# Firecrawl v2.1.0 is here!
## ✨ New Features
- **Search Categories**: Filter search results by specific categories using the `categories` parameter:
- `github`: Search within GitHub repositories, code, issues, and documentation
- `research`: Search academic and research websites (arXiv, Nature, IEEE, PubMed, etc.)
- More coming soon
- **Image Extraction:** Added image extraction support to the v2 scrape endpoint.
- **Data Attribute Scraping:** Now supports extraction of `data-*` attributes.
- **Hash-Based Routing:** Crawl endpoints now handle hash-based routes.
- **Improved Google Drive Scraping:** Added ability to scrape TXT, PDF, and Sheets from Google Drive.
- **PDF Enhancements:** Extracts PDF titles and shows them in metadata.
- **API Enhancements:**
- Map endpoint supports up to **100k results**.
- **Helm Chart:** Initial Helm chart added for Firecrawl deployment.
- **Security:** Improved protection against XFF spoofing.
## 🛠 Fixe
<img width="994" height="570" alt="Image" src="https://github.com/user-attachments/assets/491002a7-02e9-4fa4-98ea-9c9c5ba2b940" />
## 🎉 Dify v1.8.0 Release Notes 🎉
Hello, Dify community! We're excited to bring you version 1.8.0, packed with significant improvements across the board - from enhanced security and performance optimizations to a revamped UI and powerful new workflow features. Let's dive into what's new!
### 🚀 New Features
#### Workflow & Agent Capabilities
- **Multi-Model Credentials System**: Implemented a comprehensive multi-model credentials system with new database tables, enabling more flexible model management. Thanks to @hjlarry! (#24451)
- **MCP Support with OAuth**: Added Model Context Protocol (MCP) support for resource discovery with OAuth authentication, expanding integration possibilities. Kudos to @CodeSpaceiiii! (#24223)
- **Default Values for Workflow Variables**: All workflow start node variable types now support default values, making workfl
This release fixes the "SSRF Vulnerability via malicious webhook" security advisory. It is recommended that people using the self-hosted version of Firecrawl update to v2.0.1 immediately. More info in the advisory: https://github.com/firecrawl/firecrawl/security/advisories/GHSA-p2wg-prhf-jx79
# Introducing v2.0.0
### Key Improvements
* **Faster by default**: Requests are cached with `maxAge` defaulting to 2 days, and sensible defaults like `blockAds`, `skipTlsVerification`, and `removeBase64Images` are enabled.
* **New summary format**: You can now specify `"summary"` as a format to directly receive a concise summary of the page content.
* **Updated JSON extraction**: JSON extraction and change tracking now use an object format: `{ type: "json", prompt, schema }`. The old `"extract"` format has been renamed to `"json"`.
* **Enhanced screenshot options**: Use the object form: `{ type: "screenshot", fullPage, quality, viewport }`.
* **New search sources**: Search across `"news"` and `"images"` in addition to web results by setting the `sources` parameter.
* **Smart crawling with prompts**: Pass a natural-language `prompt` to crawl and the system derives paths/limits automatically. Use the new crawl-params-preview endpoint to inspect the derived options be
# ✨ What’s New in v1.7.2? ✨
Alright folks, buckle up! Version 1.7.2 is here, packed with a ton of quality-of-life improvements, bug fixes, and some slick new features to make your Dify experience even smoother. This release has been a community effort, and we want to give a big shoutout to all the contributors, especially the new folks who jumped in – welcome to the party! 🎉
## 🚀 Major Feature: Workflow Visualization
A new relations panel allows you to visualize dependencies within your workflows. Big thanks to @Minamiyama for #21998! Now when you select any node and press `Shift`, you will see magic flowing lines.
<img width="3840" height="1870" alt="image" src="https://github.com/user-attachments/assets/fa196809-10ee-472b-936e-1270787d4535" />
## 🚀 Major Feature: Node Search
You can now easily find nodes in the workflow editor using the new search feature by @croatialu, @ZeroZ-lab, @HyaCiovo, @MatriQ, @lyzno1, @crazywoola in #23685.
