@elizaos/plugin-knowledge 1.5.13 → 1.5.14

package/dist/index.js

@@ -20,16 +20,16 @@ import {
   splitChunks
 } from "@elizaos/core";
 
-// node_modules/uuid/dist/esm/regex.js
+// node_modules/uuid/dist-node/regex.js
 var regex_default = /^(?:[0-9a-f]{8}-[0-9a-f]{4}-[1-8][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$/i;
 
-// node_modules/uuid/dist/esm/validate.js
+// node_modules/uuid/dist-node/validate.js
 function validate(uuid) {
   return typeof uuid === "string" && regex_default.test(uuid);
 }
 var validate_default = validate;
 
-// node_modules/uuid/dist/esm/parse.js
+// node_modules/uuid/dist-node/parse.js
 function parse(uuid) {
   if (!validate_default(uuid)) {
     throw TypeError("Invalid UUID");
@@ -39,7 +39,7 @@ function parse(uuid) {
 }
 var parse_default = parse;
 
-// node_modules/uuid/dist/esm/stringify.js
+// node_modules/uuid/dist-node/stringify.js
 var byteToHex = [];
 for (let i = 0; i < 256; ++i) {
   byteToHex.push((i + 256).toString(16).slice(1));
@@ -48,7 +48,7 @@ function unsafeStringify(arr, offset = 0) {
   return (byteToHex[arr[offset + 0]] + byteToHex[arr[offset + 1]] + byteToHex[arr[offset + 2]] + byteToHex[arr[offset + 3]] + "-" + byteToHex[arr[offset + 4]] + byteToHex[arr[offset + 5]] + "-" + byteToHex[arr[offset + 6]] + byteToHex[arr[offset + 7]] + "-" + byteToHex[arr[offset + 8]] + byteToHex[arr[offset + 9]] + "-" + byteToHex[arr[offset + 10]] + byteToHex[arr[offset + 11]] + byteToHex[arr[offset + 12]] + byteToHex[arr[offset + 13]] + byteToHex[arr[offset + 14]] + byteToHex[arr[offset + 15]]).toLowerCase();
 }
 
-// node_modules/uuid/dist/esm/rng.js
+// node_modules/uuid/dist-node/rng.js
 import { randomFillSync } from "crypto";
 var rnds8Pool = new Uint8Array(256);
 var poolPtr = rnds8Pool.length;
@@ -60,7 +60,7 @@ function rng() {
   return rnds8Pool.slice(poolPtr, poolPtr += 16);
 }
 
-// node_modules/uuid/dist/esm/v35.js
+// node_modules/uuid/dist-node/v35.js
 function stringToBytes(str) {
   str = unescape(encodeURIComponent(str));
   const bytes = new Uint8Array(str.length);
@@ -96,15 +96,12 @@ function v35(version, hash, value, namespace, buf, offset) {
   return unsafeStringify(bytes);
 }
 
-// node_modules/uuid/dist/esm/native.js
+// node_modules/uuid/dist-node/native.js
 import { randomUUID } from "crypto";
 var native_default = { randomUUID };
 
-// node_modules/uuid/dist/esm/v4.js
-function v4(options, buf, offset) {
-  if (native_default.randomUUID && !buf && !options) {
-    return native_default.randomUUID();
-  }
+// node_modules/uuid/dist-node/v4.js
+function _v4(options, buf, offset) {
   options = options || {};
   const rnds = options.random ?? options.rng?.() ?? rng();
   if (rnds.length < 16) {
@@ -124,9 +121,15 @@ function v4(options, buf, offset) {
   }
   return unsafeStringify(rnds);
 }
+function v4(options, buf, offset) {
+  if (native_default.randomUUID && !buf && !options) {
+    return native_default.randomUUID();
+  }
+  return _v4(options, buf, offset);
+}
 var v4_default = v4;
 
