From c67804f0c610691953ed751f04c2221da12bcf2c Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Tue, 16 Apr 2024 19:41:00 +0000
Subject: [PATCH 1/8] feat: Browserbase Web Reader

---
 .../data_connectors/WebPageDemo.ipynb         | 52 +++++++++++++++++++
 .../llama_index/readers/web/__init__.py       |  2 +
 .../readers/web/browserbase_web/BUILD         |  5 ++
 .../readers/web/browserbase_web/README.md     | 45 ++++++++++++++++
 .../readers/web/browserbase_web/__init__.py   |  0
 .../readers/web/browserbase_web/base.py       | 48 +++++++++++++++++
 .../web/browserbase_web/requirements.txt      |  1 +
 7 files changed, 153 insertions(+)
 create mode 100644 llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/BUILD
 create mode 100644 llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
 create mode 100644 llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/__init__.py
 create mode 100644 llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
 create mode 100644 llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/requirements.txt

diff --git a/docs/docs/examples/data_connectors/WebPageDemo.ipynb b/docs/docs/examples/data_connectors/WebPageDemo.ipynb
index a2c221bdaceb2..f631afe73c255 100644
--- a/docs/docs/examples/data_connectors/WebPageDemo.ipynb
+++ b/docs/docs/examples/data_connectors/WebPageDemo.ipynb
@@ -130,6 +130,58 @@
     "display(Markdown(f\"<b>{response}</b>\"))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "005d14cd",
+   "metadata": {},
+   "source": [
+    "# Using Browserbase Reader 🅱️\n",
+    "\n",
+    "[Browserbase](https://browserbase.com) is a serverless platform for running headless browsers, it offers advanced debugging, session recordings, stealth mode, integrated proxies and captcha solving.\n",
+    "\n",
+    "## Installation and Setup\n",
+    "\n",
+    "- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_KEY`).\n",
+    "- Install the [Browserbase SDK](http://github.com/browserbase/python-sdk):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c74e6425",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "% pip install browserbase"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c23d02bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.readers.web import BrowserbaseWebReader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e71d347",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reader = BrowserbaseWebReader()\n",
+    "docs = reader.load_data(\n",
+    "    urls=[\n",
+    "        \"https://example.com\",\n",
+    "    ],\n",
+    "    # Text mode\n",
+    "    text_content=False\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "15f46387",
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/__init__.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/__init__.py
index 3d23feffdb6b4..87cbcb5898c87 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/__init__.py
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/__init__.py
@@ -5,6 +5,7 @@
 from llama_index.readers.web.beautiful_soup_web.base import (
     BeautifulSoupWebReader,
 )
+from llama_index.readers.web.browserbase.base import BrowserbaseWebReader
 from llama_index.readers.web.firecrawl_web.base import FireCrawlWebReader
 from llama_index.readers.web.knowledge_base.base import (
     KnowledgeBaseWebReader,
@@ -42,6 +43,7 @@
 __all__ = [
     "AsyncWebPageReader",
     "BeautifulSoupWebReader",
+    "BrowserbaseWebReader",
     "FireCrawlWebReader",
     "KnowledgeBaseWebReader",
     "MainContentExtractorReader",
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/BUILD b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/BUILD
new file mode 100644
index 0000000000000..8f515a7fcd9f5
--- /dev/null
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/BUILD
@@ -0,0 +1,5 @@
+python_sources()
+
+python_requirements(
+    name="reqs",
+)
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
new file mode 100644
index 0000000000000..4fae9f7be623d
--- /dev/null
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
@@ -0,0 +1,45 @@
+# Browserbase Web Reader
+
+[Browserbase](https://browserbase.com) is a serverless platform for running headless browsers, it offers advanced debugging, session recordings, stealth mode, integrated proxies and captcha solving.
+
+## Installation and Setup
+
+- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_KEY`).
+- Install the [Browserbase SDK](http://github.com/browserbase/python-sdk):
+
+```python
+pip install browserbase
+```
+
+### Loading documents
+
+You can load webpages into LangChain using `BrowserbaseWebReader`. Optionally, you can set `text_content` parameter to convert the pages to text-only representation.
+
+```python
+from llama_index.readers.web import BrowserbaseWebReader
+
+
+reader = BrowserbaseWebReader()
+docs = reader.load_data(
+    urls=[
+        "https://example.com",
+    ],
+    # Text mode
+    text_content=False
+)
+```
+
+### Loading images
+
+You can also load screenshots of webpages (as bytes) for multi-modal models.
+
+```python
+from browserbase import Browserbase
+from base64 import b64encode
+
+browser = Browserbase()
+screenshot = browser.screenshot("https://browserbase.com")
+
+# Optional. Convert to base64
+img_encoded = b64encode(screenshot).decode()
+```
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/__init__.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/__init__.py
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
new file mode 100644
index 0000000000000..b007510545c79
--- /dev/null
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
@@ -0,0 +1,48 @@
+import os
+import logging
+from typing import List
+from llama_index.core.readers.base import BaseReader
+from llama_index.core.schema import Document
+
+
+logger = logging.getLogger(__name__)
+
+
+class BrowserbaseWebReader(BaseReader):
+    """Browserbase Web Reader"""
+
+    def __init__(
+        self,
+        api_key: str = os.environ["BROWSERBASE_KEY"],
+    ) -> None:
+        try:
+            from browserbase import Browserbase
+        except ImportError:
+            raise ImportError(
+                "`browserbase` package not found, please run `pip install browserbase`"
+            )
+
+        self.browserbase = Browserbase(api_key=api_key)
+
+    def load_data(self, urls: List[str], text_content: bool = False) -> List[Document]:
+        """Load pages using Browserbase Web Reader"""
+
+        pages = self.browserbase.load_urls(urls, text_content)
+
+        documents = []
+        for i, page in enumerate(pages):
+            documents.append(
+                Document(
+                    text=page,
+                    metadata={
+                        "url": urls[i],
+                    },
+                )
+            )
+
+        return documents
+
+
+if __name__ == "__main__":
+    reader = BrowserbaseWebReader()
+    logger.info(reader.load_data(urls=["https://example.com"]))
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/requirements.txt b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/requirements.txt
new file mode 100644
index 0000000000000..529e0a3ed6e8b
--- /dev/null
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/requirements.txt
@@ -0,0 +1 @@
+browserbase

