Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/ac-rad/xdl-generation

CLAIRify: Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting

https://github.com/ac-rad/xdl-generation

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.6%) to scientific vocabulary

Keywords

language-model planning robot
Last synced: 5 months ago · JSON representation

Repository

CLAIRify: Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting

Basic Info
Statistics
  • Stars: 40
  • Watchers: 7
  • Forks: 3
  • Open Issues: 1
  • Releases: 0
Topics
language-model planning robot
Created about 3 years ago · Last pushed about 1 year ago
Metadata Files
Readme License

README.md

CLAIRify

Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting

  • Project website: https://ac-rad.github.io/clairify/

This repository contains - The source code for CLAIRify - Dataset (Chem-RnD and Chem-EDU) - CLAIRify web interface

Tutorial

Open In Colab

A tutorial on CLAIRify is provided as Jupyter Notebook.

Requirement

  • OpenAI Python Library

You need to set your OpenAI API key in OPENAI_API_KEY environment variable.

How to run

To generate a XDL protocol from a natural language description of an experiment, run the following:

python3 xdlgenerator/nlp2xdl.py --input_dir /path/to/experiment/dir

where /path/to/experiment/dir is a directory containing natural language experiments. Each experiment is assumed to be its own file in the dictory (e.g. expertiment1.txt, experiment2.txt). Running the script will automatically generate an output directory /path/to/experiment/dir_output. Each file in the new directory contains a XDL description.

Note: This repository contains the original code for the CLAIRify paper, which is incompatible with the current OpenAI API. Please check the develop branch for the updated version.

Owner

  • Name: RA^2D: Robotics-assisted Accelerated Discovery
  • Login: ac-rad
  • Kind: organization

We introduce novel robotic & AI solutions to accelerate science discoveries, sponsored by Acceleration Consortium.

GitHub Events

Total
  • Watch event: 7
  • Push event: 1
  • Fork event: 1
  • Create event: 1
Last Year
  • Watch event: 7
  • Push event: 1
  • Fork event: 1
  • Create event: 1

Issues and Pull Requests

Last synced: 5 months ago

All Time
  • Total issues: 1
  • Total pull requests: 10
  • Average time to close issues: 19 days
  • Average time to close pull requests: 27 days
  • Total issue authors: 1
  • Total pull request authors: 3
  • Average comments per issue: 1.0
  • Average comments per pull request: 0.4
  • Merged pull requests: 6
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • sgbaird (1)
Pull Request Authors
  • Whitney-JiZhi (5)
  • n-yoshikawa (3)
  • SebA-R (2)
Top Labels
Issue Labels
Pull Request Labels