* feat: Add helper text for Astra DB embedding generation provider * feat: Add helper text support for dropdown and parameter components * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * Update astradb.py * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * feat: Add org_id to excluded metadata keys in dropdown component * fix: Update Astra DB component UI and starter project configuration - Improved AstraDB component's embedding provider link with better accessibility attributes - Updated Vector Store RAG starter project JSON with formatted configuration - Refined UI text and link presentation for better user experience * Remove providers that arent configured * feat: Add required field indicator to node parameters - Implemented visual indicator (*) for required node parameters - Updated custom parameter title rendering to show required status - Enhanced UI to provide clearer input requirements * Revert "Merge branch 'lfoss-683-1' of https://github.com/langflow-ai/langflow into lfoss-683-1" This reverts commit 2eb0fcb4d3d347de0df1f021f761ea63e882b757, reversing changes made to 9ea44aca477e8a418ef82722da4b1e0fc2afa2e1. * [autofix.ci] apply automated fixes * Add changes back * Fix some comments * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes * Update astradb.py * feat: Add dynamic disabled state for node dialog and int component * feat: Add dynamic placeholder for node dialog input * [autofix.ci] apply automated fixes * feat: Enhance IntComponent with disabled state styling and stepper interactions * Fix some db creation params * Update astradb.py * fix: Resolve node dialog input value handling in TypeScript * Update astradb.py * feat: Add required field validation to node dialog submission * Update astradb.py * [autofix.ci] apply automated fixes * Update astradb.py * Clean up functions and add read only flag * feat: Add readonly support to IntComponent and improve node dialog validation * fix: Improve dropdown component disabled and empty options handling * console.log removed * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * Read only field and cleanup * Astra DB selector updates * [autofix.ci] apply automated fixes * fix: Improve dropdown component disabled state handling * Fix value of region in create db * [autofix.ci] apply automated fixes * Remove database icon from component * fix: Conditionally render dropdown option icons * Don't show Nvidia if not available * [autofix.ci] apply automated fixes * Exceptions unless pending mean, skip * feat: Enhance AstraDBVectorStoreComponent with HTML sanitization - Added DOMPurify for sanitizing HTML input in the convertStringToHTML function. - Introduced a new sanitizeHTML function to ensure safe rendering of HTML strings. * fix: Correct field key usage in NodeDialog and refactor disabled class name in IntComponent - Updated NodeDialogComponent to use fieldKey instead of underscore for better clarity in mapping field values. - Refactored IntComponent to replace the getDisabledClassName function with a constant for the disabled input class, improving readability. * ✨ (playground.spec.ts): Refactor drag and drop functionality to use hover and click for better interaction 🔧 (chatInputOutput.spec.ts): Update drag and drop functionality to use target position for more precise placement 🔧 (chatInputOutputUser-shard-1.spec.ts): Simplify connecting elements by replacing hover and mouse actions with click for better user experience * 🐛 (generalBugs-prompt.spec.ts): fix issue with selecting the last element with getByTestId to ensure correct element is clicked and tested * ✅ (chatInputOutputUser-shard-1.spec.ts): add 600ms timeout to wait for elements to be interactable before proceeding with the test steps --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Eric Hare <ericrhare@gmail.com> Co-authored-by: cristhianzl <cristhian.lousa@gmail.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.md | ||
| render.yaml | ||
| uv.lock | ||
Langflow is a powerful tool for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and a built-in API server that turns every agent into an API endpoint 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 to get started quickly and iterate.
- Access to Code so developers can tweak any component using Python.
- Playground to immediately test and iterate on their flows with step-by-step control.
- Multi-agent orchestration and conversation management and retrieval.
- Deploy as an API or export as JSON for Python apps.
- Observability with LangSmith, LangFuse and other integrations.
- Enterprise-ready security and scalability.
⚡️ Quickstart
Langflow works with Python 3.10 to 3.13.
Install with uv (recommended)
uv pip install langflow
Install with pip
pip install langflow
📦 Deployment
Self-managed
Langflow is completely open source and you can deploy it to all major deployment clouds. Follow this guide to learn how to use Docker to deploy Langflow.
Fully-managed by DataStax
DataStax Langflow is a full-managed environment with zero setup. Developers can sign up for a free account to get started.
⭐ 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.