Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
9c23759c7d* refactor: turn sorting methods into functions in a separate module - Added `layered_topological_sort` function to perform layered topological sorting of graph vertices, accommodating cycles and input vertex checks. - Introduced `refine_layers` function to ensure proper dependency ordering among vertices. - Implemented helper functions for sorting layers by dependency and filtering vertices based on predecessors. - Enhanced utility functions to support better graph traversal and layer management. This update improves the graph processing capabilities, allowing for more efficient handling of complex graph structures. * feat(tests): enhance graph utility tests with cycle detection and sorting functionality - Added a new fixture `graph_with_loop` to simulate a graph containing cycles for testing purposes. - Improved the `test_large_graph_efficiency` to validate cycle detection in large graphs. - Introduced multiple tests for sorting vertices in graphs with cycles, ensuring correct order and handling of input vertices. - Enhanced assertions to provide clearer error messages for failed tests, improving debugging experience. These changes strengthen the testing framework for graph utilities, ensuring robust handling of complex graph structures. * refactor(graph): remove unused parent_node_map from Graph class initialization - Eliminated the `parent_node_map` parameter from the Graph class constructor, streamlining the graph initialization process. - This change enhances code clarity and reduces unnecessary complexity in graph management. This update contributes to cleaner and more maintainable graph-related code. * refactor(graph): optimize dependency sorting and vertex filtering - Improved the `_max_dependency_index` function by utilizing `index_map.get()` for cleaner code and better handling of missing successors. - Enhanced the `_sort_single_layer_by_dependency` function with a caching mechanism to avoid redundant calculations, improving performance during vertex sorting. - Updated `filter_vertices_up_to_vertex` to use a set for `vertices_ids`, optimizing membership checks and enhancing efficiency in vertex filtering. These changes contribute to more efficient graph processing and improved code readability. * chore: remove unused 'parent_node_map' parameter * [autofix.ci] apply automated fixes * fix: replace old method call with a new func * test: enhance assertions for file existence in webhook tests * refactor(graph): enhance component ID retrieval and chat input sorting - Updated `find_start_component_id` to accept an optional `is_webhook` parameter, allowing for dynamic priority input selection based on the flow type. - Improved `sort_chat_inputs_first` to handle chat input positioning more efficiently, ensuring only one chat input exists and adjusting its position within the layers as needed. - These changes enhance the flexibility and efficiency of graph processing, particularly for webhook flows. * test(graph): update assertions in sort_chat_inputs_first test for accuracy - Modified assertions in the `test_chat_inputs_at_start` function to reflect the correct expected output of the `sort_chat_inputs_first` utility. - Adjusted the expected length and order of the result to ensure accurate validation of chat input sorting functionality. These changes enhance the reliability of the test suite for graph utilities, ensuring that the sorting logic is correctly validated. * test(chat): update assertion in consume_and_assert_stream for accurate ID validation - Modified the assertion in the `consume_and_assert_stream` function to include an additional expected ID, ensuring the test accurately reflects the current output of the chat endpoint. - This change enhances the reliability of the test suite by validating the correct behavior of the chat input sorting functionality. * test(endpoints): update assertion in test_get_vertices for accurate ID validation - Modified the assertion in the `test_get_vertices` function to include an additional expected ID, "Webhook", alongside "ChatInput". - This change ensures the test accurately reflects the current output of the endpoint, enhancing the reliability of the test suite for endpoint functionality. --------- Co-authored-by: italojohnny <italojohnnydosanjos@gmail.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> |
||
|---|---|---|
| .devcontainer | ||
| .github | ||
| .vscode | ||
| deploy | ||
| docker | ||
| docker_example | ||
| docs | ||
| scripts | ||
| src | ||
| test-results | ||
| .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.ES.md | ||
| README.FR.md | ||
| README.ja.md | ||
| README.KR.md | ||
| README.md | ||
| README.PT.md | ||
| README.zh_CN.md | ||
| render.yaml | ||
| uv.lock | ||
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.
📦 Quickstart
- Install with uv (recommended) (Python 3.10 to 3.12):
uv pip install langflow
- Install with pip (Python 3.10 to 3.12):
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.
⭐ 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.