EDSL: AI-Powered Research

Expected Parrot Domain-Specific Language (EDSL) is an open-source Python package for conducting AI-powered research.

EDSL is developed by Expected Parrot and available under the MIT License.

This page provides documentation, tutorials and demo notebooks for the EDSL package and Coop: a platform for creating, storing and sharing AI research. The contents are organized into key sections to help you get started:

Links

  Download the latest version of EDSL at PyPI.

  Get the latest EDSL updates at GitHub.

  Join our Discord channel to connect with other users and ask questions.

Introduction

Overview: An overview of the purpose, concepts and goals of the EDSL package.
Whitepaper: A whitepaper about the EDSL package (in progress).
Citation: How to cite the package in your work.

Getting Started

Starter Tutorial: A tutorial to help you get started using EDSL.
Installation: How to install the EDSL package.
API Keys: How to store API keys for language models.

Core Concepts

Questions: Learn about different question types and applications.
Scenarios: Explore how questions can be dynamically parameterized for tasks like data labeling.
Surveys: How to construct surveys and implement rules and conditions.
Agents: How to design and implement AI agents to respond to surveys.
Language Models: How to select language models to generate results.
Results: Explore built-in methods for analyzing and utilizing survey results.
data: Learn about caching and sharing results.
Exceptions: How to identify and handle exceptions in your survey design.
Token limits: How to manage token limits for language models.

Importing Data

Conjure: Automatically import other survey data into EDSL to: * Clean and analyze your data. * Create AI agents for respondents and conduct follow-on interviews. * Extend your results with new questions and surveys. * Store and share your data on the Coop.

Coop

Coop: A platform for creating, storing and sharing AI research.
Notebooks: Instructions for sharing .ipynb files with other users on the Coop.
Remote Caching: Learn how to cache your results and API calls on our server.
Remote Inference: Run your jobs on our server.

How-to Guides

Examples of special methods and use cases, such as data labeling tasks, cognitive testing, dynamic agent traits and creating new methods.

Notebooks

A variety of templates and examples for using the package to conduct different kinds of research. We’re happy to create a new notebook for your use case!

Developers

Information about additional functionality for developers.