# baidu/AnyQ

FAQ-based Question Answering System

Repository: https://github.com/baidu/AnyQ
Canonical: https://ross.abutalabs.com/products/anyq
Language: C++
License: Apache-2.0
License Family: permissive
Topics: qa-system, semantic-matching, faq, faqbot, faq-question-answering-system, faq-system, question-answering, dialogue-systems, dialogue
Last push: 2020-11-28T12:32:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2984, "days_push": 2104, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2575, forks 657 (observed 2026-08-28T04:07:02.172103+00:00)

## What it is
AnyQ is Baidu's open-source FAQ-based question answering framework with a configurable, plugin-based architecture covering question analysis, retrieval, matching, and re-ranking. It includes SimNet, a semantic text matching framework with models like BOW, CNN, RNN, MM-DNN, MatchPyramid, MV-LSTM, and K-NRM implemented in PaddlePaddle and TensorFlow.

## Use cases
- build a faq chatbot for customer support
- match user questions to predefined answers semantically
- serve question answering over an http api
- train semantic matching models for chinese text
- customize retrieval and ranking plugins for a qa system

## When to choose
- you need a self-hosted FAQ question answering system with Chinese language support
- you want a plugin-based QA pipeline you can customize with custom retrieval or matching logic
- you need semantic matching models integrated into a retrieval system

## When to avoid
- you need a modern, actively maintained project with recent updates
- you want a managed cloud QA service rather than self-hosted C++ deployment
- your use case is English-only open-domain question answering

## Facets
- artifact type: framework
- maturity: maintenance
- function: nlp, search-engine, machine-learning, http-server, plugin-system
- domain: chatbots, machine-learning
- platform: windows, cpp, python
- tags: faq, question-answering, semantic-matching, simnet, chatbot, retrieval, chinese-nlp, solr, paddlepaddle, natural-language-processing, search, linux, macos, docker

## Member repositories
- baidu/AnyQ (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:02.172103+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 2026-08-30T02:22:44.333415+00:00, confidence not recorded.
  - readme: https://github.com/baidu/AnyQ (fetched 2026-08-28T04:07:02.172103+00:00, sha 83ef3a282fc6)
- Data as of 2026-08-30T08:39:29.467469+00:00.