Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
* URL component improvement - JSON URL * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * ♻️ (url.py): refactor URLComponent class to simplify data_dict creation by using dictionary unpacking instead of manual key-value pairs * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * 📝 (url.py): improve formatting of info string for DropdownInput in URLComponent class ♻️ (url.py): refactor ensure_url method to simplify logic and improve readability 🐛 (url.py): fix error handling in URLComponent class for invalid JSON content * [autofix.ci] apply automated fixes * ✨ (url.py): Add BoolInput and StrInput to support new features in URLComponent 📝 (url.py): Update description in URLComponent to provide more detailed information about its functionality ♻️ (url.py): Refactor update_build_config method in URLComponent to dynamically update fields based on selected format 🐛 (url.py): Fix ensure_url method in URLComponent to ensure valid URLs are provided and handle exceptions properly 🐛 (url.py): Fix fetch_content method in URLComponent to handle cases where no valid URLs are provided and improve error handling 🐛 (url.py): Fix fetch_content_text method in URLComponent to correctly format and clean text output based on selected format and settings 🐛 (url.py): Fix as_dataframe method in URLComponent to return fetched content as a DataFrame object * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * ♻️ (url.py): remove unnecessary comments and improve code readability by removing redundant comments and adjusting code structure. * [autofix.ci] apply automated fixes * 📝 (url.py): improve readability by splitting long description and info strings into multiple lines 🐛 (url.py): handle cases where invalid URLs or JSON URLs are provided, and provide informative error messages 🐛 (url.py): handle cases where no valid URLs are provided and raise an error with a clear message * 🔧 (Blog Writer.json, Custom Component Maker.json, Graph Vector Store RAG.json): resolve merge conflicts in JSON files related to the 'format' field options to ensure consistency across starter projects. * [autofix.ci] apply automated fixes * 🐛 (url.py): fix validation of JSON content from URLs to ensure correct handling of JSON data ✨ (url.py): introduce async validation of JSON content from URLs using aiohttp to improve performance and reliability * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) * merge fix * ✅ (test_audio_file.wav): update test_audio_file.wav to fix binary file differences in the test asset * 🐛 (test_url_component.py): update error message format to improve clarity and consistency * update templates * 🐛 (test_database.py): fix error handling in test_read_flows_components_only_paginated to properly catch and log exceptions during test execution * 📝 (backend): Add noqa comments to files to ignore specific linting rule A005 🔧 (test_database.py): Remove duplicate import statement for sqlalchemy ♻️ (test_database.py): Refactor test_read_flows_components_only_paginated function for better readability and maintainability * 🐛 (test_database.py): fix test_read_flows_components_only_paginated to handle exceptions and provide more context in case of failure * 📝 (test_database.py): remove unnecessary comment to improve code readability and maintainability * 📝 (backend): Remove unnecessary noqa comments from __init__.py files 🔧 (test_database.py): Refactor test_read_flows_components_only_paginated function for better readability and maintainability * [autofix.ci] apply automated fixes --------- 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.RU.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.

