Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
d9ab4458ad* feat: add new event delivery method "direct" - Updated event_delivery options in ConfigResponse and Settings to include "direct". - Modified build_flow function to utilize settings_service for conditional event handling. - Improved flow processing by returning job_id or event responses based on delivery method. * feat: implement direct event delivery method on the frontend - Updated buildFlow function to include eventDelivery parameter, allowing for "direct" event delivery mode. - Modified NodeStatus and IOModal components to utilize the new eventDelivery setting. - Expanded flowStore and buildUtils to support event delivery options, improving flexibility in event handling. - Added "direct" option to event delivery types in enums for better configurability. - Updated tests to cover new event delivery modes. * fix: change default event delivery method to "polling" - Updated the default value of event_delivery in Settings from "direct" to "polling" to align with intended behavior. - Ensured documentation reflects the change in default settings for clarity on event delivery options. * Update src/frontend/src/controllers/API/api.tsx * Update src/frontend/src/utils/buildUtils.ts * Update src/frontend/src/utils/buildUtils.ts * Update src/frontend/src/utils/buildUtils.ts * feat: add event delivery validation for multi-worker environments - Introduced a new field validator for the `event_delivery` setting to enforce "direct" delivery when the number of workers exceeds one. - This change ensures compatibility with multi-worker setups, improving the robustness of event handling in the application. * feat: add warning for multi-worker event delivery - Added a warning log in the Settings class to notify users when a multi-worker environment is detected, indicating that "direct" event delivery will be used. This enhances visibility and understanding of event handling behavior in such setups. * refactor: remove "direct" from event delivery modes in tests - Updated the event delivery modes in the withEventDeliveryModes utility to exclude "direct", aligning with recent changes in event handling behavior. - This change simplifies the testing setup and ensures consistency with the current application logic. --------- Co-authored-by: Cristhian Zanforlin Lousa <cristhian.lousa@gmail.com> |
||
|---|---|---|
| .devcontainer | ||
| .github | ||
| .vscode | ||
| deploy | ||
| docker | ||
| docker_example | ||
| docs | ||
| scripts | ||
| src | ||
| test-results | ||
| .composio.lock | ||
| .env.example | ||
| .eslintrc.json | ||
| .gitattributes | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| CODE_OF_CONDUCT.md | ||
| CONTRIBUTING.md | ||
| DEVELOPMENT.md | ||
| eslint.config.js | ||
| LICENSE | ||
| Makefile | ||
| pyproject.toml | ||
| README.md | ||
| render.yaml | ||
| uv.lock | ||
Langflow is a powerful tool for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and a built-in API server that turns every agent into an API endpoint 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 to get started quickly and iterate.
- Access to Code so developers can tweak any component using Python.
- Playground to immediately test and iterate on their flows with step-by-step control.
- Multi-agent orchestration and conversation management and retrieval.
- Deploy as an API or export as JSON for Python apps.
- Observability with LangSmith, LangFuse and other integrations.
- Enterprise-ready security and scalability.
⚡️ Quickstart
Langflow works with Python 3.10 to 3.13.
Install with uv (recommended)
uv pip install langflow
Install with pip
pip install langflow
📦 Deployment
Self-managed
Langflow is completely open source and you can deploy it to all major deployment clouds. Follow this guide to learn how to use Docker to deploy Langflow.
Fully-managed by DataStax
DataStax Langflow is a full-managed environment with zero setup. Developers can sign up for a free account to get started.
⭐ 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.