Update ragflow

charts/ragflow/CUSTOM-README.md

@@ -20,16 +20,19 @@
 
 | Name                   | 설명                                                         | 기본값 |
 | ---------------------- | ------------------------------------------------------------ | ------ |
-| `env.DOC_ENGINE` | 문서 엔진 타입 설정. `elasticsearch` 또는 `infinity` 선택 가능 | `infinity`   |
+| `env.DOC_ENGINE` | 문서 엔진 타입 설정. `elasticsearch`, `infinity`, `opensearch` 선택 가능 | `infinity`   |
 | `env.STACK_VERSION` | Elasticsearch 버전 설정 | `"8.11.3"`   |
 | `env.ELASTIC_PASSWORD` | Elasticsearch 비밀번호 | `infini_rag_flow_helm`   |
+| `env.OPENSEARCH_PASSWORD` | OpenSearch 비밀번호 (대소문자, 숫자, 특수문자 포함 필요) | `infini_rag_flow_OS_01`   |
 | `env.MYSQL_PASSWORD` | MySQL 비밀번호 | `infini_rag_flow_helm`   |
 | `env.MYSQL_DBNAME` | MySQL 데이터베이스 이름 | `rag_flow`   |
 | `env.MINIO_ROOT_USER` | MinIO 사용자명 | `rag_flow`   |
 | `env.MINIO_PASSWORD` | MinIO 비밀번호 | `infini_rag_flow_helm`   |
 | `env.REDIS_PASSWORD` | Redis 비밀번호 | `infini_rag_flow_helm`   |
-| `env.RAGFLOW_IMAGE` | RAGFlow Docker 이미지 | `infiniflow/ragflow:v0.19.0-slim`   |
+| `env.RAGFLOW_IMAGE` | RAGFlow Docker 이미지 | `infiniflow/ragflow:v0.20.1-slim`   |
-| `env.TIMEZONE` | 로컬 시간대 설정 | `"Asia/Shanghai"`   |
+| `env.TIMEZONE` | 로컬 시간대 설정 | `"Asia/Seoul"`   |
+| `env.DOC_BULK_SIZE` | 문서 파싱 시 단일 배치에서 처리되는 문서 청크 수 | `4`   |
+| `env.EMBEDDING_BATCH_SIZE` | 임베딩 벡터화 시 단일 배치에서 처리되는 텍스트 청크 수 | `16`   |
 
 
 
@@ -43,6 +46,39 @@
 | `ragflow.api.service.type`         | API 서비스 타입 설정             | `ClusterIP`      |
 | `ragflow.deployment.strategy`      | 배포 전략 설정                   | ``  |
 | `ragflow.deployment.resources`     | 리소스 제한 설정                 | `` |
+| `ragflow.service_conf.oauth.oidc`  | OIDC 인증 설정                   | 설정 예시 참조 |
+| `ragflow.llm_factories`            | LLM 팩토리 설정                  | 설정 예시 참조 |
+
+#### 2.1) OIDC 인증 설정 예시
+```yaml
+ragflow:
+  service_conf:
+    oauth:
+      oidc:
+        display_name: "OIDC"
+        client_id: "ragflow"
+        client_secret: "your-client-secret"
+        issuer: "https://your-keycloak-domain/realms/your-realm"
+        scope: "openid email profile"
+        redirect_uri: "https://your-ragflow-domain/v1/user/oauth/callback/oidc"
+```
+
+#### 2.2) LLM 팩토리 설정 예시
+```yaml
+ragflow:
+  llm_factories:
+    factory_llm_infos:
+    - name: OpenAI-API-Compatible
+      logo: ""
+      tags: "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION"
+      status: "1"
+      llm:
+        - llm_name: my-custom-llm
+          tags: "LLM,CHAT,"
+          max_tokens: 100000
+          model_type: chat
+          is_tools: false
+```
 
 
 
@@ -52,9 +88,11 @@
 | Name                        | 설명                                                         | 기본값                  |
 | --------------------------- | ------------------------------------------------------------ | ----------------------- |
 | `infinity.image.repository` | Infinity 이미지 저장소 | `infiniflow/infinity` |
-| `infinity.image.tag` | Infinity 이미지 태그 | `v0.6.0-dev3` |
+| `infinity.image.tag` | Infinity 이미지 태그 | `v0.6.0-dev5` |
 | `infinity.storage.className` | 스토리지 클래스 이름 | `` |
