ericwyuan/sentinel-home-ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[架构重构] 移除本地Ollama融合，云端直出JSON直存DB，Q&A三模型降级

Browse Source 
1. 视频摘要链路：云端VLM直出结构化JSON → Edge format_cloud_result格式化校验 → 直存NAS DB（移除run_text_fusion本地融合）
2. 智能问答链路：Gemini→NVIDIA→Ollama降级，新增chat()纯文本问答方法
3. 适配器重构：base/gemini/nvidia/ollama adapter新增chat()；gemini多图单请求结构化JSON；nvidia逐帧调用聚合
4. 端点变更：/api/edge/chat → /api/edge/chat/ask，调orchestrator.run_qa()
5. chat_handler改经Edge Q&A编排，不再直连Ollama
6. 配置更新：ollama_url → qa_url，Ollama role注释改为Q&A兜底
7. README同步更新架构描述、拓扑图、时序图、模块表
This commit is contained in:
ericwyuan
2026-08-20 10:21:09 +08:00
parent 486eee4feb
commit babf5b09a9
10 changed files with 503 additions and 267 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fam-core/config/config.yaml
View File

@@ -37,6 +37,6 @@ video_server:
video_dir: "/volume1/surveillance"
chat_handler:
ollama_url: "http://129.146.203.203:5000/api/edge/chat"
model_name: "llava-phi3"
# 智能问答统一走 FAM-Edge 编排端点（Gemini → NVIDIA → 本地 Ollama 兜底）
qa_url: "http://129.146.203.203:5000/api/edge/chat/ask"
timeout: 120