Skip to content

feat: add Browser Run integration (Loader + Tool) #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vamshi694 wants to merge 5 commits into
base: main
Choose a base branch
from
Open

feat: add Browser Run integration (Loader + Tool) #41

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8c87c8f
feat: add Browser Run integration (Loader + Tool)
Apr 20, 2026
407ba99
docs: improve Browser Run README with mode tables, scrape/json exampl…
Apr 20, 2026
200a38b
refactor: rename browser_run.py to loaders.py, add notebook with real…
Apr 21, 2026
d7240a3
fix: address review feedback - timeouts, error handling, focused tests
Apr 21, 2026
bfb68b4
fix: add missing timeout to crawl pagination GET request
Apr 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,26 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## langchain-cloudflare


### [0.3.5]

#### Added

- **`CloudflareBrowserRunLoader`**: New `BaseLoader` for document ingestion via [Cloudflare Browser Run](https://developers.cloudflare.com/browser-run/) REST API. Supports four modes: `markdown` (`/markdown`), `crawl` (`/crawl` with async polling), `scrape` (`/scrape` with CSS selectors), and `content` (`/content` for raw HTML). Includes sync (`load`, `lazy_load`) and async (`aload`, `alazy_load`) methods. Configurable crawl depth, page limit, poll interval, timeout, and all shared Browser Run options (viewport, cookies, headers, resource blocking).
- **`CloudflareBrowserRunTool`**: New `BaseTool` for LangGraph agent workflows. Supports five modes: `markdown`, `json` (AI-powered structured data extraction via `/json`), `links` (`/links`), `screenshot` (`/screenshot`), and `pdf` (`/pdf`). Tool name is auto-set per mode (e.g. `cloudflare_browser_run_json`) for agent disambiguation. JSON mode supports both natural language prompts and JSON schema definitions for structured extraction.
- **`TokenErrors.INSUFFICIENT_BROWSER_RUN_TOKEN`**: New centralized error message for missing Browser Run API credentials. Notes that Browser Run is REST-only (no Worker binding support).

#### Changed

- **Version bump**: 0.3.4 → 0.3.5 (Browser Run integration).

#### Tests

- Added unit tests for `CloudflareBrowserRunLoader` and `CloudflareBrowserRunTool`: token validation, configuration defaults, URL construction, header building, shared options builder.
- Added integration tests covering markdown/content/scrape/crawl loader modes and markdown/json/links/screenshot tool modes, both sync and async.

---

### [0.3.4]

#### Changed
Expand Down
3 changes: 3 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,9 @@ It contains the following packages.
- [ChatCloudflareWorkersAI](https://python.langchain.com/docs/integrations/chat/cloudflare_workersai/)
- [CloudflareWorkersAIEmbeddings](https://python.langchain.com/docs/integrations/text_embedding/cloudflare_workersai/)
- [CloudflareVectorize](https://python.langchain.com/docs/integrations/vectorstores/cloudflare_vectorize/)
- CloudflareWorkersAIReranker
- CloudflareBrowserRunLoader (Document Loader via [Browser Run](https://developers.cloudflare.com/browser-run/))
- CloudflareBrowserRunTool (Agent Tool via [Browser Run](https://developers.cloudflare.com/browser-run/))

### LangGraph

Expand Down
Loading