 | `infinity.storage.capacity` | 스토리지 용량 | `5Gi` |
+| `infinity.deployment.strategy` | 배포 전략 설정 | `` |
+| `infinity.deployment.resources` | 리소스 제한 설정 | `` |
 | `infinity.service.type` | 서비스 타입 | `ClusterIP` |
 
 
@@ -151,17 +189,28 @@
       cert-manager.io/cluster-issuer: "selfsigned-issuer" 
       cert-manager.io/duration: 8760h  
       cert-manager.io/renew-before: 720h
+      konghq.com/https-redirect-status-code: '301'
+      konghq.com/protocols: https
     hosts:
     - host: ragflow.example.org
       paths:
       - path: /
         pathType: ImplementationSpecific
-    tls: 
+    tls:
     -  hosts:
        - ragflow.example.org
        secretName: ragflow-tls
   ```
 
+#### 8.4) Kong 관련 어노테이션
+
+- Kong Ingress Controller 사용 시 추가 설정 옵션들:
+
+| Name                                    | 설명                               | 기본값    |
+| --------------------------------------- | ---------------------------------- | --------- |
+| `konghq.com/https-redirect-status-code` | HTTPS 리다이렉트 상태 코드         | `'301'`   |
+| `konghq.com/protocols`                  | 허용할 프로토콜                    | `https`   |
+
 
 ## 3. 주요 설정 가이드
 
@@ -169,6 +218,7 @@
 - `env.DOC_ENGINE`을 통해 문서 엔진을 선택할 수 있습니다.
   - `elasticsearch`: 안정적이고 검증된 검색 엔진
   - `infinity`: 고성능 벡터 검색 엔진 (권장)
+  - `opensearch`: Elasticsearch의 오픈소스 대안
 
 ### 3.2) 리소스 설정
 - 각 서비스별로 `deployment.resources`에서 CPU/메모리 리소스를 설정할 수 있습니다.
@@ -180,4 +230,22 @@
 
 ### 3.4) 보안 설정
 - 모든 비밀번호는 기본값에서 변경하여 사용하세요.
-- OIDC를 통한 외부 인증 시스템 연동이 가능합니다.
+- OIDC를 통한 외부 인증 시스템 연동이 가능합니다.
+
+### 3.5) 성능 튜닝 설정
+- 문서 처리 및 임베딩 성능을 조정할 수 있는 설정들입니다.
+
+| Name                        | 설명                                                         | 기본값                  |
+| --------------------------- | ------------------------------------------------------------ | ----------------------- |
+| `env.DOC_BULK_SIZE`         | 문서 파싱 시 단일 배치에서 처리되는 문서 청크 수             | `4`                     |
+| `env.EMBEDDING_BATCH_SIZE`  | 임베딩 벡터화 시 단일 배치에서 처리되는 텍스트 청크 수       | `16`                    |
+
+### 3.6) 추가 환경 설정
+- 기타 선택적 환경 설정들입니다.
+
+| Name                        | 설명                                                         | 기본값                  |
+| --------------------------- | ------------------------------------------------------------ | ----------------------- |
+| `env.HF_ENDPOINT`           | Hugging Face 엔드포인트 (접근 제한 시 미러 사용)             | 설정하지 않음           |
+| `env.MAX_CONTENT_LENGTH`    | 업로드 파일 최대 크기 (바이트)                               | `134217728` (128MB)     |
+
+**참고**: `MAX_CONTENT_LENGTH` 변경 시 nginx 설정의 `client_max_body_size`도 함께 수정해야 합니다.

charts/ragflow/custom-values.yaml

@@ -4,8 +4,10 @@ env:
   # Available options:
   # - `elasticsearch` (default)
   # - `infinity` (https://github.com/infiniflow/infinity)
+  # - `opensearch` (https://github.com/opensearch-project/OpenSearch)
   # DOC_ENGINE: elasticsearch
   DOC_ENGINE: infinity
+  # DOC_ENGINE: opensearch
 
   # The version of Elasticsearch.
   STACK_VERSION: "8.11.3"
@@ -13,6 +15,10 @@ env:
   # The password for Elasticsearch
   ELASTIC_PASSWORD: infini_rag_flow_helm
 
+  # The password for OpenSearch.
+  # At least one uppercase letter, one lowercase letter, one digit, and one special character
+  OPENSEARCH_PASSWORD: infini_rag_flow_OS_01
+
   # The password for MySQL
   MYSQL_PASSWORD: infini_rag_flow_helm
   # The database of the MySQL service to use
@@ -27,13 +33,13 @@ env:
   REDIS_PASSWORD: infini_rag_flow_helm
 
   # The RAGFlow Docker image to download.
-  # Defaults to the v0.19.0-slim edition, which is the RAGFlow Docker image without embedding models.
+  # Defaults to the v0.20.1-slim edition, which is the RAGFlow Docker image without embedding models.
-  RAGFLOW_IMAGE: infiniflow/ragflow:v0.19.0-slim
+  RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.1-slim
   #
   # To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
-  # RAGFLOW_IMAGE: infiniflow/ragflow:v0.19.0
+  # RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.1
   #
-  # The Docker image of the v0.19.0 edition includes:
+  # The Docker image of the v0.20.1 edition includes:
   # - Built-in embedding models:
   #   - BAAI/bge-large-zh-v1.5
   #   - BAAI/bge-reranker-v2-m3
@@ -52,7 +58,7 @@ env:
   #
 
   # The local time zone.
-  TIMEZONE: "Asia/Shanghai"
+  TIMEZONE: "Asia/Seoul"
 
   # Uncomment the following line if you have limited access to huggingface.co:
   # HF_ENDPOINT: https://hf-mirror.com
@@ -62,7 +68,45 @@ env:
   # MAX_CONTENT_LENGTH: "134217728"
   # After making the change, ensure you update `client_max_body_size` in nginx/nginx.conf correspondingly.
 
+  # The number of document chunks processed in a single batch during document parsing.
+  DOC_BULK_SIZE: 4
+
+  # The number of text chunks processed in a single batch during embedding vectorization.
+  EMBEDDING_BATCH_SIZE: 16
+
 ragflow:
+
+  # Optional service configuration overrides
+  # to be written to local.service_conf.yaml
+  # inside the RAGFlow container
+  # https://ragflow.io/docs/dev/configurations#service-configuration
+  service_conf:
+    oauth:
+      oidc:
+        display_name: "OIDC"
+        client_id: "Client ID"
+        client_secret: "Client Secret"
+        issuer: "https://keycloak_domain/realms/paasup"
+        scope: "openid email profile"
+        redirect_uri: "https://ragflow_domain/v1/user/oauth/callback/oidc"
+
+  # Optional yaml formatted override for the
+  # llm_factories.json file inside the RAGFlow
+  # container.
+  llm_factories:
+    # factory_llm_infos:
+    # - name: OpenAI-API-Compatible
+    #   logo: ""
+    #   tags: "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION"
+    #   status: "1"
+    #   llm:
+    #     - llm_name: my-custom-llm
+    #       tags: "LLM,CHAT,"
+    #       max_tokens: 100000
+    #       model_type: chat
+    #       is_tools: false
+
+  # Kubernetes configuration
   deployment:
     strategy:
     resources:
@@ -77,7 +121,7 @@ ragflow:
 infinity:
   image:
     repository: infiniflow/infinity
-    tag: v0.6.0-dev3
+    tag: v0.6.0-dev5
   storage:
     className:
     capacity: 5Gi
@@ -87,19 +131,6 @@ infinity:
   service:
     type: ClusterIP
 
-elasticsearch:
-  storage:
-    className:
-    capacity: 20Gi
-  deployment:
-    strategy:
-    resources:
-      requests:
-        cpu: "4"
-        memory: "16Gi"
-  service:
-    type: ClusterIP
-
 minio:
   image:
     repository: quay.io/minio/minio
@@ -135,6 +166,11 @@ redis:
     capacity: 5Gi
   persistence:
     enabled: true
+    # Set's the retention policy for the persistent storage (only available in k8s 1.32 or later)
+    # https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention
+    # retentionPolicy:
+      # whenDeleted: Delete
+      # whenScaled: Delete
   deployment:
     strategy:
     resources:
@@ -154,11 +190,11 @@ ingress:
     konghq.com/https-redirect-status-code: '301'
     konghq.com/protocols: https
   hosts:
-    - host: ragflow.gke.paasup.io
+    - host: ragflow.example.org
       paths:
         - path: /
           pathType: ImplementationSpecific
   tls:
    - secretName: ragflow-tls
      hosts:
-       - ragflow.gke.paasup.io
+       - ragflow.example.org

charts/ragflow/templates/elasticsearch-config.yaml

@@ -10,4 +10,8 @@ data:
   xpack.security.enabled: "true"
   xpack.security.http.ssl.enabled: "false"
   xpack.security.transport.ssl.enabled: "false"
+  cluster.routing.allocation.disk.watermark.low: 5gb
+  cluster.routing.allocation.disk.watermark.high: 3gb
+  cluster.routing.allocation.disk.watermark.flood_stage: 2gb
+  TZ: {{ .Values.env.TIMEZONE }}
 {{- end -}}

charts/ragflow/templates/elasticsearch.yaml

@@ -19,7 +19,7 @@ spec:
       storage: {{ .Values.elasticsearch.storage.capacity }}
 ---
 apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
   name: {{ include "ragflow.fullname" . }}-es
   labels:

charts/ragflow/templates/env.yaml

@@ -43,14 +43,11 @@ stringData:
   ELASTIC_PASSWORD: {{ .Values.env.ELASTIC_PASSWORD | required "ELASTIC_PASSWORD is required" }}
   {{- else if eq .Values.env.DOC_ENGINE "infinity" }}
   INFINITY_HOST: {{ printf "%s-infinity.%s.svc" (include "ragflow.fullname" .) .Release.Namespace }}
+  {{- else if eq .Values.env.DOC_ENGINE "opensearch" }}
+  OS_HOST: {{ printf "%s-opensearch.%s.svc" (include "ragflow.fullname" .) .Release.Namespace }}
+  OS_PORT: "9201"
+  OPENSEARCH_PASSWORD: {{ .Values.env.OPENSEARCH_PASSWORD | required "OPENSEARCH_PASSWORD is required" }}
+  OPENSEARCH_INITIAL_ADMIN_PASSWORD: {{ .Values.env.OPENSEARCH_PASSWORD | required "OPENSEARCH_PASSWORD is required" }}
   {{- else }}
-  {{ fail "env.DOC_ENGINE must be either 'elasticsearch' or 'infinity'" }}
+  {{ fail "env.DOC_ENGINE must be either 'elasticsearch', 'opensearch' or 'infinity'" }}
-  {{- end }}
-  {{- if .Values.oidc.enable }}
-  DISPLAY_NAME: {{ .Values.oidc.display_name }}
-  CLIENT_ID: {{ .Values.oidc.client_id }}
-  CLIENT_SECRETS: {{ .Values.oidc.client_secret }}
-  ISSUER: {{ .Values.oidc.issuer }}
-  SCOPE: {{ .Values.oidc.scope }}
-  REDIRECT_URI: {{ .Values.oidc.redirect_uri }}
   {{- end }}

charts/ragflow/templates/infinity.yaml

@@ -19,7 +19,7 @@ spec:
       storage: {{ .Values.infinity.storage.capacity }}
 ---
 apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
   name: {{ include "ragflow.fullname" . }}-infinity
   labels:

charts/ragflow/templates/minio.yaml

@@ -19,9 +19,9 @@ spec:
       storage: {{ .Values.minio.storage.capacity }}
 ---
 apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
-  name: ragflow-minio-deployment
+  name: {{ include "ragflow.fullname" . }}-minio
   labels:
     {{- include "ragflow.labels" . | nindent 4 }}
     app.kubernetes.io/component: minio

charts/ragflow/templates/mysql.yaml

@@ -19,7 +19,7 @@ spec:
       storage: {{ .Values.mysql.storage.capacity }}
 ---
 apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
   name: {{ include "ragflow.fullname" . }}-mysql
   labels:

charts/ragflow/templates/opensearch-config.yaml

@@ -0,0 +1,18 @@
+{{- if eq .Values.env.DOC_ENGINE "opensearch" -}}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "ragflow.fullname" . }}-opensearch-config
+data:
+  node.name: opensearch01
+  bootstrap.memory_lock: "false"
+  discovery.type: single-node
+  plugins.security.disabled: "false"
+  plugins.security.ssl.http.enabled: "false"
