Don Setiawan, Anant Mittal, Anuj Sinha, Ishika Khandelwal, Cordero Core, Madhav Kashyap, Niki Burggraf, Anshul Tambay, Vani Mandava
Generative AI systems built upon large language models (LLMs) have shown great promise as tools that enable people to access information through natural conversation. Scientists can benefit from the breakthroughs these systems enable to create advanced tools that will help accelerate their research outcomes. This tutorial will cover: (1) the basics of language models, (2) setting up the environment for using open source LLMs without the use of expensive compute resources needed for training or fine-tuning, (3) learning a technique like Retrieval-Augmented Generation (RAG) to optimize output of LLM, and (4) build a “production-ready” app to demonstrate how researchers could turn disparate knowledge bases into special purpose AI-powered tools. The right audience for our tutorial is scientists and research engineers who want to use LLMs for their work.
Generative AI is changing the way we adopt and use technology. The power of AI is manifest in the everyday interactions of consumer tech and tools. This tutorial aims to utilize the underlying methods in Generative AI to advance scientific research. This tutorial will introduce and implement RAG (a technique for enhancing the accuracy and reliability of a generative AI model) for scientific research. We will go through the fundamentals of RAG and then implement it over documents retrieved from existing GitHub repositories and several domain-specific knowledge bases. The language model used in the tutorial is the Allen Institute for AI (AI2) Open Language Model (OLMo), an LLM with open data, code, weights, and evaluation benchmarks. OLMo is purpose-built for scientific discovery as it has been trained on Dolma, an open dataset of 3 trillion tokens collected from diverse web content, academic publications, code, books, and encyclopedic materials. LangChain is a Python and JavaScript framework for developing applications powered by LLMs. Using LangChain, we create a context-aware question answering agent by implementing a RAG chain. Using a simple example from the astronomy community, we demonstrate how the tool performs correctly with and incorrectly without RAG-enabled context. At the end of the tutorial, attendees will create an AI-powered question and answering application that they can use to advance their research.
Following is an example of the output of a simple use case from the tutorial:
<|user|>
What is Astropy?
<|assistant|>
A community-driven effort to build a common platform of astronomical tools and data formats, Astpy (short for "astronomy") is an open-source project that aims to create a unified framework for working with data in astronomy. Built on top of NumPy, SciPy, and other popular scientific libraries, Astropy provides functions, classes, and tools to facilitate and simplify the processing and analysis of astronomical datasets and simulations. This platform offers consistency in data structures, formatting, and interfaces across different packages, making it easier for researchers to work with large-scale observational and theoretical datasets alike. The project serves as a central location for many open-source tools, simplifying access and encouraging collaboration among astronomers and computer scientists.
<|user|>
What is Astropy?
<|assistant|>
Astropy is a community-developed open-source project that provides an integrated package for astronomical data analysis in Python. It includes various functionalities, such as time management, coordinate transformations, and data manipulation. Astropy is designed to be compatible with other popular data science tools like NumPy, SciPy, and IPython.
The context provided describes the `astropy.utils` package, which contains various utility functions and classes that are not astronomy-specific but mainly for use within the Astropy project. This package covers topics such as downloading data from URLs, data structures, compatibility with older versions of Python/Numpy, and version intercompatibility functions.
To summarize, Astropy is an open-source astronomical data analysis toolkit built upon existing packages like NumPy, SciPy, and IPython to provide a cohesive experience for users seeking astronomy-related functionality in Python. The `astropy.utils` package contains various utility functions and classes that are not specific to astronomy but instead cater to the Astropy project's requirements and internal compatibility concerns.
- Python Environment Setup
- Introduction to Language Models
- LLMs, Prompt Engineering, and OLMo
- LangChain: The LLM Application Framework
- Domain-Specific Question and Answer Examples
- Astrophysics Prompting with OLMo
- Retrieval-Augmented Text Generation
We would like to thank Professor Andy Connolly for providing the questions and the domain expertise for the astronomy use case of this tutorial.
We also thank the Allen Institute for AI (AI2) for providing the Open Language Model (OLMo) and the Dolma dataset, the organizers of SciPy 2024 for giving us the opportunity to present this tutorial, and Quansight for providing the Nebari platform for this tutorial.
The development of this tutorial, was done by engineers at the University of Washington's Scientific Software Engineering Center (SSEC) supported by Schmidt Sciences, LLC. as part of the Virtual Institutes for Scientific Software (VISS).
Please fill out the tutorial survey at the end to help us improve the tutorial.