-// node_modules/uuid/dist/esm/sha1.js
+// node_modules/uuid/dist-node/sha1.js
 import { createHash } from "crypto";
 function sha1(bytes) {
   if (Array.isArray(bytes)) {
@@ -138,7 +141,7 @@ function sha1(bytes) {
 }
 var sha1_default = sha1;
 
-// node_modules/uuid/dist/esm/v5.js
+// node_modules/uuid/dist-node/v5.js
 function v5(value, namespace, buf, offset) {
   return v35(80, sha1_default, value, namespace, buf, offset);
 }
@@ -1083,7 +1086,7 @@ function logCacheMetrics(result) {
 import { Buffer as Buffer2 } from "buffer";
 import * as mammoth from "mammoth";
 import { logger as logger3 } from "@elizaos/core";
-import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
+import { extractText } from "unpdf";
 import { createHash as createHash2 } from "crypto";
 var PLAIN_TEXT_CONTENT_TYPES = [
   "application/typescript",
@@ -1162,32 +1165,24 @@ This document was indexed for search but cannot be displayed directly in the bro
 }
 async function convertPdfToTextFromBuffer(pdfBuffer, filename) {
   const docName = filename || "unnamed-document";
-  logger3.debug(`[PdfService] Starting conversion for ${docName}`);
+  logger3.debug(`[PdfService] Starting conversion for ${docName} using unpdf`);
   try {
-    const uint8Array = new Uint8Array(pdfBuffer);
-    const pdf = await getDocument({ data: uint8Array }).promise;
-    const numPages = pdf.numPages;
-    const textPages = [];
-    for (let pageNum = 1; pageNum <= numPages; pageNum++) {
-      logger3.debug(`[PdfService] Processing page ${pageNum}/${numPages}`);
-      const page = await pdf.getPage(pageNum);
-      const textContent = await page.getTextContent();
-      const lineMap = /* @__PURE__ */ new Map();
-      textContent.items.filter(isTextItem).forEach((item) => {
-        const yPos = Math.round(item.transform[5]);
-        if (!lineMap.has(yPos)) {
-          lineMap.set(yPos, []);
-        }
-        lineMap.get(yPos).push(item);
-      });
-      const sortedLines = Array.from(lineMap.entries()).sort((a, b) => b[0] - a[0]).map(
-        ([_, items]) => items.sort((a, b) => a.transform[4] - b.transform[4]).map((item) => item.str).join(" ")
-      );
-      textPages.push(sortedLines.join("\n"));
+    const uint8Array = new Uint8Array(
+      pdfBuffer.buffer.slice(pdfBuffer.byteOffset, pdfBuffer.byteOffset + pdfBuffer.byteLength)
+    );
+    const result = await extractText(uint8Array, {
+      mergePages: true
+      // Merge all pages into a single string
+    });
+    if (!result.text || result.text.trim().length === 0) {
+      logger3.warn(`[PdfService] No text extracted from ${docName}`);
+      return "";
     }
-    const fullText = textPages.join("\n\n").replace(/\s+/g, " ").trim();
-    logger3.debug(`[PdfService] Conversion complete for ${docName}, length: ${fullText.length}`);
-    return fullText;
+    const cleanedText = result.text.split("\n").map((line) => line.trim()).filter((line) => line.length > 0).join("\n").replace(/\n{3,}/g, "\n\n");
+    logger3.debug(
+      `[PdfService] Conversion complete for ${docName}, ${result.totalPages} pages, length: ${cleanedText.length}`
+    );
+    return cleanedText;
   } catch (error) {
     logger3.error(`[PdfService] Error converting PDF ${docName}:`, error.message);
     throw new Error(`Failed to convert PDF to text: ${error.message}`);
@@ -1336,9 +1331,6 @@ function isBinaryContentType(contentType, filename) {
   ];
   return binaryExtensions.includes(fileExt);
 }
-function isTextItem(item) {
-  return "str" in item;
-}
 function normalizeS3Url(url) {
   try {
     const urlObj = new URL(url);