PsyChat 是一款基于范例引导与Agentic RAG的智能 AI 心理咨询助手,基于高度匹配的Few-shot Learning与学习笔记,应用理性情绪行为疗法(REBT)帮助用户识别并调整非理性信念,缓解负面情绪。
PsyChat 是一个基于检索增强生成(RAG)技术的心理咨询 AI 助手。其核心目标是最大程度地蒸馏真实心理咨询师的说话方式——不只是复用知识库中的内容,而是主动分析、学习专业咨询师在共情、提问、引导节奏上的共性模式,并将其迁移到每一轮对话中。
系统运用理情行为疗法(REBT)理论框架,结合多阶段 Agent 工作流,帮助用户识别和调整非理性信念,缓解负面情绪。
graph TD
A[用户输入] --> B[Psychology Agent 决策层]
B --> C{RAG判断 + 主题分类\n单次LLM调用}
C -->|不需要检索| D[对话持续监控\n连续N轮无RAG?]
D -->|未超限| E[直接回答\nREBT提示词]
D -->|已超限| F[🚨 强制触发RAG]
C -->|需要检索| G[ReAct 查询优化循环\n最多3轮]
F --> G
G --> G1[Observation: 轻检索获取锚点 top3]
G1 --> G2[Thought+Action: 分析锚点质量]
G2 -->|FINISH| H[使用当前查询词]
G2 -->|REWRITE| G1
H --> I[多查询词向量检索\nChromaDB]
I --> J{找到相关文档?}
J -->|未找到| E
J -->|找到| K[上下文扩展\n纯I/O 无LLM]
K --> K1[通过chunk锚点\n回溯原始完整对话]
K1 --> L[咨询师话术分析\n带主题缓存]
L --> L1{缓存命中?}
L1 -->|命中| M[复用话术分析结果\n0次LLM]
L1 -->|未命中| L2[LLM分析4维度话术共性\n1次LLM]
L2 --> M
M --
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.
A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."
Ultimate LLM API Integration Cookbook 2026 for Cursor & AI Agents
Ultimate Multi-Agent OS for Autonomous AI NPCs 2026
PrivateAgent is an open-source Android automation agent built with Flutter. It utilizes the DeepSeek API and native Android Accessibility Services to interpret screen layouts and execute multi-step tasks across any installed application via natural language commands.
把一队分工 Agent 织成一条写小说的流水线,做成桌面客户端;写作指纹让它越写越像你(BYO DeepSeek key,纯本地)。
Workflows from the Neura Market marketplace related to this DeepSeek resource