# zhaoyingjun/chatbot

Chatbot继续沿着LLM前进，近期更新小参数量SLM的和训练脚本，支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。

Repository: https://github.com/zhaoyingjun/chatbot
Canonical: https://ross.abutalabs.com/products/zhaoyingjun-chatbot
Language: Python
License Family: other
Topics: chatbot, ai, python, seq2seq-chatbot, pytorch, agentic-ai, aiagents, shopping, slm
Last push: 2025-10-09T11:20:37+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 46, release rhythm 35, longevity 100
- inputs: {"age_days": 3159, "days_push": 328, "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 3581, forks 1010 (observed 2026-08-28T04:08:10.966122+00:00)

## What it is
A Chinese chatbot project that trains conversational models (Seq2Seq and GPT-style, including small SLM variants) on custom corpora with local training scripts, plus a ChatAgent/Shopping Agent component. The Shopping Agent uses browser automation, screenshots, and LLM analysis to extract order data from web backends and export it to Excel via a FastAPI backend and Streamlit frontend.

## Use cases
- train a chatbot on my own chinese conversation corpus
- build a shopping agent that extracts orders from a web dashboard
- scrape order pages with screenshots and export to excel
- fine-tune a small language model locally
- automate order data extraction from a backend that has no export
- learn seq2seq and GPT chatbot implementations
- build an AI agent that controls a browser via natural language

## When to choose
- you want a trainable Chinese chatbot with Seq2Seq and GPT variants
- you need to extract order data from web pages that cannot be exported directly
- you want example agent implementations with real business scenarios
- you want to experiment with small language model training scripts locally

## When to avoid
- you need a production-grade enterprise chatbot platform
- you require a licensed, commercially supported product (no license is provided)
- you need a non-Chinese-language chatbot out of the box
- you want a no-code solution without Python setup

## Facets
- artifact type: application
- maturity: active
- function: chatbot, agent-framework, machine-learning, llm-training, web-scraping, ocr, data-science
- domain: artificial-intelligence, chatbots, large-language-models, machine-learning, e-commerce
- platform: python, cross-platform
- tags: shopping-agent, seq2seq, gpt, mindspore, pytorch, browser-automation, selenium, streamlit, fastapi, chinese-chatbot, slm, order-extraction, excel-export, ai-agents, automation, web-server, docker

## Member repositories
- zhaoyingjun/chatbot (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:10.966122+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 2026-08-29T18:33:58.923300+00:00, confidence not recorded.
  - readme: https://github.com/zhaoyingjun/chatbot (fetched 2026-08-28T04:08:10.966122+00:00, sha 22f90f27240d)
- Data as of 2026-08-30T08:39:29.467469+00:00.