v6ole/qiji
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 恢复 AI_MODEL 为 deepseek-v4-flash

Browse Source 
DeepSeek API 当前模型:
- deepseek-v4-flash / deepseek-v4-pro (2026-04-24 发布)
- deepseek-chat / deepseek-reasoner 是旧别名, 2026-07-24 废弃

.env.example 同步添加 DeepSeek 配置注释
This commit is contained in:
v6ole
2026-06-24 19:33:06 +08:00
parent d07311d5a5
commit 24c7aff093
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/.env.example
+1
View File
@@ -39,6 +39,7 @@ WECOM_ENCODING_AES_KEY=your-encoding-aes-key
# ── AI / LLM (OpenAI 兼容接口，用于周报摘要) ──
# 支持 OpenAI / DeepSeek / 通义千问 / 本地 Ollama 等
# DeepSeek: AI_API_URL=https://api.deepseek.com/v1/chat/completions AI_MODEL=deepseek-v4-flash
AI_API_URL=https://api.openai.com/v1/chat/completions
AI_API_KEY=sk-your-api-key
AI_MODEL=gpt-4o