# wxywb/history_rag

Repository: https://github.com/wxywb/history_rag
Canonical: https://ross.abutalabs.com/products/history_rag
Language: Python
License Family: other
Last push: 2024-08-07T07:31:19+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 69
- inputs: {"age_days": 978, "days_push": 756, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1038, forks 137 (observed 2026-08-28T04:03:19.670273+00:00)

## What it is
A Chinese history question-answering application built with RAG (retrieval-augmented generation) over a corpus of Chinese historical texts, using Milvus or Zilliz Cloud as the vector database and LlamaIndex with GPT-4 (or local/alternative LLMs). It includes a CLI and a Gradio web UI for building the knowledge base and querying it.

## Use cases
- ask questions about chinese history with cited sources
- build a rag pipeline over historical documents
- reduce llm hallucinations when answering history questions
- index classical chinese texts into a vector database
- demo retrieval-augmented generation with milvus and llamaindex
- chat with the twenty-four histories corpus

## When to choose
- you want a working RAG example over Chinese historical texts
- you need a reference implementation combining Milvus, LlamaIndex, and embeddings
- you want to reduce hallucinations by grounding LLM answers in source documents

## When to avoid
- you need a production-ready, licensed product (no license is specified)
- you need non-Chinese-language corpora out of the box
- you want a fully local solution without any LLM API key

## Facets
- artifact type: application
- maturity: active
- function: rag, vector-database, llm-inference, search-engine, chatbot
- domain: large-language-models
- platform: python, cli, self-hosted
- tags: milvus, llamaindex, chinese-history, question-answering, embeddings, gradio, zilliz, retrieval-augmented-generation, natural-language-processing, history, docker

## Member repositories
- wxywb/history_rag (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.670273+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:04:19.700988+00:00, confidence not recorded.
  - readme: https://github.com/wxywb/history_rag (fetched 2026-08-28T04:03:19.670273+00:00, sha 204c3068f377)
- Data as of 2026-08-30T08:39:29.467469+00:00.