From 94457dec62ac482b656bddc472cf45ab98e557d2 Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Tue, 16 Apr 2024 19:55:12 +0000
Subject: [PATCH 2/8] updated browserbase docs

---
 .../llama_index/readers/web/browserbase_web/README.md           | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
index 4fae9f7be623d..e96a4be00e8dd 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
@@ -11,6 +11,8 @@
 pip install browserbase
 ```
 
+## Usage
+
 ### Loading documents
 
 You can load webpages into LangChain using `BrowserbaseWebReader`. Optionally, you can set `text_content` parameter to convert the pages to text-only representation.

From 82f5aa7bf2a225ba271652fd131854f8bbde5268 Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Wed, 17 Apr 2024 13:30:26 +0000
Subject: [PATCH 3/8] updated browserbase readme

---
 .../llama_index/readers/web/browserbase_web/README.md       | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
index e96a4be00e8dd..5d6134b8cd4d5 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
@@ -7,7 +7,7 @@
 - Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_KEY`).
 - Install the [Browserbase SDK](http://github.com/browserbase/python-sdk):
 
-```python
+```
 pip install browserbase
 ```
 
@@ -15,7 +15,7 @@ pip install browserbase
 
 ### Loading documents
 
-You can load webpages into LangChain using `BrowserbaseWebReader`. Optionally, you can set `text_content` parameter to convert the pages to text-only representation.
+You can load webpages into LlamaIndex using `BrowserbaseWebReader`. Optionally, you can set `text_content` parameter to convert the pages to text-only representation.
 
 ```python
 from llama_index.readers.web import BrowserbaseWebReader
@@ -27,7 +27,7 @@ docs = reader.load_data(
         "https://example.com",
     ],
     # Text mode
-    text_content=False
+    text_content=False,
 )
 ```
 

From 61439c24fe2723bfe848be16d50ec2f7115edec6 Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Thu, 18 Apr 2024 14:29:44 +0000
Subject: [PATCH 4/8] added lazy_load_data to browserbase web reader

