Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
6f521e17ea* refactor: remove unused property and state management from StateVertex class * feat: extend next runnable vertices for activated vertices in state vertices * refactor: simplify ListenComponent by removing unused methods and updating inheritance * refactor: update NotifyComponent to use new input/output structure and improve context handling * feat: add is_state attribute to StateVertex for improved state management * refactor: update input validation to exclude custom attributes from reserved words * refactor: enhance ListenComponent and NotifyComponent with improved input types and output caching - Updated ListenComponent to include additional input types for context_key. - Modified NotifyComponent to use HandleInput for input_value and added input types. - Set cache to False for the output in NotifyComponent to ensure fresh data retrieval. * refactor: update state management in Graph class to improve handling of state vertices - Changed _is_state_vertices to be initialized as None and updated its type hint. - Added a property is_state_vertices to lazily compute state vertices when accessed. - Refactored activate_state_vertices method to utilize the new property for better clarity and performance. * refactor: update ListenComponent to return Data with text instead of data - Modified the build method in ListenComponent to return Data initialized with a text field instead of a data field, enhancing clarity in data handling. * refactor: update NotifyComponent to use input_value for data handling - Modified the build method in NotifyComponent to replace input_data with input_value for improved clarity and consistency in data processing. - Ensured that the context handling and status updates reflect the changes in input handling. * refactor: simplify context key check in Graph class for better readability * refactor: enhance Graph class to include recursive predecessor retrieval and update edge handling * 📝 Add docstrings to `try-to-fix-listen-notify` (#8326) Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes * refactor: clean up unused imports and improve docstring formatting across components * refactor: rename build method to notify_components and improve input handling in NotifyComponent * refactor: rename build method to listen_for_data in ListenComponent for clarity * fix: correct status assignment logic in NotifyComponent to ensure accurate state updates * fix: handle None input value in NotifyComponent to ensure default Data initialization * Make context_key required Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * 📝 Add docstrings to `try-to-fix-listen-notify` (#8442) Co-authored-by: Jordan Frazier <jordan.frazier@datastax.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: Edwin Jose <edwin.jose@datastax.com> Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> fix: remove duplicated import statement in nvidia_ingest (#8439) * ✨ Implement caching logic for Listen/Notify components and enhance docstring for edge retrieval - Added `_set_cache_if_listen_notify_components` method to disable caching for all vertices if Listen/Notify components are present, ensuring proper real-time communication. - Improved docstring for `_get_edges_as_list_of_tuples` to clarify the return value and structure. * 🔧 Refactor Graph class by removing state management methods - Removed `get_state` and `update_state` methods from the `Graph` class to streamline state management. - This change simplifies the class structure and focuses on enhancing the overall design of the graph handling. * fix(listen): restrict input types to "Message" for ListenComponent * refactor: remove deprecated components from deactivated module --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Jordan Frazier <jordan.frazier@datastax.com> Co-authored-by: Edwin Jose <edwin.jose@datastax.com> |
||
|---|---|---|
| .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 | ||
| SECURITY.md | ||
| uv.lock | ||
Caution
Users must update to Langflow >= 1.3 to protect against CVE-2025-3248.
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 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.
- Observability with LangSmith, LangFuse and other integrations.
- Enterprise-ready security and scalability.
⚡️ Quickstart
Langflow requires Python 3.10 to 3.13 and uv.
- To install Langflow, run:
uv pip install langflow -U
- To run Langflow, run:
uv run langflow run
- Go to the default Langflow URL at
http://127.0.0.1:7860.
For more information about installing Langflow, including Docker and Desktop options, see Install Langflow.
📦 Deployment
Langflow is completely open source and you can deploy it to all major deployment clouds. To learn how to use Docker to deploy Langflow, see the Docker deployment guide.
⭐ 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.