<img width="3840" height="1870
# 🎉 Dify v1.7.1 Release Notes 🎉
Hello, Dify enthusiasts! We're thrilled to announce version 1.7.1 of our platform, bringing a fresh batch of refinements and enhancements to your workflow. Here's a breakdown of what's changed:
## 🚀 New Features
- **Default Value for Select Inputs**: Now you can set a default value for select input fields, providing a smoother user experience when working with forms. Thanks to @antonko. (#21192)
- **Selecting Variables in Conditional Filters**: We've added the capability to select variables in conditional filtering within list operations. This feature, spearheaded by @leslie2046, will streamline data manipulation tasks. (#23029)
- **OpenAPI Schema Enhancement**: Support for `allOf` in OpenAPI properties inside schema has been added, courtesy of @mike1936. It's a big win for API design consistency. (#22975)
- **K8s Pure Migration Option**: We've introduced a pure migration option for the `api` component within Kubernetes deployments, mak
# 🌟 What’s New in v1.7.0? 🌟
Version 1.7.0 is packed with features that expand our app's flexibility and enhance performance. Here's what we're bringing to the table:
## 🏗️ Major Feature: OAuth Support in Tool Plugins
Tool plugins now support OAuth 2.0 authentication, allowing users to securely connect with third-party services without manually managing API keys. This includes refresh token support for maintaining long-term authentication sessions.
(#22550 thanks @Mairuis @zxhlyh )
<img width="3596" height="1878" alt="image" src="https://github.com/user-attachments/assets/cd155e0a-7c52-44cf-97e5-167958c4986d" />
## 🏗️ Major Feature: Plugin auto upgrade strategy
Plugins can now be automatically updated with configurable upgrade policies and rollback mechanisms. The system monitors plugin repositories and performs seamless upgrades while ensuring compatibility with your Dify version.
(#19758 thanks @RockChinQ @iamjoel )
<img width="3002" height="1926" alt="image" src="h
## Thank you and welcome to our new contributors 🔥
@MagnusS0
## Summary 🎉
The release of 4.4.5 includes new extensions, endpoints, and functionality; security and package updates; along with general bug fixes.
## 🚨 OpenBB Platform Breaking Changes
- This version introduces a deprecation warning for Python 3.9 - support for this version will be dropped later this year.
- File logging service is now disabled by default, the logging module is no longer initialized on startup.
- Set `"logging_suppress": false`, in `system_settings.json`, to enable.
- The endpoint, `obb.economy.port_volume`, is now deprecated and moved to: `obb.economy.shipping.port_volume`
## 🚨 Dependency Changes
- `openbb-charting` has been updated to use Plotly V6
- `pytest-recorder` now has a `record_curl` marker for capturing unit test cassettes for HTTP requests via [curl-adapter](https://pypi.org/project/curl-adapter/)
- Code for Posthog has been completely removed from `openbb-core`, depen
## Firecrawl v1.15.0 is here!
- SSO for enterprise
- Improved scraping reliability
- Search params added to activity logs
- FireGEO example
- And over 50 PRs merged for bug & improvements 🔥
### Improvements
- OMCE support in `scrapeURL` and HTML transformer
- Improved logging (search params, cache age)
- New `created_at` field in `/crawl/active` response
- Case-insensitive URL protocol checks
- `filterLinks` ported to Rust
### Fixes
- HTML transformer stability (Arabic, base tag, panic)
- `scrapeURL` index bug & waitFor exclusion
- PDF billing bug with `parsePDF=false`
- Crawl returning only 1 result (edge case)
- Crawler no-sections bug
- Logger method naming
- Timeout handling in API
- `crawl-status` resilience for ejected jobs
### SDK & Infra
- SDK header param fix & async error handling
- Express port now configurable via env var
- Temporary crawl expiry exemption
### Docs
- Kubernetes setup update
## What's Changed
* Make worker Express s
# 🌟 What’s New in v1.6.0? 🌟
Welcome to version 1.6.0! 🎉🎉🎉 This release is packed with new features, crucial fixes, and various optimisations aimed at enhancing your experience. We've listened to your feedback and made significant improvements across the board.
## 🎯 Spotlight Feature: **Introducing MCP Support!** 🎯
We’re thrilled to introduce **support for [Anthropic’s Model Context Protocol (MCP)](https://docs.anthropic.com/claude/docs/model-context-protocol)** — a new industry standard for structuring model inputs and outputs. MCP makes it easier than ever to integrate with cutting-edge language models using a unified, reliable format.
📖 **[FOR MORE INFORMATION](https://dify.ai/blog/v1-6-0-built-in-two-way-mcp-support)**
## 🚀 New Features
- **MCP Support**: We've integrated MCP support, opening doors for more seamless interactions. (See #20716, by *Novice*
## v1.14.0 Release
We're excited to announce the release of Firecrawl v1.14.0, packed with cool updates.
