The DSP framework provides a programming abstraction for building grounded AI systems. In a few lines of code, a DSP program expresses rich interactions between retrieval models (RMs) and language models (LMs) to tackle difficult knowledge-intensive NLP tasks (e.g., complex question answering or conversational search).
DSP programs don't involve hard-coding few-shot prompts for LMs. Instead, we view "prompt engineering" akin to hyperparameter tuning in traditional ML. That is, prompt engineering is only a final (and relatively minor) step after building up an effective architecture and getting its modules to work together. DSP provides a high-level abstraction for building these architectures — with LMs and search. And it gets the modules working together on your behalf (e.g., it annotates few-shot demonstrations for LM calls within your arbitrary pipeline automatically).
Once you're happy with things, DSP can compile your DSP program into a tiny LM that's a lot cheaper to work with.
pip install dsp-ml
Our intro notebook provides examples of five "multi-hop" question answering programs of increasing complexity written in DSP.
You can open the intro notebook in Google Colab. You don't even need an API key to get started with it.
Once you go through the notebook, you'll be ready to create your own DSP pipelines!
Our compiler notebook introduces the new experimental compiler, which can optimize DSP programs automatically for (much) cheaper execution.
You can open the compiler notebook in Google Colab. You don't even need an API key to get started with it.
You can get an overview via our Twitter threads:
- Introducing DSP (Jan 24, 2023)
- Releasing the DSP Compiler (v0.1) (Feb 13, 2023)
And read more in the academic paper:
If you use DSP in a research paper, please cite our work as follows:
@article{khattab2022demonstrate,
title={Demonstrate-Search-Predict: Composing Retrieval and Language Models for Knowledge-Intensive {NLP}},
author={Khattab, Omar and Santhanam, Keshav and Li, Xiang Lisa and Hall, David and Liang, Percy and Potts, Christopher and Zaharia, Matei},
journal={arXiv preprint arXiv:2212.14024},
year={2022}
}