---
 .../data_connectors/WebPageDemo.ipynb         |  2 +-
 .../readers/web/browserbase_web/base.py       | 22 +++++++------------
 2 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/docs/docs/examples/data_connectors/WebPageDemo.ipynb b/docs/docs/examples/data_connectors/WebPageDemo.ipynb
index f631afe73c255..22119fd684a95 100644
--- a/docs/docs/examples/data_connectors/WebPageDemo.ipynb
+++ b/docs/docs/examples/data_connectors/WebPageDemo.ipynb
@@ -178,7 +178,7 @@
     "        \"https://example.com\",\n",
     "    ],\n",
     "    # Text mode\n",
-    "    text_content=False\n",
+    "    text_content=False,\n",
     ")"
    ]
   },
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
index b007510545c79..463b3c3b9a876 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
@@ -1,6 +1,6 @@
 import os
 import logging
-from typing import List
+from typing import Iterator, List
 from llama_index.core.readers.base import BaseReader
 from llama_index.core.schema import Document
 
@@ -24,25 +24,19 @@ def __init__(
 
         self.browserbase = Browserbase(api_key=api_key)
 
-    def load_data(self, urls: List[str], text_content: bool = False) -> List[Document]:
+    def lazy_load_data(self, urls: List[str], text_content: bool = False) -> Iterator[Document]:
         """Load pages using Browserbase Web Reader"""
-
         pages = self.browserbase.load_urls(urls, text_content)
 
-        documents = []
         for i, page in enumerate(pages):
-            documents.append(
-                Document(
-                    text=page,
-                    metadata={
-                        "url": urls[i],
-                    },
-                )
+            yield Document(
+                text=page,
+                metadata={
+                    "url": urls[i],
+                },
             )
 
-        return documents
-
 
 if __name__ == "__main__":
     reader = BrowserbaseWebReader()
-    logger.info(reader.load_data(urls=["https://example.com"]))
+    logger.warning(reader.load_data(urls=["https://example.com"]))

From 0a4d8cfcec944d0d343139645a2b6af7b5739a0f Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Thu, 18 Apr 2024 14:30:18 +0000
Subject: [PATCH 5/8] browserbase logger fix

---
 .../llama_index/readers/web/browserbase_web/base.py             | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
index 463b3c3b9a876..088f5cecac25a 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
@@ -39,4 +39,4 @@ def lazy_load_data(self, urls: List[str], text_content: bool = False) -> Iterato
 
 if __name__ == "__main__":
     reader = BrowserbaseWebReader()
-    logger.warning(reader.load_data(urls=["https://example.com"]))
+    logger.info(reader.load_data(urls=["https://example.com"]))

From d718034f4dbab7edc6b81313fa19ca9615d336a8 Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Fri, 19 Apr 2024 11:13:06 +0000
Subject: [PATCH 6/8] updated browserbase integration

---
 .../examples/data_connectors/WebPageDemo.ipynb   |  2 +-
 .../readers/web/browserbase_web/README.md        |  2 +-
 .../readers/web/browserbase_web/base.py          | 16 ++++++++++------
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/docs/docs/examples/data_connectors/WebPageDemo.ipynb b/docs/docs/examples/data_connectors/WebPageDemo.ipynb
index 22119fd684a95..0b1f036317aa2 100644
--- a/docs/docs/examples/data_connectors/WebPageDemo.ipynb
+++ b/docs/docs/examples/data_connectors/WebPageDemo.ipynb
@@ -141,7 +141,7 @@
     "\n",
     "## Installation and Setup\n",
     "\n",
-    "- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_KEY`).\n",
+    "- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_API_KEY`).\n",
     "- Install the [Browserbase SDK](http://github.com/browserbase/python-sdk):"
    ]
   },
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
index 5d6134b8cd4d5..3985ccb9bad2e 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/README.md
@@ -4,7 +4,7 @@
 
