TheD0ubleC/StickerSelector
StickerSelector 是一个基于语义向量匹配的表情包选择系统，用于让 AI 在聊天中发送真正符合语境的表情包。 与传统依赖关键词或规则的方案不同，StickerSelector 会将 AI 生成的“表情包意图描述”与本地表情包进行语义匹配，从而选出在当前语境下最自然、最像真人会使用的表情。 适用于 AI 聊天机器人、QQ或微信的自动聊天、AI 女友等需要“拟人化表达”的场景。
This tool helps AI chat applications select the perfect emoji or sticker to send, making conversations feel more natural and human-like. You give it a description of the AI's intended emotional expression, and it finds the most contextually relevant sticker from your collection. It's designed for anyone building or managing AI chatbots, automatic chat systems (like for QQ or WeChat), or AI companion applications.
Use this if your AI needs to go beyond basic text and incorporate expressive, contextually appropriate stickers and emojis into conversations to sound more human.
Not ideal if your AI communication is strictly text-based or doesn't require emotional nuance and expressive visual elements.
Stars
22
Forks
3
Language
Python
License
GPL-3.0
Category
Last pushed
Jan 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/TheD0ubleC/StickerSelector"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unum-cloud/UForm
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts,...
rom1504/clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
mazzzystar/Queryable
Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.
s-emanuilov/litepali
LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing,...
slavabarkov/tidy
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized...