Skip to main content

Researching AI

Project description

Cybrex AI

Cybrex AI integrates several strategies to use AI for facilitating navigation through science:

  • IPFS is utilized to access the Standard Template Construct (STC).
  • STC provides the raw documents for Cybrex.
  • Embedding Model (OpenAI or Instructor-XL) constructs embeddings for these documents and Cybrex stores these embeddings locally in the Chroma database.
  • These embeddings are then used to filter relevant documents before they are sent to LLM (Open AI, WizardLM or any other one) for Q&A and summarization.

Install

You should have installed IPFS

pip install cybrex

Upon its initial launch, cybrex will create a ~/.cybrex directory containing a config.yaml file and a chroma directory. You can edit the config file to point to different IPFS addresses.

Usage

# Summarize a document
cybrex sum-doc --field doi --value 10.1155/2022/7138756

# Question a document
cybrex chat-doc --field doi --value 10.1155/2022/7138756 \
  --question "What is the antivirus effect of resveratrol?"
  
# Question science
cybrex chat-sci --question "What is the antivirus effect of resveratrol?"

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cybrex-1.0.9.tar.gz (6.6 kB view hashes)

Uploaded Source

Built Distribution

cybrex-1.0.9-py3-none-any.whl (7.2 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page