Flowco
by Emery Berger, Stephen Freund, Eunice Jun, Brooke Simon (ordered alphabetically)
Flowco is a system for authoring data analysis workflows with LLM assistance at every stage of the process. Flowco employs a dataflow programming model that serves as a foundation for reliable LLM-centric programming.
For technical details, see our arXiv paper, Flowco: Rethinking Data Analysis in the Age of LLMs.
Watch Flowco in Action!
| Demo Video | Tutorial Video |
|---|---|
Example Diagrams
| Exploratory Data Analysis | Multiverse Analysis | Logistic Regression |
|---|---|---|
Web Service
You can try Flowco on the web here.
Local Installation
Configuration
- Use a conda virtual environment or some other virtual environment.
- Use Python 3.11+.
- Ensure
dotis on your path.
OpenAI API Key
Installing
From Pypi [Recommended]
With pip:
pip3 install flowco
From Source
Or clone the repo and install as an editable package.
pip3 install -e .
This installs a bunch of normal packages, a custom component for Streamlit, and then Flowco as an editable package that you can run locally (rather than as the web service).
Running
On the command line, run flowco, passing it the directory in which to store its files. That directory
should already exist:
mkdir /tmp/example
flowco /tmp/example
The first time you run, it may take 15-20 seconds to bring up the web page. It should launch more quickly after that.
Flowco will intially open a welcome.flowco graph. Follow the instructions in the right-hand panel to get started. Then proceed through the numbered tutorials to experiment with additional features.
Use -v to turn on logging.
Metadata
Release files for flowco 0.76.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| flowco-0.76.0.tar.gz | 32.0 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| flowco-0.76.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 45.7 MB
Release files / flowco-0.76.0.tar.gz
| Download URL | flowco-0.76.0.tar.gz |
|---|---|
| Size | 32.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
11343f88e96a5e264aa9af4a755199b3c0c94543e763c0a024ae0b04397c6664
|
|
BLAKE2b-256 checksum How to use checksums |
a96b5d5f5ee05056d967a3806a5030d28d27ce6cf240afb432a4e6f16e8d9078
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / flowco-0.76.0-py3-none-any.whl
| Download URL | flowco-0.76.0-py3-none-any.whl |
|---|---|
| Size | 13.6 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
934be37d3ff558e95584ff6915921c35537277be1a3c76193c957a935012ed98
|
|
BLAKE2b-256 checksum How to use checksums |
f689ff39b5183755cd3aebe782b7bbbec8746e80e6dd806ef61f16d5f31f74c3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|