Skip to main content

SciBot

Author : Kevin G. Yager

SciBot is a simple demo of building a domain-specific chatbot for science, using a Large Language Model (LLM) such as OpenAI's GPT. The system uses document embeddings, whereby the bot retrieves document chunks that are relevant to a user query.

More complete technical details can be found in the corresponding preprint: https://arxiv.org/abs/2306.10067

Or the published paper: https://doi.org/10.1039/D3DD00112A

You can cite this work as:

@Article{yager2023domainspecific,
    author ="Yager, Kevin G.",
    title  ="Domain-specific chatbots for science using embeddings",
    journal  ="Digital Discovery",
    year  ="2023",
    volume  ="2",
    issue  ="6",
    pages  ="1850-1861",
    publisher  ="RSC",
    doi  ="10.1039/D3DD00112A",
    url  ="http://dx.doi.org/10.1039/D3DD00112A",
}

Metadata

Release files for SciToolsSciBot 1.0.8

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for SciToolsSciBot 1.0.8
File Size Uploaded
SciToolsSciBot-1.0.8.tar.gz 48.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for SciToolsSciBot 1.0.8
File Interpreter ABI Platform
SciToolsSciBot-1.0.8-py3-none-any.whl Python 3 none any Details

Total release size: 86.3 kB

Release files / SciToolsSciBot-1.0.8.tar.gz

Download URL SciToolsSciBot-1.0.8.tar.gz
Size 48.5 kB
Tags Source
SHA-256 checksum
How to use checksums
db3349459e28905ec20b73aea2220d5f9639983b0cbafcc2fad2ed507bf0d3f9
BLAKE2b-256 checksum
How to use checksums
e823c7b9cd11eb7400dac85c76034c98d2876b685dfd7b4459ded2d032f5102c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.1.1 pkginfo/1.4.2 requests/2.31.0 setuptools/45.2.0 requests-toolbelt/0.8.0 tqdm/4.66.1 CPython/3.8.10

Release files / SciToolsSciBot-1.0.8-py3-none-any.whl

Download URL SciToolsSciBot-1.0.8-py3-none-any.whl
Size 37.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8cc215373e3f3c84b77e2d3b301372aac3d8bd8dfe27c3824e0f995fa5422980
BLAKE2b-256 checksum
How to use checksums
73308e0058f775e24e27b58281649debb9f1a357e7c621f1fa952ebc34ee347a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.1.1 pkginfo/1.4.2 requests/2.31.0 setuptools/45.2.0 requests-toolbelt/0.8.0 tqdm/4.66.1 CPython/3.8.10

Release history Release notifications | RSS feed

This release

1.0.8 This release

2 release files

1.0.5

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page