China Biographical Database Project

biogref_CBDB

China Biographical Database project(CBDB) put the data.csv here for synchronizing CBDB data in biog_ref

cbdb-online-main-server

CBDB 在线系统主服务器

cbdb-online-query-app

cbdb_sqlite

The latest SQLite version of the China Biographical Database

crowdsource-webapp

Crowdsourcing System for Association Data 社會關係數據眾包系統

Index-Year-Calculater

The index year generator for China Biographical Database project

named-entities-for-premodern-chinese-history-research

Repo to generate and host named entities for premodern chinese history research

overview-of-DH-methods-for-Asian-studies

From CBDB Tsinghua team

processing-prompts-by-batch

This project provides a Python script to interact with multiple Large Language Models (LLMs) from various APIs. The script allows batch processing of prompts, splitting lengthy inputs into manageable chunks, and retrieving responses from the specified LLM.

sentence-segmentation-for-chinese-historical-texts

This is a pre-trained LSTM model. This model can help you to segment unpunctuated historical Chinese texts. 這是基於 LSTM 的預訓練模型。此模型可幫助您為漢語古文斷句。

cbdb-project/cbdb_sqlite

The latest SQLite version of the China Biographical Database

cbdb-project/cbdb-online-main-server

CBDB 在线系统主服务器

cbdb-project/named-entities-for-premodern-chinese-history-research

Repo to generate and host named entities for premodern chinese history research

cbdb-project/biogref_CBDB

China Biographical Database project(CBDB) put the data.csv here for synchronizing CBDB data in biog_ref

cbdb-project/haproxy_static

Build-in OpenSSL, libslz, PCRE2_JIT, lua 5.4, prometheus support; Use jemalloc (dynamic linked)

cbdb-project/processing-prompts-by-batch

This project provides a Python script to interact with multiple Large Language Models (LLMs) from various APIs. The script allows batch processing of prompts, splitting lengthy inputs into manageable chunks, and retrieving responses from the specified LLM.

cbdb-project/CBDB-disambiguation-automation

Using CBDB data points to match biography texts

cbdb-project/cbdb-data-summarization

Statistics on the number of characters and various datatypes in some dynasties of CBDB

cbdb-project/CHAR

Chinese character variant converter

cbdb-project/code-addr

cbdb-project/code-office

cbdb-project/create-new-books-for-cbdb

Create new books for CBDB MariaDB

cbdb-project/cbdb-swagger

cbdb swagger ui - openapi

cbdb-project/Jinshenlu-20240725-Han-persons-not-in-CBDB_Hongsu

cbdb-project/narrative-cbdb

Create narrative paragraphs by using CBDB sqlite database

cbdb-project/punc-by-llm

punctuate Chinese historical text by using large language model

cbdb-project/update-csa

cbdb-project/WIKI-mining

finding WIKI contents by a term list

cbdb-project/alumni-page

cbdb-project/cbdb-addr-book-script

Automatically get data from cbdb-addr-book(Google sheets) and show webpage on github.io

cbdb-project/cbdb-data-point-aggregation

cbdb-project/cbdb-llm-evaluator

cbdb-project/create-new-institutes-for-cbdb

create-new-institutes-for-cbdb

cbdb-project/create-new-office-titles-for-cbdb

create-new-office-titles-for-cbdb

cbdb-project/haystack-neo4j

cbdb-project/kinship_visualization

This repository aims to build a kinship visualization app

cbdb-project/OCR-Toolkit

A cute toolkit for OCR with GUI, including image preprocessing and text recognition. Works out of the box. 一只小小的OCR工具箱，包括图像预处理和文字识别等功能，开箱即用。

cbdb-project/tag_person_names_by_cluener

cbdb-project/Unlimited-Excel-Processing-through-GPT-3.5-API

This code processes an Excel file alongside a text file of the same name that provides a prompt for each row in the Excel file. It then sends these prompts to the ChatGPT 3.5 API. A batch (.bat) file is used to automatically close and restart the Python script whenever a API limit of 50 is reached.

cbdb-project/upload-files-to-huggingface

upload files and folders to huggingface