- Authenticated scraping (Join the waitlist [here](https://firecrawl.dev/authenticated-scraping))
- Zero data retention for enterprise (Email us at [help@firecrawl.com](mailto:help@firecrawl.com) to enable it)
- Improved p75 speeds
- New MCP version w/ maxAge + better tool calling
- Open Researcher Example (Open Source Researcher). See [repo](https://github.com/mendableai/open-researcher)
- And so much more 🔥
## What's Changed
* fix json format on search (ENG-2529) by @mogery in https://github.com/mendableai/firecrawl/pull/1729
* proxy used improvement by @mogery in https://github.com/mendableai/firecrawl/pull/1727
* add pdf prefetch log for debugging (ENG-2542) by @mogery in https://github.com/mendableai/firecrawl/pull/1734
* (feat/ledger) Ledger events by @nickscamara in https://github.com/mendableai/firecrawl/pull/1728
* fix(auto_charge): bad hourly counter log
# 🎉 What’s New in v1.5.1? 🎉
In this release, we've packed a punch with a host of new features, enhancements, and fixes designed to make your experience smoother and more intuitive.
## 🚀 New Features
- **Knowledge Basis Indexing**: Introduced KB indexing by @Gevtolev in #20868. It optimizes the access and retrieval speeds for your data treasures.
- **Model Provider Validation**: Added model provider validation in the API by @khoazero123 in #21582. Ensure your models are always in check.
- **Dynamic Select Parameter**: Implemented DYNAMIC_SELECT for dynamic options in parameter entities by @Yeuoly in #21425. Say goodbye to static param limits!
- **Structured Output Plugin**: Now invoke LLMs with structured output via a new API endpoint by @Yeuoly in #21624.
- **Adaptive Panel Width Management**: A refactor to add adaptive width observer for panels by @ZeroZ-lab in #21576.
- **New Plugin Enhancements**: Default value autofill in plugin settings by @leslie2046 in #21669.
#
## Firecrawl v1.13.0 Changelog
- Added AU, FR, DE to [Stealth Mode](https://docs.firecrawl.dev/features/proxies#location-based-proxy-selection)
- Crawl subdomains with [allowSubdomains](https://docs.firecrawl.dev/api-reference/endpoint/crawl-post#body-allow-subdomains)
- Google slides scraping
- Generate a PDF of the current page. See [docs](https://docs.firecrawl.dev/api-reference/endpoint/scrape#generate-pdf)
- Higher res screenshots with [quality param](https://docs.firecrawl.dev/api-reference/endpoint/scrape#screenshot)
- Weekly view for usage on the dashboard
- Fireplexity Example (Open Source Perplexity). See [repo](https://github.com/mendableai/fireplexity)
- And more!
### Features
- Support cookies in `scrapeURL` via `safeFetch`
- Add Google Slides scraping
- Add PDF actions to API, Python & JS SDKs
- Screenshot quality config
- `parsePDF` support in Python & JS SDKs
- Allow international URLs
- Enable subdomain crawling in SDKs
- Worker liveness check befo
# 🚀 What's New in v1.5.0?
Meet **v1.5.0**—a sleek, powerful update boosting your productivity with simplified debugging and powerful integrations. Let's jump right in:
## 🏗️ Major Feature: Enhanced Workflow Debugging
We've completely rebuilt our workflow debugging tools! Effortlessly visualize and troubleshoot workflows with improved interfaces, persistent debugging variables (#20699, thanks @QuantumGhost), and enhanced dashboard integration (#21369, kudos to @iamjoel). Easily track your workflow runs directly from the dashboard, and spend less time debugging and more time creating amazing workflows. Dive deeper in our [blog post](https://dify.ai/blog/dify-1-5-0-real-time-workflow-debugging-that-actually-works).
## ✨ New & Improved Features
* **Drag-and-Drop DSL:** Easily create apps by dropping DSL files directly into your browser (#20706, @ACAne0320).
* **Enhanced D
## Summary 🎉
OpenBB 4.4.4 includes bug fixes, package updates, and a small expansion of data coverage.
## 🚨 OpenBB Platform Breaking Changes
- Users with OpenBB Platform Installer < 1.0.3 should follow instructions [here](https://docs.openbb.co/platform/installation) to update the packages for the latest versions.
## 🆕 New Endpoints
- `obb.equity.fundamental.filings`
- Adds provider: `nasdaq`
- Download filings formatted as PDF, XLSX, DOC, or HTML.
- `obb.economy.survey.manufacturing_outlook_ny`
- Provider: `fred`
- Adds Empire State Manufacturing Survey from FRED.
## 🐛 OpenBB Platform Bug Fixes
- `yFinance` has been adapted to use `curl-cffi` by mounting the Requests Session object with `curl-adapter`.
- `to_df`/`to_dataframe` have been update to handle a wider variety of response shapes, which will reduce failures with conversion.
- FOMC Documents Workspace App definition fixed to include the new, required, 'roles' key in `widgets.json`
- Docs
## Firecrawl v1.12.0 is here!
- New Concurrency System - Specify max concurrency by request for better control. [See docs](https://docs.firecrawl.dev/api-reference/endpoint/crawl-post#body-max-concurrency).
