mdcatapult Goto Github PK

ai-tool-experiments

Lots and lots of LLM agent and RAG demos using crew-ai, langchain & llama-index.

aurac-web-plugin

Browser plugin that can find, highlight and link to interesting life science things in web pages and PDFs.

bio-aurac

Coordinating repository allowing users to run the bio-aurac application.

biobert

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

coshh-api

Go API complementing the COSHH UI web app

coshh-ui

Angular web app for tracking the locations and expiry dates of laboratory chemicals

deepfigures-open

Companion code to the paper "Extracting Scientific Figures with Distantly Supervised Neural Networks" 🤖

doccano

Open source annotation tool for machine learning practitioners.

doclib-common

Common utilities and components used by the document library

document-to-text-converter

Part of the Document Library micro service ecosystem. Converts PDFs and other document types to raw text. Uses Apache Tika.

entity-recognition

Web service to recognise entities in html using a redis based dictionary

gitlab-ci-cd-versioning

Code versioning and other continuous integration helpers for Gitlab CI/CD pipelines

go-astilectron-bundler

Bundle your Astilectron app with ease

image-converter

Web service for cropping .ome.tiff files and combining .tiff files into a single pyramid .ome.tiff file

image-model-runner

imageio

Python library for reading and writing image data

jna-inchi

Wrapper to access InChI from Java

json-combiner

Utility to scan and parse files by format and convert them into json output that can be ingested by mongoimport, Currently supports parsing of json and xml formats

minerva-author

Tool to create images and configuration files for Minerva-Story

openseadragon

MDC clone of openseadragon

pdf-converter

Webservice to convert PDFs to HTML

pdffigures2

Given a scholarly PDF, extract figures, tables, captions, and section titles.

prefetch

A Scala based microservice that fetches and processes remote files. Part of the Document Library eco-system

py-config

Python lib that allows environment variables to override hocon style yaml or json config

py-mongo

Wrapper for pymongo to allow simple instantiation of MongoDB from configuration.

py-postgres

Methods to simplify configuring and connecting to Postgresql databases

py-queue

Module to abstract queues. Currently implements RabbitMQ.

py-util

Utility methods to help work with lists & dicts

rabbitmq-alert

Send notifications to the staff when predefined conditions are triggered

regex-entity-resolver

Scala web service for identifying terms within text and resolving them to a value