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 the 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 current version of EDSL at PyPI.

• Get the latest EDSL updates at GitHub.

• Create a Coop account.

• Join our Discord channel.

• Follow us on social media:

  • Twitter/X

  • LinkedIn

  • Blog

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.

Technical Setup

• Installation: Instructions for installing the EDSL package.

• Create a Coop to create, store and share content on the Expected Parrot server.

• API Keys: (Optional) Instructions for storing API keys for language models to use EDSL locally.

Getting Started

• Starter Tutorial: A tutorial to help you get started using EDSL.

Core Concepts

• Questions: Learn about different question types and applications.

• Scenarios: Explore how questions can be dynamically parameterized for tasks like data labeling.

• Surveys: Construct surveys and implement rules and conditions.

• Agents: Design and implement AI agents to respond to surveys.

• Language Models: Select language models to generate results.

Working with Results

• Results: Access built-in methods for analyzing and utilizing survey results as datasets.

• Caching LLM Calls: Learn about caching and sharing results.

• Exceptions & Debugging: Identify and handle exceptions in your survey design.

• Token limits: Manage token limits for language models.

Coop

Coop is a platform for creating, storing and sharing EDSL content and AI research.

• Coop: Learn how to create, store and share content at the Coop.

• Remote Caching: Use remote caching to automatically store survey results and API calls on the Expected Parrot server.

• Remote Inference: Use remote inference to run jobs on the Expected Parrot server.

• Notebooks: Instructions for sharing .ipynb files with other users at the Coop.

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

How-to Guides

Examples of special methods and use cases for EDSL, including:

• Data labeling, cleaning and analysis

• Cognitive testing

• Dynamic agent traits

• Creating new methods

Notebooks

Templates and example code for using EDSL 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.