community[minor]: added Browserbase loader (#20478)

docs/docs/integrations/document_loaders/browserbase.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Browserbase\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\n",
+    "\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):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "% pip install browserbase"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loading documents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can load webpages into LangChain using `BrowserbaseLoader`. Optionally, you can set `text_content` parameter to convert the pages to text-only representation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import BrowserbaseLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = BrowserbaseLoader(\n",
+    "    urls=[\n",
+    "        \"https://example.com\",\n",
+    "    ],\n",
+    "    # Text mode\n",
+    "    text_content=False,\n",
+    ")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "print(docs[0].page_content[:61])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loading images\n",
+    "\n",
+    "You can also load screenshots of webpages (as bytes) for multi-modal models.\n",
+    "\n",
+    "Full example using GPT-4V:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from browserbase import Browserbase\n",
+    "from browserbase.helpers.gpt4 import GPT4VImage, GPT4VImageDetail\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "chat = ChatOpenAI(model=\"gpt-4-vision-preview\", max_tokens=256)\n",
+    "browser = Browserbase()\n",
+    "\n",
+    "screenshot = browser.screenshot(\"https://browserbase.com\")\n",
+    "\n",
+    "result = chat.invoke(\n",
+    "    [\n",
+    "        HumanMessage(\n",
+    "            content=[\n",
+    "                {\"type\": \"text\", \"text\": \"What color is the logo?\"},\n",
+    "                GPT4VImage(screenshot, GPT4VImageDetail.auto),\n",
+    "            ]\n",
+    "        )\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "print(result.content)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/providers/browserbase.mdx

@@ -0,0 +1,28 @@
+# Browserbase
+
+>[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_API_KEY`).
+- Install the [Browserbase SDK](http://github.com/browserbase/python-sdk):
+
+```python
+pip install browserbase
+```
+
+## Document loader
+
+See a [usage example](/docs/integrations/document_loaders/browserbase).
+
+```python
+from langchain_community.document_loaders import BrowserbaseLoader
+```
+
+## Multi-Modal
+
+See a [usage example](/docs/integrations/document_loaders/browserbase).
+
+```python
+from browserbase.helpers.gpt4 import GPT4VImage, GPT4VImageDetail
+```

libs/community/langchain_community/document_loaders/__init__.py

@@ -95,6 +95,9 @@ if TYPE_CHECKING:
     from langchain_community.document_loaders.brave_search import (
         BraveSearchLoader,  # noqa: F401
     )
+    from langchain_community.document_loaders.browserbase import (
+        BrowserbaseLoader,  # noqa: F401
+    )
     from langchain_community.document_loaders.browserless import (
         BrowserlessLoader,  # noqa: F401
     )
@@ -541,6 +544,7 @@ __all__ = [
     "BlobLoader",
     "BlockchainDocumentLoader",
     "BraveSearchLoader",
+    "BrowserbaseLoader",
     "BrowserlessLoader",
     "CSVLoader",
     "CassandraLoader",
@@ -727,6 +731,7 @@ _module_lookup = {
     "BlobLoader": "langchain_community.document_loaders.blob_loaders",
     "BlockchainDocumentLoader": "langchain_community.document_loaders.blockchain",
     "BraveSearchLoader": "langchain_community.document_loaders.brave_search",
+    "BrowserbaseLoader": "langchain_community.document_loaders.browserbase",
     "BrowserlessLoader": "langchain_community.document_loaders.browserless",
     "CSVLoader": "langchain_community.document_loaders.csv_loader",
     "CassandraLoader": "langchain_community.document_loaders.cassandra",

libs/community/langchain_community/document_loaders/browserbase.py

@@ -0,0 +1,47 @@
+from typing import Iterator, List, Optional, Tuple, Union
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.base import BaseLoader
+
+
+class BrowserbaseLoader(BaseLoader):
+    """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,
+        urls: Union[List[str], Tuple[str, ...]],
+        *,
+        api_key: Optional[str] = None,
+        text_content: bool = False,
+    ):
+        self.urls = urls
+        self.text_content = text_content
+
+        try:
+            from browserbase import Browserbase
+        except ImportError:
+            raise ImportError(
+                "You must run "
+                "`pip install --upgrade "
+                "browserbase` "
+                "to use the Browserbase loader."
+            )
+
+        self.browserbase = Browserbase(api_key=api_key)
+
+    def lazy_load(self) -> Iterator[Document]:
+        """Load pages from URLs"""
+        pages = self.browserbase.load_urls(self.urls, self.text_content)
+
+        for i, page in enumerate(pages):
+            yield Document(
+                page_content=page,
+                metadata={
+                    "url": self.urls[i],
+                },
+            )

libs/community/tests/unit_tests/document_loaders/test_imports.py

@@ -38,6 +38,7 @@ EXPECTED_ALL = [
     "BlobLoader",
     "BlockchainDocumentLoader",
     "BraveSearchLoader",
+    "BrowserbaseLoader",
     "BrowserlessLoader",
     "CassandraLoader",
     "CSVLoader",