@absolutejs/rag 0.10.0 → 0.12.0

package/dist/index.js

@@ -1,5 +1,37 @@
 // @bun
+var __create = Object.create;
+var __getProtoOf = Object.getPrototypeOf;
 var __defProp = Object.defineProperty;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+function __accessProp(key) {
+  return this[key];
+}
+var __toESMCache_node;
+var __toESMCache_esm;
+var __toESM = (mod, isNodeMode, target) => {
+  var canCache = mod != null && typeof mod === "object";
+  if (canCache) {
+    var cache = isNodeMode ? __toESMCache_node ??= new WeakMap : __toESMCache_esm ??= new WeakMap;
+    var cached = cache.get(mod);
+    if (cached)
+      return cached;
+  }
+  target = mod != null ? __create(__getProtoOf(mod)) : {};
+  const to = isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target;
+  if (mod && typeof mod === "object" || typeof mod === "function") {
+    for (let key of __getOwnPropNames(mod))
+      if (!__hasOwnProp.call(to, key))
+        __defProp(to, key, {
+          get: __accessProp.bind(mod, key),
+          enumerable: true
+        });
+  }
+  if (canCache)
+    cache.set(mod, to);
+  return to;
+};
+var __commonJS = (cb, mod) => () => (mod || cb((mod = { exports: {} }).exports, mod), mod.exports);
 var __returnValue = (v) => v;
 function __exportSetter(name, newValue) {
   this[name] = __returnValue.bind(null, newValue);
@@ -13,6 +45,7 @@ var __export = (target, all) => {
       set: __exportSetter.bind(all, name)
     });
 };
+var __require = import.meta.require;
 
 // src/quality/quality.ts
 import { mkdir, readFile } from "fs/promises";
@@ -15251,6 +15284,9 @@ var inferFormatFromName = (value) => {
 };
 var inferFormatFromContentType = (contentType) => {
   const normalizedType = (contentType || "").toLowerCase();
+  if (normalizedType.includes("html")) {
+    return "html";
+  }
   if (normalizedType.includes("xml")) {
     return "xml";
   }
@@ -19963,7 +19999,7 @@ var loadRAGDocumentFromURL = async (input) => {
     contentType: input.contentType ?? response.headers.get("content-type") ?? undefined,
     data,
     extractorRegistry: input.extractorRegistry,
-    format: input.format ?? inferFormatFromUrl(url),
+    format: input.format ?? inferFormatFromContentType(input.contentType ?? response.headers.get("content-type")) ?? inferFormatFromUrl(url),
     metadata: input.metadata,
     name: basename(new URL(url).pathname),
     source: input.source ?? url,
@@ -20011,7 +20047,7 @@ var loadRAGDocumentsFromURLs = async (input) => {
       contentType: urlInput.contentType ?? response.headers.get("content-type") ?? undefined,
       data,
       extractorRegistry: urlInput.extractorRegistry ?? input.extractorRegistry,
-      format: urlInput.format ?? inferFormatFromUrl(url),
+      format: urlInput.format ?? inferFormatFromContentType(urlInput.contentType ?? response.headers.get("content-type")) ?? inferFormatFromUrl(url),
       metadata: urlInput.metadata,
       name: basename(new URL(url).pathname),
       source: urlInput.source ?? url,
@@ -36929,5 +36965,5 @@ export {
   xaiEmbeddings
 };
 
-//# debugId=2522635E4551C85B64756E2164756E21
+//# debugId=87B4523169D1586964756E2164756E21
 //# sourceMappingURL=index.js.map