Files
Cyrene_v2/.env.example
T
Aska 7c662511ba
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled
docs(embedding): EMBEDDING_API_URL 为完整 /v1/embeddings 端点(非 base);示例改 Qwen3-Embedding-0.6B
2026-09-06 11:34:41 +08:00

75 lines
2.7 KiB
Bash
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# ============================================
# Cyrene v2 配置文件 (.env)
# 复制为 .env 后修改。所有配置均从环境变量注入,代码内禁硬编码。
# 注意:.env 仅用于本地开发;生产用 systemd / env_file。
# 敏感信息(API Key / JWT_SECRET)一律不要写进日志。
# ============================================
# ---- 运行环境 ----
ENV=development
LOG_LEVEL=debug
TZ=Asia/Shanghai
# ---- 数据目录(未设置时按 OS 惯例解析) ----
DATA_DIR=./data
# ---- 服务器(网关,唯一对外端口) ----
HOST=0.0.0.0
PORT=8080
# ---- 认证 / 管理员 ----
# JWT_SECRET 必填,长度 >= 32;缺失或过短会在启动时 panic。
JWT_SECRET=change-me-to-a-random-string-at-least-32-characters
ADMIN_USERNAME=admin
ADMIN_PASSWORD=admin12345
REGISTRATION_ENABLED=true
# ---- 数据库 ----
# SQLite 为默认(单二进制、无需外部服务)。
DB_SQLITE_PATH=./data/cyrene.db
# PostgreSQL + pgvector 为可选增强;未配置时走 SQLite。相关向量能力在 M4 接入。
# DB_PG_URL=postgres://cyrene:cyrene_pass@localhost:5432/cyrene_ai?sslmode=disable
# ---- LLM 多供应商(LLM_PROVIDER 显式声明协议:openai / anthropic,默认 openai) ----
# Provider = openai:OpenAI 兼容 /chat/completions(含 OpenAI 兼容网关,也可经它承载 Anthropic 模型,但失去原生 tool input 对象优势)
LLM_PROVIDER=openai
LLM_BASE_URL=https://api.openai.com/v1
LLM_API_KEY=sk-xxxxx
LLM_MODEL=gpt-4o
LLM_FALLBACK_MODEL=gpt-4o-mini
# Provider = anthropic:Anthropic Messages /v1/messages(tool_use.input 为结构化对象,工具循环更稳)
# ANTHROPIC_BASE_URL=https://api.anthropic.com
# ANTHROPIC_API_KEY=sk-ant-xxxxx
# ANTHROPIC_MODEL=claude-sonnet-4-20250514
# ANTHROPIC_FALLBACK_MODEL=claude-haiku-3-5
# ---- 记忆嵌入(可选,真语义) ----
# 不配置时使用内置 n-gram / FTS 向量(dim=256)。配置后必须真实走语义路径。
# EMBEDDING_API_URL 是【完整 /embeddings 端点】(不是 base)——例:Ollama / llama.cpp = http://localhost:11434/v1/embeddings
# EMBEDDING_API_URL=http://localhost:11434/v1/embeddings
# EMBEDDING_API_KEY=
# EMBEDDING_MODEL=Qwen3-Embedding-0.6B # 推荐(Q8_0 ~639MB、dim=1024、ModelScope 国内可下)
# ---- IoT 设备提供者 ----
# mock = 模拟智能家居设备(开发测试用);none = 禁用 IoT。
IOT_PROVIDER=mock
# ---- 语音服务 ----
TTS_PROVIDER=edge-tts
STT_PROVIDER=dashscope
# DASHSCOPE_API_KEY=sk-xxxxx
# ---- 后台思考 ----
ENABLE_BACKGROUND_THINKING=true
THINK_INTERVAL_SEC=300
THINK_SILENCE_TIMEOUT_SEC=120
# ---- WebSocket ----
WS_MAX_CONNECTIONS=1000
SESSION_IDLE_TIMEOUT_MIN=30
# ---- 跨域白名单 ----
ALLOWED_ORIGINS=http://localhost:5173,http://localhost:3000