84958cf99a
* refactor(loop): implement isolated subgraph execution for LoopComponent - Refactor LoopComponent to execute loop body as isolated subgraph - Add create_subgraph method to Graph class for creating isolated subgraphs - Add loop_utils with get_loop_body_vertices helper function - Add on_end_vertex event emission in async_start for progress tracking - Add comprehensive tests for subgraph execution and event emission This change enables proper vertex event streaming during loop execution by running each iteration as an isolated subgraph with its own context. * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * [autofix.ci] apply automated fixes (attempt 3/3) * fix: Improve subgraph event streaming to UI - Add event types to stream token event manager (end_vertex, error, build_start, build_end) - Preserve start_component_id in async_start for proper subgraph execution - Fix has_chat_output/has_chat_input to use vertex.base_name instead of string matching - Add _stream_to_playground check to allow inner graph components to send events - Fix _send_message_event to properly extract and forward message IDs * update index * fix: Enhance extract_loop_output to handle multiple message formats * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * [autofix.ci] apply automated fixes (attempt 3/3) * fix: Improve intra-layer cycle detection logging in sorting function * refactor: Update loop execution to create fresh subgraph for each iteration * test: Add tests for subgraph isolation and state management * fix: Update LoopComponent description for clarity on item processing * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * [autofix.ci] apply automated fixes (attempt 3/3) * fix: Add warning log for missing custom_component in loop item injection * refactor: Simplify loop event tests while preserving critical coverage Reduced test complexity by removing excessive mocking while maintaining completeå event manager propagation coverage. Event manager tests are critical for ensuring UI updates work correctly during loop execution. * fix: Update Google dependency version to 2.5.0 across multiple components * fix: Update value format in Research Translation Loop JSON for clarity * fix: Inject loop items into HandleInput fields via raw_params HandleInput fields (type="other") were receiving None instead of loop items because: 1. Fields with type="other" are skipped during field param processing 2. Loop->Parser edge is filtered out in subgraph creation 3. updated_raw_params flag was reset too early by multiple build_params() calls Fix: - Inject loop items into template before prepare() - Inject into raw_params after prepare() using update_raw_params() - Persist updated_raw_params flag across all build_params() calls - Reset flag in _build_each_vertex_in_params_dict() after processing Tests: - Add integration test exercising execute_loop_body() code path - Verify update_raw_params() called with correct data per iteration - Add full Loop+Parser integration test - Fix fieldName -> field_name in existing tests * fix: Update done_output method to use internal event manager and improve event handling * refactor: Update execute_loop_body to use async context manager for subgraph creation and cleanup * fix: import json in unified_models.py * feat: Implement subgraph tracing context management * fix: Update code_hash and improve loop component execution logic * fix: Update code_hash and refine LoopComponent execution logic * [autofix.ci] apply automated fixes * fix: Update LoopComponent subgraph execution to set event manager as instance attribute * test: Enhance subgraph execution tests to verify event manager passing --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Langflow is a powerful platform for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and built-in API and MCP servers that turn every workflow into a tool that can be integrated into applications built on any framework or stack. Langflow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.
✨ Highlight features
- Visual builder interface to quickly get started and iterate.
- Source code access lets you customize any component using Python.
- Interactive playground to immediately test and refine your flows with step-by-step control.
- Multi-agent orchestration with conversation management and retrieval.
- Deploy as an API or export as JSON for Python apps.
- Deploy as an MCP server and turn your flows into tools for MCP clients.
- Observability with LangSmith, LangFuse and other integrations.
- Enterprise-ready security and scalability.
🖥️ Langflow Desktop
Langflow Desktop is the easiest way to get started with Langflow. All dependencies are included, so you don't need to manage Python environments or install packages manually. Available for Windows and macOS.
⚡️ Quickstart
Install locally (recommended)
Requires Python 3.10–3.13 and uv (recommended package manager).
Install
From a fresh directory, run:
uv pip install langflow -U
The latest Langflow package is installed. For more information, see Install and run the Langflow OSS Python package.
Run
To start Langflow, run:
uv run langflow run
Langflow starts at http://127.0.0.1:7860.
That's it! You're ready to build with Langflow! 🎉
📦 Other install options
Run from source
If you've cloned this repository and want to contribute, run this command from the repository root:
make run_cli
For more information, see DEVELOPMENT.md.
Docker
Start a Langflow container with default settings:
docker run -p 7860:7860 langflowai/langflow:latest
Langflow is available at http://localhost:7860/. For configuration options, see the Docker deployment guide.
Caution
- Users must update to Langflow >= 1.7.1 to protect against CVE-2025-68477 and CVE-2025-68478.
- Langflow version 1.7.0 has a critical bug where persisted state (flows, projects, and global variables) cannot be found when upgrading. Version 1.7.0 was yanked and replaced with version 1.7.1, which includes a fix for this bug. DO NOT upgrade to version 1.7.0. Instead, upgrade directly to version 1.7.1.
- Langflow versions 1.6.0 through 1.6.3 have a critical bug where
.envfiles are not read, potentially causing security vulnerabilities. DO NOT upgrade to these versions if you use.envfiles for configuration. Instead, upgrade to 1.6.4, which includes a fix for this bug.- Windows users of Langflow Desktop should not use the in-app update feature to upgrade to Langflow version 1.6.0. For upgrade instructions, see Windows Desktop update issue.
- Users must update to Langflow >= 1.3 to protect against CVE-2025-3248
- Users must update to Langflow >= 1.5.1 to protect against CVE-2025-57760
For security information, see our Security Policy and Security Advisories.
🚀 Deployment
Langflow is completely open source and you can deploy it to all major deployment clouds. To learn how to deploy Langflow, see our Langflow deployment guides.
⭐ Stay up-to-date
Star Langflow on GitHub to be instantly notified of new releases.
👋 Contribute
We welcome contributions from developers of all levels. If you'd like to contribute, please check our contributing guidelines and help make Langflow more accessible.