# PeterH0323/Streamer-Sales

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭建后端🗝️、Docker-compose 打包部署🐋

Repository: https://github.com/PeterH0323/Streamer-Sales
Canonical: https://ross.abutalabs.com/products/streamer-sales
Homepage: https://openxlab.org.cn/apps/detail/HinGwenWong/Streamer-Sales
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: chat-application, internlm-chat-7b, internlm2, llm, chatbot, text-generation, chat, chatgpt, gpt, rag, tts, asr, digital-human, meta-human
Last push: 2025-03-08T00:38:06+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 10, release rhythm 28, longevity 62
- inputs: {"age_days": 880, "days_push": 544, "days_rel": 667, "gap_med": 51, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3761, forks 571 (observed 2026-08-28T04:08:17.926610+00:00)

## What it is
Streamer-Sales is a fine-tuned LLM-based AI sales livestreamer application that generates persuasive product commentary from product descriptions. It bundles LMDeploy-accelerated inference, RAG, TTS, ASR, digital-human video generation, an agent for web queries, a Vue frontend, and a FastAPI backend deployable via Docker Compose.

## Use cases
- generate sales pitch scripts for products with an LLM
- build an AI livestream shopping host with voice and digital human
- add new products to a chatbot without retraining via RAG
- deploy a full-stack LLM chat application with docker-compose
- speed up LLM inference with LMDeploy and KV cache
- let users talk to a sales assistant via speech recognition
- query real-time delivery info through an LLM agent

## When to choose
- you want an end-to-end e-commerce livestream AI host with voice and avatar
- you need a reference full-stack LLM app (Vue + FastAPI + PostgreSQL + Docker)
- you want to add products to a chatbot without fine-tuning using RAG

## When to avoid
- you need a lightweight library or SDK to embed in your own product
- you require a permissively licensed project (it is AGPL-3.0)
- you lack GPU resources for LLM inference and digital-human generation

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, rag, tts, speech-recognition, agent-framework, chatbot, web-framework, api-framework
- domain: large-language-models, chatbots, e-commerce, artificial-intelligence, web-development, speech-processing
- platform: python, self-hosted
- tags: digital-human, live-streaming, sales-pitch-generation, lmdeploy, internlm, fastapi, vue, docker-compose, asr, tts, docker, web-server, gpu, linux

## Member repositories
- PeterH0323/Streamer-Sales (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:17.926610+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 2026-08-29T18:28:53.139495+00:00, confidence not recorded.
  - readme: https://github.com/PeterH0323/Streamer-Sales (fetched 2026-08-28T04:08:17.926610+00:00, sha 534c3bb64505)
  - homepage: https://openxlab.org.cn/apps/detail/HinGwenWong/Streamer-Sales (fetched 2026-08-29T09:22:53.997109+00:00, sha 39ac88edc400)
- Data as of 2026-08-30T08:39:29.467469+00:00.