fix: add mem0-ui container and init container patch for sentence_transformers

AI/mem0/deploy.md

@@ -273,23 +273,98 @@ mem0 server 启动时读取 `DASHBOARD_URL`，设置 `allow_origins=[DASHBOARD_U
 
 确保 `DASHBOARD_URL` 设为 dashboard 的外部访问地址（与 `NEXT_PUBLIC_API_URL` 的域名部分一致）。
 
-### sentence_transformers 导入错误
+## sentence_transformers 导入错误（永久修复）
 
 mem0 的 `huggingface.py` 在文件顶部执行 `from sentence_transformers import SentenceTransformer`，即使走 `huggingface_base_url` 路径（用 OpenAI 客户端调用 TEI，不需要本地模型）也会尝试加载，造成 `ModuleNotFoundError`。
 
-**临时修复**（容器内，重启会丢）：
+通过 init container + emptyDir 挂载实现持久修复，pod recreate 不丢失：
 
-```bash
+```yaml
-sed -i 's/from sentence_transformers import SentenceTransformer/# from sentence_transformers import SentenceTransformer/' /usr/local/lib/python3.12/site-packages/mem0/embeddings/huggingface.py
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: mem0
+  namespace: tei
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: mem0
+  template:
+    metadata:
+      labels:
+        app: mem0
+    spec:
+      initContainers:
+        - name: patch-mem0
+          image: ccr.ccs.tencentyun.com/tei_agent/mem0:latest
+          command:
+            - sh
+            - -c
+            - |
+              cp -r /usr/local/lib/python3.12/site-packages/mem0 /tmp/mem0-patch/
+              sed -i 's/from sentence_transformers import SentenceTransformer/# from sentence_transformers import SentenceTransformer/' /tmp/mem0-patch/embeddings/huggingface.py
+              echo "patch done"
+          volumeMounts:
+            - name: mem0-code
+              mountPath: /tmp/mem0-patch
+      containers:
+        - name: mem0-ui
+          image: ccr.ccs.tencentyun.com/tei_agent/mem0-ui:latest
+          ports:
+            - containerPort: 3000
+              name: http
+          env:
+            - name: NEXT_PUBLIC_API_URL
+              value: "https://api.mem0.violin-work.online"
+            - name: API_INTERNAL_URL
+              value: "http://mem0.tei.svc.cluster.local:8000"
+            - name: NEXT_PUBLIC_INSTANCE_NAME
+              value: Mem0
+          resources:
+            limits:
+              cpu: 200m
+              memory: 500Mi
+            requests:
+              cpu: 100m
+              memory: 250Mi
+        - name: mem0
+          image: ccr.ccs.tencentyun.com/tei_agent/mem0:latest
+          ports:
+            - containerPort: 8000
+              name: http
+          envFrom:
+            - configMapRef:
+                name: mem0-env
+            - secretRef:
+                name: mem0-secrets
+          env:
+            - name: POSTGRES_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: dify-prod-db-secret
+                  key: password
+          volumeMounts:
+            - name: mem0-history
+              mountPath: /app/data
+            - name: mem0-code
+              mountPath: /usr/local/lib/python3.12/site-packages/mem0
+          resources:
+            limits:
+              cpu: "2"
+              memory: 4Gi
+            requests:
+              cpu: "500m"
+              memory: 1Gi
+      volumes:
+        - name: mem0-history
+          persistentVolumeClaim:
+            claimName: mem0-history
+        - name: mem0-code
+          emptyDir: {}
 ```
 
-验证：
+**原理**：init container 先于主容器启动，把镜像里的 mem0 代码复制到 emptyDir，sed 补丁打在 emptyDir 里。主容器挂载 emptyDir 到 site-packages，覆盖镜像原有文件，实现补丁持久化（recreate 不丢）。
-
-```bash
-python3 -c "from mem0.embeddings.huggingface import HuggingFaceEmbedding"
-```
-
-**永久修复**：在 Dockerfile 里加这步，或修改本地 mem0 源码后 COPY 进容器。
 
 ## 功能测试