+  plugins.security.ssl.transport.enabled: "true"
+  cluster.routing.allocation.disk.watermark.low: 5gb
+  cluster.routing.allocation.disk.watermark.high: 3gb
+  cluster.routing.allocation.disk.watermark.flood_stage: 2gb
+  TZ: {{ .Values.env.TIMEZONE }}
+  http.port: "9201"
+{{- end -}}

charts/ragflow/templates/opensearch.yaml

@@ -0,0 +1,117 @@
+{{- if eq .Values.env.DOC_ENGINE "opensearch" -}}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "ragflow.fullname" . }}-opensearch-data
+  annotations:
+    "helm.sh/resource-policy": keep
+  labels:
+    {{- include "ragflow.labels" . | nindent 4 }}
+    app.kubernetes.io/component: opensearch
+spec:
+  {{- with .Values.opensearch.storage.className }}
+  storageClassName: {{ . }}
+  {{- end }}
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: {{ .Values.opensearch.storage.capacity }}
+---
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: {{ include "ragflow.fullname" . }}-opensearch
+  labels:
+    {{- include "ragflow.labels" . | nindent 4 }}
+    app.kubernetes.io/component: opensearch
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      {{- include "ragflow.selectorLabels" . | nindent 6 }}
+      app.kubernetes.io/component: opensearch
+  {{- with .Values.opensearch.deployment.strategy }}
+  strategy:
+    {{- . | toYaml | nindent 4 }}
+  {{- end }}
+  template:
+    metadata:
+      labels:
+      {{- include "ragflow.labels" . | nindent 8 }}
+        app.kubernetes.io/component: opensearch
+      annotations:
+        checksum/config-opensearch: {{ include (print $.Template.BasePath "/opensearch-config.yaml") . | sha256sum }}
+        checksum/config-env: {{ include (print $.Template.BasePath "/env.yaml") . | sha256sum }}
+    spec:
+      initContainers:
+      - name: fix-data-volume-permissions
+        image: alpine
+        command:
+        - sh
+        - -c
+        - "chown -R 1000:0 /usr/share/opensearch/data"
+        volumeMounts:
+          - mountPath: /usr/share/opensearch/data
+            name: opensearch-data
+      - name: sysctl
+        image: busybox
+        securityContext:
+          privileged: true
+          runAsUser: 0
+        command: ["sysctl", "-w", "vm.max_map_count=262144"]
+      containers:
+      - name: opensearch
+        image: {{ .Values.opensearch.image.repository }}:{{ .Values.opensearch.image.tag }}
+        envFrom:
+          - secretRef:
+              name: {{ include "ragflow.fullname" . }}-env-config
+          - configMapRef:
+              name: {{ include "ragflow.fullname" . }}-opensearch-config
+        ports:
+          - containerPort: 9201
+            name: http
+        volumeMounts:
+          - mountPath: /usr/share/opensearch/data
+            name: opensearch-data
+        {{- with .Values.opensearch.deployment.resources }}
+        resources:
+          {{- . | toYaml | nindent 10 }}
+        {{- end }}
+        securityContext:
+          capabilities:
+            add:
+              - "IPC_LOCK"
+          runAsUser: 1000
+          allowPrivilegeEscalation: false
+        livenessProbe:
+          exec:
+            command:
+              - sh
+              - -c
+              - curl -u admin:$OPENSEARCH_PASSWORD localhost:9201
+          initialDelaySeconds: 30
+          periodSeconds: 10
+          failureThreshold: 6
+      volumes:
+        - name: opensearch-data
+          persistentVolumeClaim:
+            claimName: {{ include "ragflow.fullname" . }}-opensearch-data
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "ragflow.fullname" . }}-opensearch
