⛓️ LangFlow

~ A no-code flow builder for langchain ~

LangFlow is a no-code flow builder for LangChain, designed to provide a drag-and-drop UI, combining the capabilities of LangChain with reactFlow and a chat interface.

📦 Installation

You can install LangFlow from pip:

pip install langflow

Next, set the OPENAI_API_KEY environment variable using one of the following methods:

• Use the following command in your terminal: export OPENAI_API_KEY=your-api-key.
• In a Python script or Jupyter notebook, use the following code: import os; os.environ["OPENAI_API_KEY"] = "your-api-key".

🎨 Creating Flows

Creating flows with LangFlow is easy, thanks to its intuitive drag-and-drop interface. Simply drag components from the sidebar onto the canvas, and connect them together to create your custom NLP pipeline. LangFlow provides a range of pre-built components to choose from, including LLMs, prompt serializers, agents, and chains.

💻 Examples

LangFlow comes with a number of example flows to help you get started. These examples cover a range of use cases, from chatbots and question-answering systems to data augmentation and model comparison. You can use these examples as a starting point for your own custom flows, or modify them to suit your needs.

🧰 Components

LangFlow provides support for LangChain main components, including prompts, LLMs, document loaders, utils, chains, indexes, agents, and memory. For each module, we provide examples to get started, how-to guides, reference docs, and conceptual guides.

For more information on each component, please refer to the Modules section of the LangChain documentation.

🔧 Contributing

We welcome contributions to LangFlow! If you'd like to contribute, please follow our contributing guidelines. You can also get in touch with us via GitHub issues or our community forum.

📄 License

LangFlow is released under the MIT License. See the LICENSE file for details.