Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
768e6f02ba* Refactor `trace_name` property to use `_id` instead of `_vertex.id` for component identification * Handle missing session_id attribute in component and agent classes * Add SUPPORTED_VERSIONS constant for version tracking in tests * Add utility to download components from GitHub in integration tests * Rename TestComponent to ComponentForTesting to avoid conflict with pytest * test: enhance PromptComponent tests for version support Add parameterized testing for supported versions and a validation for the latest PromptComponent. This improves test coverage and ensures compatibility across different versions. * refactor: move build_component_instance_for_tests utility to integration utils * Make `from_template_and_variables` async for backwards compatibility and add sync version * Refactor `PromptComponent` to use `Message.from_template` method across starter projects JSON files. * add await to `from_template_and_variables` call * Add async test for message prompt serialization and update cache directory handling - Introduced `async` in `test_message_prompt_serialization` for asynchronous message creation. - Added `test_message_sync_prompt_serialization` for synchronous message testing. - Updated cache directory paths to "langflow_test" for test isolation. - Utilized `monkeypatch` to set environment variable for cache directory in `langflow_cache_dir` fixture. * Add fixture and existence check in test_schema_message.py - Use `langflow_cache_dir` fixture in `test_message_with_single_image`. - Add assertion to verify the existence of `second_image`. * Add base test class to ensure file names are defined for all supported versions * Remove default value for 'file_name' parameter in 'build_component_instance_for_tests' function * Enhance `TestPromptComponent` with version-specific file name handling and base class integration * Refactor test_prompt_component_versions to use FILE_NAMES_MAPPING directly * Add component version tests and base classes for testing with/without client * Simplify `build_component_instance_for_tests` by returning `cc_class` directly * Refactor `TestPromptComponent` to use `ComponentTestBaseWithClient` and remove version tests * Add assertion for LANGFLOW_CONFIG_DIR in test_message_with_multiple_images * Refactor: update method call to `from_template` in `langchain_hub.py` * Handle missing '_id' attribute in 'trace_name' method of custom_component.py * Optimize `get_and_cache_all_types_dict` call by removing unnecessary thread usage in test. |
||
|---|---|---|
| .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 | ||
| eslint.config.js | ||
| LICENSE | ||
| Makefile | ||
| pyproject.toml | ||
| README.ES.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 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.
⭐ 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.