Merge branch 'dev' into feate-webloader-support-proxy

backend/open_webui/retrieval/web/utils.py

@@ -3,7 +3,8 @@ import aiohttp
 import asyncio
 import urllib.parse
 import validators
-from typing import Union, Sequence, Iterator, Dict
+from typing import Any, AsyncIterator, Dict, Iterator, List, Sequence, Union
+
 
 from langchain_community.document_loaders import (
     WebBaseLoader,
@@ -109,6 +110,32 @@ class SafeWebBaseLoader(WebBaseLoader):
                         await asyncio.sleep(cooldown * backoff**i)
         raise ValueError("retry count exceeded")
 
+    def _unpack_fetch_results(
+        self, results: Any, urls: List[str], parser: Union[str, None] = None
+    ) -> List[Any]:
+        """Unpack fetch results into BeautifulSoup objects."""
+        from bs4 import BeautifulSoup
+
+        final_results = []
+        for i, result in enumerate(results):
+            url = urls[i]
+            if parser is None:
+                if url.endswith(".xml"):
+                    parser = "xml"
+                else:
+                    parser = self.default_parser
+                self._check_parser(parser)
+            final_results.append(BeautifulSoup(result, parser, **self.bs_kwargs))
+        return final_results
+
+    async def ascrape_all(
+        self, urls: List[str], parser: Union[str, None] = None
+    ) -> List[Any]:
+        """Async fetch all urls, then return soups for all results."""
+        results = await self.fetch_all(urls)
+        return self._unpack_fetch_results(results, urls, parser=parser)
+
+
     def lazy_load(self) -> Iterator[Document]:
         """Lazy load text from the url(s) in web_path with error handling."""
         for path in self.web_paths:
@@ -132,6 +159,26 @@ class SafeWebBaseLoader(WebBaseLoader):
                 # Log the error and continue with the next URL
                 log.error(f"Error loading {path}: {e}")
 
+    async def alazy_load(self) -> AsyncIterator[Document]:
+        """Async lazy load text from the url(s) in web_path."""
+        results = await self.ascrape_all(self.web_paths)
+        for path, soup in zip(self.web_paths, results):
+            text = soup.get_text(**self.bs_get_text_kwargs)
+            metadata = {"source": path}
+            if title := soup.find("title"):
+                metadata["title"] = title.get_text()
+            if description := soup.find("meta", attrs={"name": "description"}):
+                metadata["description"] = description.get(
+                    "content", "No description found."
+                )
+            if html := soup.find("html"):
+                metadata["language"] = html.get("lang", "No language found.")
+            yield Document(page_content=text, metadata=metadata)
+
+    async def aload(self) -> list[Document]:
+        """Load data into Document objects."""
+        return [document async for document in self.alazy_load()]
+
 
 def get_web_loader(
     urls: Union[str, Sequence[str]],