+  labels:
+    {{- include "ragflow.labels" . | nindent 4 }}
+    app.kubernetes.io/component: opensearch
+spec:
+  selector:
+    {{- include "ragflow.selectorLabels" . | nindent 4 }}
+    app.kubernetes.io/component: opensearch
+  ports:
+    - protocol: TCP
+      port: 9201
+      targetPort: http
+  type: {{ .Values.opensearch.service.type }}
+{{- end -}}

charts/ragflow/templates/ragflow.yaml

@@ -43,10 +43,15 @@ spec:
           - mountPath: /etc/nginx/nginx.conf
             subPath: nginx.conf
             name: nginx-config-volume
-          {{- if .Values.oidc.enable }}
+          {{- with .Values.ragflow.service_conf }}
-          - mountPath: /ragflow/conf/service_conf.yaml.template
+          - mountPath: /ragflow/conf/local.service_conf.yaml
-            subPath: service_conf.yaml.template
+            subPath: local.service_conf.yaml
-            name: nginx-config-volume
+            name: service-conf-volume
+          {{- end }}
+          {{- with .Values.ragflow.llm_factories }}
+          - mountPath: /ragflow/conf/llm_factories.json
+            subPath: llm_factories.json
+            name: service-conf-volume
           {{- end }}
         envFrom:
           - secretRef:
@@ -59,6 +64,9 @@ spec:
         - name: nginx-config-volume
           configMap:
             name: nginx-config
+        - name: service-conf-volume
+          configMap:
+            name: ragflow-service-config
 ---
 apiVersion: v1
 kind: Service

charts/ragflow/templates/ragflow_config.yaml

@@ -1,6 +1,20 @@
 ---
 apiVersion: v1
 kind: ConfigMap
+metadata:
+  name: ragflow-service-config
+data:
+  {{- with .Values.ragflow.service_conf }}
+  local.service_conf.yaml: |
+    {{- . | toYaml | nindent 4 }}
+  {{- end }}
+  {{- with .Values.ragflow.llm_factories }}
+  llm_factories.json: |
+    {{- . | toPrettyJson | nindent 4 }}
+  {{- end }}
+---
+apiVersion: v1
+kind: ConfigMap
 metadata:
   name: nginx-config
 data:
@@ -73,116 +87,3 @@ data:
 
         include /etc/nginx/conf.d/ragflow.conf;
     }
-  {{- if .Values.oidc.enable }}
-  service_conf.yaml.template: |
-    ragflow:
-      host: ${RAGFLOW_HOST:-0.0.0.0}
-      http_port: 9380
-    mysql:
-      name: '${MYSQL_DBNAME:-rag_flow}'
-      user: '${MYSQL_USER:-root}'
-      password: '${MYSQL_PASSWORD:-infini_rag_flow}'
-      host: '${MYSQL_HOST:-mysql}'
-      port: 3306
-      max_connections: 900
-      stale_timeout: 300
-    minio:
-      user: '${MINIO_USER:-rag_flow}'
-      password: '${MINIO_PASSWORD:-infini_rag_flow}'
-      host: '${MINIO_HOST:-minio}:9000'
-    es:
-      hosts: 'http://${ES_HOST:-es01}:9200'
-      username: '${ES_USER:-elastic}'
-      password: '${ELASTIC_PASSWORD:-infini_rag_flow}'
-    os:
-      hosts: 'http://${OS_HOST:-opensearch01}:9201'
-      username: '${OS_USER:-admin}'
-      password: '${OPENSEARCH_PASSWORD:-infini_rag_flow_OS_01}'
-    infinity:
-      uri: '${INFINITY_HOST:-infinity}:23817'
-      db_name: 'default_db'
-    redis:
-      db: 1
-      password: '${REDIS_PASSWORD:-infini_rag_flow}'
-      host: '${REDIS_HOST:-redis}:6379'
-
-    # postgres:
-    #   name: '${POSTGRES_DBNAME:-rag_flow}'
-    #   user: '${POSTGRES_USER:-rag_flow}'
-    #   password: '${POSTGRES_PASSWORD:-infini_rag_flow}'
-    #   host: '${POSTGRES_HOST:-postgres}'
-    #   port: 5432
-    #   max_connections: 100
-    #   stale_timeout: 30
-    # s3:
-    #   access_key: 'access_key'
-    #   secret_key: 'secret_key'
-    #   region: 'region'
-    #   endpoint_url: 'endpoint_url'
-    #   bucket: 'bucket'
-    #   prefix_path: 'prefix_path'
