Langflow is a powerful tool for building and deploying AI-powered agents and workflows. http://www.langflow.org
Find a file
2023-03-28 19:17:26 -03:00
.devcontainer Create devcontainer.json 2023-02-09 22:11:42 -03:00
.github/workflows fix: replace poetry build with make build 2023-03-14 11:57:21 -03:00
docker_example fix: change default port 2023-03-17 16:47:27 -03:00
img fix: removing unwanted image 2023-03-14 11:23:39 -03:00
src feat: code validation, endpoint and tests 2023-03-28 19:17:26 -03:00
tests feat: code validation, endpoint and tests 2023-03-28 19:17:26 -03:00
.gitignore update gitIgnore 2023-03-13 18:35:01 -03:00
build_and_push refac: langflow_backend -> langflow 2023-03-17 09:50:02 -03:00
CODE_OF_CONDUCT.md Create CODE_OF_CONDUCT.md 2023-03-07 17:18:11 -03:00
CONTRIBUTING.md fix: improvements to local dev instructions 2023-03-20 11:58:37 -03:00
dev.Dockerfile fix: added gcc to dev.Dockerfile 2023-03-19 21:54:23 -03:00
docker-compose.yml feat: added script to setup proxy for local dev 2023-03-20 11:41:27 -03:00
Dockerfile refac: langflow_backend -> langflow 2023-03-17 09:50:02 -03:00
LICENSE docs: Add img, LICENSE 2023-02-23 20:29:53 -03:00
Makefile feat: added build option in dev command 2023-03-20 06:35:29 -03:00
poetry.lock feat: added rich in dev 2023-03-27 17:31:54 -03:00
pyproject.toml feat: added rich in dev 2023-03-27 17:31:54 -03:00
README.md Merge remote-tracking branch 'origin/export_improvement' into dev 2023-03-20 12:00:19 -03:00

⛓️ LangFlow

~ A User Interface For LangChain ~

GitHub Contributors GitHub Last Commit GitHub Issues GitHub Pull Requests Github License

LangFlow is a GUI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows with drag-and-drop components and a chat box.

📦 Installation

You can install LangFlow from pip:

pip install langflow

Next, run:

langflow

🎨 Creating Flows

Creating flows with LangFlow is easy. Simply drag sidebar components onto the canvas and connect them together to create your pipeline. LangFlow provides a range of LangChain components to choose from, including LLMs, prompt serializers, agents, and chains.

Explore by editing prompt parameters, link chains and agents, track an agent's thought process, and export your flow.

Once you're done, you can export your flow as a JSON file to use with LangChain. To do so, click the "Export" button in the top right corner of the canvas, then in Python, you can load the flow with:

from langflow import load_flow_from_json

flow = load_flow_from_json("path/to/flow.json")
# Now you can use it like any chain
flow("Hey, have you heard of LangFlow?")

👋 Contributing

We welcome contributions from developers of all levels to our open-source project on GitHub. If you'd like to contribute, please check our contributing guidelines and help make LangFlow more accessible.

Star History Chart

📄 License

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