dylifo

Streamlit demo using DSPy to summarize JSON from the Senzing SDK.

Set Up

This library uses poetry for package management, and first you need to install it. Then run:

poetry update

Also download/install Ollama https://ollama.com/ and pull the models you wish to use, for example:

ollama pull gpt-oss:20b

If you're not running locally, set the configuration parameter run_local false and be sure to set the OPENAI_API_KEY environment variable to your key.

Otherwise modify the config.toml configuration file to change models, adjust parameters, etc.

To prepare for the interactive demo, first pull the latest Docker container for Senzing:

docker pull senzing/serve-grpc:latest

Run Demo

Run the demo.py script with one of the JSON data files, for example:

poetry run python3 demo.py data/get.json

For an interactive UI based on Streamlit: first launch this container and have it running in the background:

docker run -it --publish 8261:8261 --rm senzing/serve-grpc

Then run:

poetry run streamlit run stream.py

Restart the container each time before re-running the Streamlit demo.

---

---

License and Copyright

Source code for Dylifo plus logo, documentation, and examples have an MIT license which is succinct and simplifies use in commercial applications.

All materials herein are Copyright © 2025 Senzing, Inc.

Kudos to @brianmacy, @jbutcher21, @docktermj, @cj2001, and the kind folks at GraphGeeks for their support.

Star History