- Crawl Entire Domain Param - Follow internal links to sibling or parent URLs, not just child paths (prev. allowBackwardLinks). [See docs](https://docs.firecrawl.dev/api-reference/endpoint/crawl-post#body-crawl-entire-domain).
- Google Docs Scraping - We now officially support scraping Google Docs files
- Improved Activity Logs - Better support for FIRE-1 requests. [See your logs here.](https://www.firecrawl.dev/app/logs)
- /search Playground Enhanced - Location Params added. [Check out the playground.](https://www.firecrawl.dev/playground?mode=search)
- Firestarter Example - Open Source Chatbot building platform. [Repo here.](https://github.com/mendableai/firestarter)
- Plus tons of performance improvements and bug fixes.
P.S. Have feedback or ideas for v1.13.0? Hit re
# 🚀 What’s New in v1.4.3? 🚀
It’s all about smoothing out the wrinkles and enhancing flexibility in this update. Here’s the rundown:
## 🛠 Fixes and Improvements
- **LLM Node Enhancements**: We've ironed out issues with missing parameters for structured outputs; now your LLM node is more robust and prepared for all it can handle thanks to @laipz8200 in [#20915](https://github.com/langgenius/dify/pull/20915).
- **Gemini LLM Support**: For those integrating with Gemini, you'll now find support for the Gemini 0.2.x plugin running smoothly in your agent apps, as addressed by @takuya-o in [#20794](https://github.com/langgenius/dify/pull/20794).
- **Markdown Button Fix**: Sending messages through the Markdown button should now work flawlessly, thanks to @hjlarry in [#20933](https://github.com/langgenius/dify/pull/20933).
- **Login Rate Limit Clearing**: After a password reset, we’ve made sure the login rate limits are cleared, preventing any unnecessary hurdles, addressed by
## Firecrawl v1.11.0 is here!
### Major Features
- Launched our Firecrawl Index
- Speed up scrapes 5x if opted in
- Improved Activity Logs
- View webhook events
- Active crawl management
- Fire Enrich Example (Open Source Clay)
- Community Java SDK
- and a lot more
### Features
- Improved Playwright tests and webhook test coverage
- Added `GET /crawl/ongoing` endpoint
- Introduced tag support in change tracking
- Added `integration` field to jobs and propagated through queue worker
- Parallel testing for runpod v2 and updated `mu`
- Ported `queryIndexAtSplitLevel` to RPC
- Enhanced SDK with index and missing parameters
- Removed redundant GCS check to improve performance
- Added `credits_billed` field across pipeline
- Enabled domain-level index splitting for better map querying
- Used index in search and extract operations
- Removed unused index columns
### Fixes & Improvements
- Fixed crawl pre-finishing logic
- Refactored `callWebhook`
## 🚀 What's New in v1.4.2?
We've packed v1.4.2 with usability upgrades, polished features, and stability enhancements. Check out what's new:
### 🌟 New Features & Improvements
- **Smarter Webapp Inputs**: Automatically fill hidden fields using URL parameters (#20630), by @hjlarry.
- **Efficient Document Extraction**: Faster, streamlined processing for Excel and CSV files (#20625), thanks to @HaiyangPeng.
- **Marketplace UI Update**: Easier browsing with improved sorting for app types (#20685), courtesy of @nite-knite.
- **Personalized Chatbot UX**: Chat input placeholder now dynamically displays your bot's name (#20473), thanks to @crazywoola.
- **Robust File Uploads**: Addressed issues with multiple file extension mappings (#20559), by @bowenliang123.
- **Advanced Knowledge Base API Features**:
- Refined metadata filtering for precise querying. Targeted searches using chunk IDs (#20426), by @Gevtolev.
- Improved tagging and dataset binding capabilities
We’re excited to announce the launch of our new Search API endpoint that combines web search with Firecrawl’s powerful scraping capabilities.
### Search Features:
- Search the web and get full content from results in one API call
- Choose specific output formats (markdown, HTML, links, screenshots)
- Customize search parameters (language, country, time range, number of results)
- Full SDK support for Python and Node.js
### More Features
- Auto mode proxy for scraping (`scrapeURL`, `js-sdk`) [#1551](https://github.com/mendableai/firecrawl/pull/1551), [#1602](https://github.com/mendableai/firecrawl/pull/1602)
- Timeout handling and content type improvements for `scrapeURL/pdf` [#1570](https://github.com/mendableai/firecrawl/pull/1570), [#1604](https://github.com/mendableai/firecrawl/pull/1604), [#1592](https://github.com/mendableai/firecrawl/pull/1592)
- Redis improvements: separate non-eviction Redis support [#1600](https://github.com/mendableai/firecrawl/pull/1600)
- Sear