Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
4d3eae63ac* chore: update webrtcvad dependency and add optional audio support - Updated webrtcvad version requirement to >=1.9.4 in pyproject.toml and uv.lock. - Moved webrtcvad to optional dependencies under the new 'audio' category in both pyproject.toml files for better modularity. - Ensured compatibility with existing dependencies while enhancing documentation for optional audio features. * fix: handle optional import of voice_mode_router in API initialization - Updated the API router initialization to conditionally include the voice_mode_router if it is available, improving modularity and preventing import errors. - Adjusted the import statement for voice_mode_router to handle ImportError gracefully, ensuring the application remains robust in its absence. * feat: add voice mode flag to API configuration - Introduced a new function `get_voice_mode_enabled` to check for the availability of the `webrtcvad` library, enhancing the API's capability to support voice mode features. - Updated the `ConfigResponse` schema to include `voice_mode_enabled` flag, allowing clients to query the status of voice mode support. - Integrated the voice mode feature flag into the `get_config` endpoint response, improving the configurability of the API. * test: skip voice mode tests if webrtcvad is not installed - Added a conditional import for the webrtcvad library in the voice mode test suite. - Implemented a pytest marker to skip tests when webrtcvad is unavailable, enhancing test robustness and preventing unnecessary failures. * feat: add voice mode state management to flows manager store - Introduced `voiceModeEnabled` state and `setVoiceModeEnabled` action in the flows manager store to manage the voice mode feature. - Updated the `ConfigResponse` interface and `useGetConfig` hook to integrate the new voice mode state, allowing for dynamic configuration updates. - Enhanced the API's configurability by ensuring the voice mode state is properly set based on the API response. * feat: conditionally render voice button based on voice mode state - Integrated `voiceModeEnabled` from the flows manager store to control the visibility of the VoiceButton component. - The VoiceButton will now return null if voice mode is not enabled, enhancing the user interface by preventing unnecessary rendering. * fix: ensure boolean conversion for voice mode state in config hook - Updated the `setVoiceModeEnabled` function in the `useGetConfig` hook to explicitly convert the `voice_mode_enabled` value to a boolean, ensuring consistent handling of the voice mode state based on API responses. * refactor: conditionally import voice_mode_router in API initialization - Updated the API router to conditionally include the voice_mode_router based on its availability, enhancing modularity and preventing import errors. - Adjusted the __init__.py file to dynamically add voice_mode_router to the __all__ list if the import is successful, improving the API's robustness. * chore: revert mcp version update * refactor: reorder router initialization and add audio flag to backend install task * feat: add audio module to backend installation command in VS Code tasks * ci: add audio extras to uv sync in frontend tests |
||
|---|---|---|
| .cursor/rules | ||
| .devcontainer | ||
| .github | ||
| .vscode | ||
| deploy | ||
| docker | ||
| docker_example | ||
| docs | ||
| scripts | ||
| src | ||
| test-results | ||
| .coderabbit.yaml | ||
| .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.