-    #   signature_version: 'v4'
-    #   addressing_style: 'path'
-    # oss:
-    #   access_key: '${ACCESS_KEY}'
-    #   secret_key: '${SECRET_KEY}'
-    #   endpoint_url: '${ENDPOINT}'
-    #   region: '${REGION}'
-    #   bucket: '${BUCKET}'
-    #   prefix_path: '${OSS_PREFIX_PATH}'
-    # azure:
-    #   auth_type: 'sas'
-    #   container_url: 'container_url'
-    #   sas_token: 'sas_token'
-    # azure:
-    #   auth_type: 'spn'
-    #   account_url: 'account_url'
-    #   client_id: 'client_id'
-    #   secret: 'secret'
-    #   tenant_id: 'tenant_id'
-    #   container_name: 'container_name'
-    # user_default_llm:
-    #   factory: 'Tongyi-Qianwen'
-    #   api_key: 'sk-xxxxxxxxxxxxx'
-    #   base_url: ''
-    #   default_models:
-    #     chat_model: 'qwen-plus'
-    #     embedding_model: 'BAAI/bge-large-zh-v1.5@BAAI'
-    #     rerank_model: ''
-    #     asr_model: ''
-    #     image2text_model: ''
-    oauth:
-    #     oauth2:
-    #     display_name: "OAuth2"
-    #     client_id: "your_client_id"
-    #     client_secret: "your_client_secret"
-    #     authorization_url: "https://your-oauth-provider.com/oauth/authorize"
-    #     token_url: "https://your-oauth-provider.com/oauth/token"
-    #     userinfo_url: "https://your-oauth-provider.com/oauth/userinfo"
-    #     redirect_uri: "https://your-app.com/v1/user/oauth/callback/oauth2"
-      oidc:
-        display_name: '${DISPLAY_NAME}'
-        client_id: '${CLIENT_ID}'
-        client_secret: '${CLIENT_SECRETS}'
-        issuer: '${ISSUER}'
-        scope: '${SCOPE:openid}'
-        redirect_uri: '${REDIRECT_URI}'
-    #   github:
-    #     type: "github"
-    #     icon: "github"
-    #     display_name: "Github"
-    #     client_id: "your_client_id"
-    #     client_secret: "your_client_secret"
-    #     redirect_uri: "https://your-app.com/v1/user/oauth/callback/github"
-    # authentication:
-    #   client:
-    #     switch: false
-    #     http_app_key:
-    #     http_secret_key:
-    #   site:
-    #     switch: false
-    # permission:
-    #   switch: false
-    #   component: false
-    #   dataset: false
-  {{- end }}

charts/ragflow/templates/redis.yaml

@@ -64,11 +64,20 @@ spec:
             {{- . | toYaml | nindent 12 }}
           {{- end }}
   {{- if .Values.redis.persistence.enabled }}
+  {{- with .Values.redis.persistence.retentionPolicy }}
+  persistentVolumeClaimRetentionPolicy:
+    {{- with .whenDeleted }}
+    whenDeleted: {{ . }}
+    {{- end }}
+    {{- with .whenScaled }}
+    whenScaled: {{ . }}
+    {{- end }}
+  {{- end }}
   volumeClaimTemplates:
     - metadata:
         name: redis-data
         labels:
-          {{- include "ragflow.labels" . | nindent 10 }}
+          {{- include "ragflow.selectorLabels" . | nindent 10 }}
           app.kubernetes.io/component: redis
       spec:
         accessModes:
@@ -109,4 +118,4 @@ spec:
   selector:
     matchLabels:
       {{- include "ragflow.selectorLabels" . | nindent 6 }}
-      app.kubernetes.io/component: redis
+      app.kubernetes.io/component: redis

charts/ragflow/values.yaml

@@ -4,8 +4,10 @@ env:
   # Available options:
   # - `elasticsearch` (default)
   # - `infinity` (https://github.com/infiniflow/infinity)
+  # - `opensearch` (https://github.com/opensearch-project/OpenSearch)
   # DOC_ENGINE: elasticsearch
   DOC_ENGINE: infinity
+  # DOC_ENGINE: opensearch
 
   # The version of Elasticsearch.
   STACK_VERSION: "8.11.3"
@@ -13,6 +15,10 @@ env:
   # The password for Elasticsearch
   ELASTIC_PASSWORD: infini_rag_flow_helm
 
+  # The password for OpenSearch.
