Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
80ebe03d94* feat: add import utilities for LangFlow components - Introduced a new module `_importing.py` containing the `import_mod` function. - This function dynamically imports attributes from specified modules, enhancing modularity and flexibility in component initialization. - Comprehensive docstring added for clarity on usage and parameters. * feat: implement dynamic imports for LangFlow components - Added dynamic import functionality to various LangFlow components, allowing for lazy loading of attributes on access. - Introduced mapping in each component's to manage imports efficiently. - Enhanced error handling for import failures, providing clearer messages for missing attributes. - Updated method to reflect available attributes for better introspection and tab-completion support. - Comprehensive docstrings added to improve documentation and usability. * test: add comprehensive tests for dynamic imports and component accessibility - Introduced integration tests for dynamic import functionality, ensuring components are discoverable and instantiable post-refactor. - Added unit tests for the `_import_utils` module, validating the `import_mod` function's behavior and error handling. - Implemented tests to confirm all component modules are importable and maintain backward compatibility with existing import patterns. - Enhanced performance tests to measure lazy loading efficiency and memory usage during component access. - Ensured that all components have the required attributes for dynamic loading and that circular imports are prevented. * chore: update ruff pre-commit hook to version 0.12.2 in configuration file * refactor: update warning handling for dynamic imports - Moved the warning suppression for LangChainDeprecationWarning into the dynamic import context to ensure it only applies during the import process. - This change enhances clarity and maintains the original functionality while improving the robustness of the import mechanism. * test: enhance dynamic import integration tests for component attributes - Removed unnecessary import of AgentComponent and added assertions to verify essential attributes of OpenAIModelComponent, including display_name, description, icon, and inputs. - Ensured that each input field has the required attributes for better validation of component integrity during dynamic imports. * refactor: update import paths for Message class in conversation utilities - Changed the import of the Message class from langflow.field_typing to langflow.schema.message across multiple utility files, ensuring consistency and alignment with the updated module structure. - This refactor enhances code clarity and maintains compatibility with the latest schema definitions. * refactor: remove Vectara components from LangFlow - Deleted the Vectara components module from the codebase, streamlining the component structure. - This change helps to reduce complexity and maintain focus on core functionalities. * refactor: remove Vectara references from LangFlow component imports - Eliminated Vectara from both the import statements and dynamic imports mapping, streamlining the component structure. - This change contributes to reducing complexity and maintaining focus on core functionalities within the LangFlow framework. * [autofix.ci] apply automated fixes * fix: remove 'vectara' from __all__ in components module * refactor: improve error handling tests for dynamic imports * test: add tests for ModuleNotFoundError handling with None and special module names --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Edwin Jose <edwin.jose@datastax.com> |
||
|---|---|---|
| .cursor | ||
| .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 | ||
| codecov.yml | ||
| CONTRIBUTING.md | ||
| DEVELOPMENT.md | ||
| LICENSE | ||
| Makefile | ||
| Makefile.frontend | ||
| 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 built-in API and MCP servers that turn every workflow into a tool 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.
- Deploy as an MCP server and turn your flows into tools for MCP clients.
- 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.