[docs/community]: langchain docs + browserbaseloader fix (#30973)

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
  - Example: "community: add foobar LLM"

community: fix browserbase integration
docs: update docs

- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Updated BrowserbaseLoader to use the new python sdk.
    - **Issue:** update browserbase integration with langchain
    - **Dependencies:** n/a
    - **Twitter handle:** @kylejeong21

- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.

- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

libs/community/langchain_community/document_loaders/browserbase.py

@@ -1,4 +1,4 @@
-from typing import Iterator, Optional, Sequence
+from typing import Any, Dict, Iterator, Optional, Sequence
 
 from langchain_core.documents import Document
 
@@ -8,7 +8,7 @@ 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.
+    Depends on `browserbase` and `playwright` packages.
     Get your API key from https://browserbase.com
     """
 
@@ -24,6 +24,7 @@ class BrowserbaseLoader(BaseLoader):
         self.urls = urls
         self.text_content = text_content
         self.session_id = session_id
+        self.project_id = project_id
         self.proxy = proxy
 
         try:
@@ -32,22 +33,57 @@ class BrowserbaseLoader(BaseLoader):
             raise ImportError(
                 "You must run "
                 "`pip install --upgrade "
-                "browserbase` "
+                "browserbase playwright` "
                 "to use the Browserbase loader."
             )
 
-        self.browserbase = Browserbase(api_key, project_id)
+        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, self.session_id, self.proxy
-        )
-
-        for i, page in enumerate(pages):
-            yield Document(
-                page_content=page,
-                metadata={
-                    "url": self.urls[i],
-                },
+        try:
+            from playwright.sync_api import sync_playwright
+        except ImportError:
+            raise ImportError(
+                "playwright is required for BrowserbaseLoader. "
+                "Please run `pip install --upgrade playwright`."
             )
+
+        for url in self.urls:
+            with sync_playwright() as playwright:
+                # Create or use existing session
+                if self.session_id:
+                    session = self.browserbase.sessions.retrieve(id=self.session_id)
+                else:
+                    if not self.project_id:
+                        raise ValueError("project_id is required to create a session")
+                    session_params: Dict[str, Any] = {"project_id": self.project_id}
+                    if self.proxy is not None:
+                        session_params["proxy"] = bool(self.proxy)
+                    session = self.browserbase.sessions.create(**session_params)
+
+                # Connect to the remote session
+                browser = playwright.chromium.connect_over_cdp(session.connect_url)
+                context = browser.contexts[0]
+                page = context.pages[0]
+
+                # Navigate to URL and get content
+                page.goto(url)
+                # Get content based on the text_content flag
+                if self.text_content:
+                    page_text = page.inner_text("body")
+                    content = str(page_text)
+                else:
+                    page_html = page.content()
+                    content = str(page_html)
+
+                # Close browser
+                page.close()
+                browser.close()
+
+                yield Document(
+                    page_content=content,
+                    metadata={
+                        "url": url,
+                    },
+                )