mirror of
https://github.com/langflow-ai/langflow.git
synced 2026-07-25 06:34:24 +08:00
bee466e52b
* Refactor YfinanceToolComponent to inherit from LCToolComponent and remove unused outputs * Refactor `PythonREPLToolComponent` to use new input configuration and update method signatures * Add functions to handle dict values in ATTR_FUNC_MAPPING for '_outputs_maps' and '_inputs' * Handle '_outputs_maps' argument in frontend node creation * Add unit test for custom component subclassing from LCToolComponent * Add input and output handling to PythonREPLToolComponent - Introduced `input_value` to `inputs` for capturing user input. - Added `outputs` to define the output structure, including `api_run_model` and `tool` for backward compatibility. - Implemented `run_model` method to execute the tool and return results as `Data`. * Add input and output handling to YfinanceToolComponent - Introduced `MessageTextInput` for user queries. - Added `Output` definitions for `api_run_model` and `tool` methods. - Implemented `run_model` method to execute tool with user input. * Add input and output definitions to YfinanceTool for better data handling * Update error message to use display_name instead of vertex_type in edge validation * Add unit test for YfinanceToolComponent template output validation * Refactor tool components to include 'Data' output and update input types - Added 'Data' output type to 'Agent Flow', 'Sequential Agent', and 'Complex Agent' starter projects. - Updated input types to use 'MessageTextInput' and 'MultiselectInput' for better input handling. - Refactored code to align with new input and output structures, ensuring backward compatibility. * Add unit test for PythonREPLToolComponent template validation * test: disblable test --------- Co-authored-by: italojohnny <italojohnnydosanjos@gmail.com>
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.