mirror of
https://github.com/langflow-ai/langflow.git
synced 2026-07-24 08:57:31 +08:00
c5d9cbae49
* feat: add initial implementation of dynamic state model creation and output getter in graph state module * feat: implement _reset_all_output_values method to initialize component outputs in custom_component class * feat: add state model management with lazy initialization and dynamic instance getter in custom_component class * feat: Refactor Component class to use public method get_output_by_method Refactor the Component class in the custom_component module to change the visibility of the method `_get_output_by_method` to public by renaming it to `get_output_by_method`. This change improves the accessibility and clarity of the method for external use. * feat: add output setter utility to manage output values in state model properties * feat: implement validation for methods' classes in output getter/setter utilities in state model to ensure proper structure * feat: add state model creation from graph in state_model.py * feat: enhance Graph class with lazy loading for state model creation from graph * feat: add unit tests for state model creation and validation in test_state_model.py * feat: add unit tests for state model creation and validation in test_state_model.py * feat: add functional test for graph state update and validation in test_graph_state_model.py * fix: update _instance_getter function to accept a parameter in component.py for state model instance retrieval * refactor: rename test to clarify purpose in test_state_model.py for functional state update validation * chore: import Finish constant in test_graph_state_model.py for improved clarity and usage in state model tests * refactor: add optional validation in output getter/setter methods for improved method integrity in state model handling * refactor: enhance state model creation with optional validation and error handling for output methods in model.py * refactor: serialize and deserialize GraphStateModel in test_graph_state_model.py * refactor: improve error message and add verbose mode for graph start in test_state_model.py * refactor: remove verbose flag from graph.start in TestCreateStateModel for consistency in test_state_model.py * refactor: disable validation when creating GraphStateModel in state_model.py for improved flexibility * refactor: add validation documentation for method attributes in model.py to enhance code clarity and usability * refactor: expand docstring for build_output_getter in model.py to clarify usage and validation details * refactor: add detailed docstring for build_output_setter in model.py to improve clarity on functionality and usage scenarios * refactor: add comprehensive docstring for create_state_model in model.py to clarify functionality and usage examples * refactor: enhance docstring for create_state_model_from_graph in state_model.py to clarify functionality and provide examples * test: add JSON schema validation in graph state model tests for improved structure and correctness verification * refactor: Improve graph_state_model.json_schema unit test readability and structure.
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Docs - Free Cloud Service - Self Managed
✨ Core features
- Python-based and agnostic to models, APIs, data sources, or databases.
- Visual IDE for drag-and-drop building and testing of workflows.
- Playground to immediately test and iterate workflows with step-by-step control.
- Multi-agent orchestration and conversation management and retrieval.
- Free cloud service to get started in minutes with no setup.
- Publish as an API or export as a Python application.
- Observability with LangSmith, LangFuse, or LangWatch integration.
- Enterprise-grade security and scalability with free DataStax Langflow cloud service.
- Customize workflows or create flows entirely just using Python.
- Ecosystem integrations as reusable components for any model, API or database.
⭐ Stay up-to-date
Star Langflow on GitHub to be instantly notified of new releases.
📦 Quickstart
- Install with pip (Python 3.10 or greater):
pip install langflow
- Cloud: DataStax Langflow is a hosted environment with zero setup. Sign up for a free account.
- Self-managed: Run Langflow in your environment. Install Langflow to run a local Langflow server, and then use the Quickstart guide to create and execute a flow.
- Hugging Face: Clone the space using this link to create a Langflow workspace.
👋 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.