 ## Installation and Setup
 
-- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_KEY`).
+- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_API_KEY`).
 - Install the [Browserbase SDK](http://github.com/browserbase/python-sdk):
 
 ```
diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
index 088f5cecac25a..f6436389a8db9 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
@@ -1,6 +1,6 @@
 import os
 import logging
-from typing import Iterator, List
+from typing import Optional, Iterator, Sequence
 from llama_index.core.readers.base import BaseReader
 from llama_index.core.schema import Document
 
@@ -9,11 +9,14 @@
 
 
 class BrowserbaseWebReader(BaseReader):
-    """Browserbase Web Reader"""
+    """Load pre-rendered web pages using a headless browser hosted on Browserbase.
+     Depends on `browserbase` package.
+     Get your API key from https://browserbase.com
+     """
 
     def __init__(
         self,
-        api_key: str = os.environ["BROWSERBASE_KEY"],
+        api_key: Optional[str] = None,
     ) -> None:
         try:
             from browserbase import Browserbase
@@ -22,10 +25,11 @@ def __init__(
                 "`browserbase` package not found, please run `pip install browserbase`"
             )
 
+        api_key = api_key or os.environ["BROWSERBASE_API_KEY"]
         self.browserbase = Browserbase(api_key=api_key)
 
-    def lazy_load_data(self, urls: List[str], text_content: bool = False) -> Iterator[Document]:
-        """Load pages using Browserbase Web Reader"""
+    def lazy_load_data(self, urls: Sequence[str], text_content: bool = False) -> Iterator[Document]:
+        """Load pages from URLs"""
         pages = self.browserbase.load_urls(urls, text_content)
 
         for i, page in enumerate(pages):
@@ -39,4 +43,4 @@ def lazy_load_data(self, urls: List[str], text_content: bool = False) -> Iterato
 
 if __name__ == "__main__":
     reader = BrowserbaseWebReader()
-    logger.info(reader.load_data(urls=["https://example.com"]))
+    logger.warn(reader.load_data(urls=["https://example.com"]))

From a5b6ccbcc9bf45f5b5a59a4f1b8dec2e0732a4e4 Mon Sep 17 00:00:00 2001
From: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Date: Fri, 19 Apr 2024 11:38:29 +0000
Subject: [PATCH 7/8] removed redundant line

---
 .../llama_index/readers/web/browserbase_web/base.py            | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
index f6436389a8db9..20087ea196eb0 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
@@ -25,7 +25,6 @@ def __init__(
                 "`browserbase` package not found, please run `pip install browserbase`"
             )
 
-        api_key = api_key or os.environ["BROWSERBASE_API_KEY"]
         self.browserbase = Browserbase(api_key=api_key)
 
     def lazy_load_data(self, urls: Sequence[str], text_content: bool = False) -> Iterator[Document]:
@@ -43,4 +42,4 @@ def lazy_load_data(self, urls: Sequence[str], text_content: bool = False) -> Ite
 
 if __name__ == "__main__":
     reader = BrowserbaseWebReader()
-    logger.warn(reader.load_data(urls=["https://example.com"]))
+    logger.info(reader.load_data(urls=["https://example.com"]))

From 2f6fb674d6a00ead88115fb1e4893a7c551df738 Mon Sep 17 00:00:00 2001
From: Logan Markewich <logan.markewich@live.com>
Date: Wed, 1 May 2024 21:35:13 -0600
Subject: [PATCH 8/8] linting

---
 .../readers/web/browserbase_web/base.py         | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
index 20087ea196eb0..63ad0804730e2 100644
--- a/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
+++ b/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/browserbase_web/base.py
@@ -1,4 +1,3 @@
-import os
 import logging
 from typing import Optional, Iterator, Sequence
 from llama_index.core.readers.base import BaseReader
@@ -9,10 +8,12 @@
 
 
 class BrowserbaseWebReader(BaseReader):
-    """Load pre-rendered web pages using a headless browser hosted on Browserbase.
-     Depends on `browserbase` package.
-     Get your API key from https://browserbase.com
-     """
+    """BrowserbaseWebReader.
+
+    Load pre-rendered web pages using a headless browser hosted on Browserbase.
+    Depends on `browserbase` package.
+    Get your API key from https://browserbase.com
+    """
 
     def __init__(
         self,
@@ -27,8 +28,10 @@ def __init__(
 
         self.browserbase = Browserbase(api_key=api_key)
 
-    def lazy_load_data(self, urls: Sequence[str], text_content: bool = False) -> Iterator[Document]:
-        """Load pages from URLs"""
+    def lazy_load_data(
+        self, urls: Sequence[str], text_content: bool = False
+    ) -> Iterator[Document]:
+        """Load pages from URLs."""
         pages = self.browserbase.load_urls(urls, text_content)
 
         for i, page in enumerate(pages):