feat: couchbase integration (#6165)

Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Elliot Scribner <elliot.scribner@couchbase.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Bowen Liang <bowenliang@apache.org>

docker/docker-compose.yaml

@@ -110,6 +110,11 @@ x-shared-env: &shared-api-worker-env
   QDRANT_CLIENT_TIMEOUT: ${QDRANT_CLIENT_TIMEOUT:-20}
   QDRANT_GRPC_ENABLED: ${QDRANT_GRPC_ENABLED:-false}
   QDRANT_GRPC_PORT: ${QDRANT_GRPC_PORT:-6334}
+  COUCHBASE_CONNECTION_STRING: ${COUCHBASE_CONNECTION_STRING:-'couchbase-server'}
+  COUCHBASE_USER: ${COUCHBASE_USER:-Administrator}
+  COUCHBASE_PASSWORD: ${COUCHBASE_PASSWORD:-password}
+  COUCHBASE_BUCKET_NAME: ${COUCHBASE_BUCKET_NAME:-Embeddings}
+  COUCHBASE_SCOPE_NAME: ${COUCHBASE_SCOPE_NAME:-_default}
   MILVUS_URI: ${MILVUS_URI:-http://127.0.0.1:19530}
   MILVUS_TOKEN: ${MILVUS_TOKEN:-}
   MILVUS_USER: ${MILVUS_USER:-root}
@@ -475,6 +480,39 @@ services:
     environment:
       QDRANT_API_KEY: ${QDRANT_API_KEY:-difyai123456}
 
+  # The Couchbase vector store.
+  couchbase-server:
+    build: ./couchbase-server
+    profiles:
+      - couchbase
+    restart: always
+    environment:
+      - CLUSTER_NAME=dify_search
+      - COUCHBASE_ADMINISTRATOR_USERNAME=${COUCHBASE_USER:-Administrator}
+      - COUCHBASE_ADMINISTRATOR_PASSWORD=${COUCHBASE_PASSWORD:-password}
+      - COUCHBASE_BUCKET=${COUCHBASE_BUCKET_NAME:-Embeddings}
+      - COUCHBASE_BUCKET_RAMSIZE=512
+      - COUCHBASE_RAM_SIZE=2048
+      - COUCHBASE_EVENTING_RAM_SIZE=512
+      - COUCHBASE_INDEX_RAM_SIZE=512
+      - COUCHBASE_FTS_RAM_SIZE=1024
+    hostname: couchbase-server
+    container_name: couchbase-server
+    working_dir: /opt/couchbase
+    stdin_open: true
+    tty: true
+    entrypoint: [""]
+    command: sh -c "/opt/couchbase/init/init-cbserver.sh"
+    volumes:
+      - ./volumes/couchbase/data:/opt/couchbase/var/lib/couchbase/data
+    healthcheck:
+      # ensure bucket was created before proceeding
+      test: [ "CMD-SHELL", "curl -s -f -u Administrator:password http://localhost:8091/pools/default/buckets | grep -q '\\[{' || exit 1" ]
+      interval: 10s
+      retries: 10
+      start_period: 30s
+      timeout: 10s
+
   # The pgvector vector database.
   pgvector:
     image: pgvector/pgvector:pg16