IAAI,CAAC,CAAC;YACb,CAAC;QACH,CAAC;QACD,OAAO,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;IAC3B,CAAC;IAED,2EAA2E;IAC3E,2EAA2E;IAC3E,MAAM,KAAK,GAAG,CAAC,IAAY,EAAU,EAAE;QACrC,MAAM,CAAC,GAAG,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACjC,OAAO,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC;IAC3D,CAAC,CAAC;IACF,MAAM,WAAW,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC;IAC7C,MAAM,OAAO,GACX,WAAW,CAAC,MAAM,KAAK,CAAC;QACtB,CAAC,CAAC,CAAC;QACH,CAAC,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,KAAK,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YAC3D,WAAW,CAAC,MAAM,CAAC;IACzB,MAAM,cAAc,GAAG,wBAAwB,GAAG,OAAO,CAAC;IAE1D,MAAM,MAAM,GAAc,EAAE,CAAC;IAC7B,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,KAAK,EAAE,EAAE;QAClC,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;QAC9B,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACrB,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;QACzC,KAAK,MAAM,KAAK,IAAI,GAAG,EAAE,CAAC;YACxB,MAAM,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QAClD,CAAC;QAED,IAAI,KAAK,GAAG,CAAC,CAAC;QACd,KAAK,MAAM,IAAI,IAAI,WAAW,EAAE,CAAC;YAC/B,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YAC9B,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;gBACvB,SAAS;YACX,CAAC;YACD,mEAAmE;YACnE,MAAM,GAAG,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC;YACxB,MAAM,IAAI,GAAG,IAAI,GAAG,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;YAC7B,MAAM,KAAK,GAAG,IAAI,GAAG,EAAE,GAAG,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,SAAS,IAAI,CAAC,CAAC,CAAC,CAAC;YACxE,KAAK,IAAI,GAAG,GAAG,CAAC,IAAI,GAAG,KAAK,CAAC,CAAC;QAChC,CAAC;QAED,0EAA0E;QAC1E,4EAA4E;QAC5E,uEAAuE;QACvE,EAAE;QACF,0EAA0E;QAC1E,2EAA2E;QAC3E,4EAA4E;QAC5E,0EAA0E;QAC1E,2DAA2D;QAC3D,IACE,QAAQ,CAAC,IAAI,CACX,CAAC,OAAO,EAAE,EAAE,CACV,MAAM,CAAC,GAAG,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC;YACjC,cAAc,CAAC,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC,CACxC,EACD,CAAC;YACD,KAAK,IAAI,cAAc,CAAC;QAC1B,CAAC;QAED,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;YACd,MAAM,CAAC,IAAI,CAAC,EAAE,GAAG,OAAO,EAAE,KAAK,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,OAAO,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC;AAClD,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,cAAc,CAC5B,OAAe,EACf,KAAa,EACb,KAAK,GAAG,CAAC;IAET,OAAO,YAAY,CAAC,aAAa,CAAC,OAAO,CAAC,EAAE,KAAK,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;AACrE,CAAC"}
package/mcp.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "better-web-search-mcp",
3
- "version": "0.5.1",
3
+ "version": "0.5.2",
4
4
  "description": "BetterWebSearch MCP — keyless-first web research (DuckDuckGo) with optional Brave/Tavily and 3-tier extraction",
5
5
  "mcpServers": {
6
6
  "better-web-search-mcp": {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "better-web-search-mcp",
3
- "version": "0.5.1",
3
+ "version": "0.5.2",
4
4
  "description": "MCP server for genuinely better web research — keyless-first (DuckDuckGo), 3-tier extraction, deep research. Brave/Tavily optional.",
5
5
  "type": "module",
6
6
  "bin": {
@@ -55,6 +55,7 @@
55
55
  "check:publish": "npm pack --dry-run",
56
56
  "bench": "node benchmarks/run.mjs",
57
57
  "bench:quality": "node benchmarks/quality.mjs",
58
+ "bench:corpus": "node benchmarks/corpus.mjs",
58
59
  "docs:api": "typedoc --options typedoc.json && node scripts/typedoc-postprocess.mjs",
59
60
  "docs:changelog": "node scripts/sync-docs-changelog.mjs",
60
61
  "docs:build": "npm run docs:api && npm run docs:changelog && hugo --source site --gc --minify",