+  # At least one uppercase letter, one lowercase letter, one digit, and one special character
+  OPENSEARCH_PASSWORD: infini_rag_flow_OS_01
+
   # The password for MySQL
   MYSQL_PASSWORD: infini_rag_flow_helm
   # The database of the MySQL service to use
@@ -27,13 +33,13 @@ env:
   REDIS_PASSWORD: infini_rag_flow_helm
 
   # The RAGFlow Docker image to download.
-  # Defaults to the v0.19.0-slim edition, which is the RAGFlow Docker image without embedding models.
+  # Defaults to the v0.20.1-slim edition, which is the RAGFlow Docker image without embedding models.
-  RAGFLOW_IMAGE: infiniflow/ragflow:v0.19.0-slim
+  RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.1-slim
   #
   # To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
-  # RAGFLOW_IMAGE: infiniflow/ragflow:v0.19.0
+  # RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.1
   #
-  # The Docker image of the v0.19.0 edition includes:
+  # The Docker image of the v0.20.1 edition includes:
   # - Built-in embedding models:
   #   - BAAI/bge-large-zh-v1.5
   #   - BAAI/bge-reranker-v2-m3
@@ -62,7 +68,37 @@ env:
   # MAX_CONTENT_LENGTH: "134217728"
   # After making the change, ensure you update `client_max_body_size` in nginx/nginx.conf correspondingly.
 
+  # The number of document chunks processed in a single batch during document parsing.
+  DOC_BULK_SIZE: 4
+
+  # The number of text chunks processed in a single batch during embedding vectorization.
+  EMBEDDING_BATCH_SIZE: 16
+
 ragflow:
+
+  # Optional service configuration overrides
+  # to be written to local.service_conf.yaml
+  # inside the RAGFlow container
+  # https://ragflow.io/docs/dev/configurations#service-configuration
+  service_conf:
+
+  # Optional yaml formatted override for the
+  # llm_factories.json file inside the RAGFlow
+  # container.
+  llm_factories:
+    # factory_llm_infos:
+    # - name: OpenAI-API-Compatible
+    #   logo: ""
+    #   tags: "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION"
+    #   status: "1"
+    #   llm:
+    #     - llm_name: my-custom-llm
+    #       tags: "LLM,CHAT,"
+    #       max_tokens: 100000
+    #       model_type: chat
+    #       is_tools: false
+
+  # Kubernetes configuration
   deployment:
     strategy:
     resources:
@@ -77,7 +113,7 @@ ragflow:
 infinity:
   image:
     repository: infiniflow/infinity
-    tag: v0.6.0-dev3
+    tag: v0.6.0-dev5
   storage:
     className:
     capacity: 5Gi
@@ -100,6 +136,22 @@ elasticsearch:
   service:
     type: ClusterIP
 
+opensearch:
+  image:
+    repository: opensearchproject/opensearch
+    tag: 2.19.1
+  storage:
+    className:
+    capacity: 20Gi
+  deployment:
+    strategy:
+    resources:
+      requests:
+        cpu: "4"
+        memory: "16Gi"
+  service:
+    type: ClusterIP
+
 minio:
   image:
     repository: quay.io/minio/minio
@@ -135,6 +187,11 @@ redis:
     capacity: 5Gi
   persistence:
     enabled: true
+    # Set's the retention policy for the persistent storage (only available in k8s 1.32 or later)
+    # https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention
+    # retentionPolicy:
+      # whenDeleted: Delete
+      # whenScaled: Delete
   deployment:
     strategy:
     resources:
@@ -159,12 +216,3 @@ ingress:
   #  - secretName: chart-example-tls
   #    hosts:
   #      - chart-example.local
-oidc:
-  enable: false
-  display_name: "OAuth2"
-  client_id: "your_client_id"
-  client_secret: "your_client_secret"
-  authorization_url: "https://your-oauth-provider.com/oauth/authorize"
-  token_url: "https://your-oauth-provider.com/oauth/token"
-  userinfo_url: "https://your-oauth-provider.com/oauth/userinfo"
-  redirect_uri: "https://your-app.com/v1/user/oauth/callback/oauth2"