update documentation

Author: bennotieno

UPGRADE-OPERATIONS.md

@@ -750,8 +750,8 @@ export QDRANT_S3_ACCESS_KEY_ID="your-access-key"
 export QDRANT_S3_SECRET_ACCESS_KEY="your-secret-key"
 export QDRANT_S3_BUCKET_NAME="qdrant-snapshots"
 
-# Auto-discover peers
-export GET_PEERS_FROM_CLUSTER_INFO="true"
+# Disable Auto-discover of peers
+export GET_PEERS_FROM_CLUSTER_INFO="false"
 
 # Timeout settings
 export CURL_TIMEOUT="1800"

qdrant-backup-restore/k8s/README.md

@@ -163,9 +163,9 @@ kubectl -n <namespace> logs -lapp=qdrant-backup -f
 Update the following environment varibles accordingly;
 
 1. Update the `secretKeyRef.name` on all `env:` entries under `env.[*].valueFrom` to the name of the kubernetes secrets deployed when configuring Qdrant.
-2. Update the `QDRANT_SOURCE_HOSTS` to the kubernetes service domain of the source Qdrant deployment.
+2. Update the `QDRANT_SOURCE_HOSTS` to empty `""`.
 3. Update the `QDRANT_RESTORE_HOSTS` to the target qdrant cluster service domain.
-4. `GET_PEERS_FROM_CLUSTER_INFO` should be `true` to discover qdrant cluster peers when backing up collections.
+4. `GET_PEERS_FROM_CLUSTER_INFO` should be `false` during restore.
 5. `CURL_TIMEOUT` is set at `3000` seconds. This is the max time curl will wait for request to complete. Its increased in scenarios where restoration takes a while.
 6. `QDRANT_S3_LINK_EXPIRY_DURATION` is set at `3600`. This is the duration that an s3 presigned url will be active. The url is used during the recovery process.
 7. `QDRANT_WAIT_ON_TASK` is set as `true`. This configuation make restoration process synchronous meaning 'wait for snapshot process to finish successfully before moving on'. Its used during backup and recovery.

qdrant-backup-restore/k8s/backup-job.yaml

@@ -26,11 +26,30 @@ spec:
             - -c
             - "cd scripts && ./qdrant_backup_recovery.sh create_snap"
           env:
+            - name: QDRANT_S3_ACCESS_KEY_ID
+              valueFrom:
+                secretKeyRef:
+                  name: qdrant-credentials-minio # change this to your qdrant kubernetes secret name
+                  key: QDRANT_S3_ACCESS_KEY_ID
+            - name: QDRANT_S3_SECRET_ACCESS_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: qdrant-credentials-minio # change this to your qdrant kubernetes secret name
+                  key: QDRANT_S3_SECRET_ACCESS_KEY
+            - name: QDRANT_S3_BUCKET_NAME
+              valueFrom:
+                secretKeyRef:
+                  name: qdrant-credentials-minio # change this to your qdrant kubernetes secret name
+                  key: QDRANT_S3_BUCKET_NAME
             - name: QDRANT_API_KEY
               valueFrom:
                 secretKeyRef:
                   name: qdrant-credentials-minio # change this to your qdrant kubernetes secret name
                   key: QDRANT_API_KEY
+            - name: QDRANT_S3_ENDPOINT_URL
+              value: "http://minio.default.svc.cluster.local:9000" # change this to your s3 endpoint url
+            - name: MC_CONFIG_DIR
+              value: "mc" # sets the configuration location for mc S3 client
             - name: QDRANT_SOURCE_HOSTS
               value: "http://qdrant-headless:6333"  # change this to your qdrant kubernetes headless service name
             - name: QDRANT_RESTORE_HOSTS
@@ -39,6 +58,8 @@ spec:
               value: "true"
             - name: CURL_TIMEOUT
               value: "3000" # increase if more time is needed for a single backup
+            - name: BACKUP_COLLECTION_ALIASES_ON_S3
+              value: "true"
           resources:
             requests:
               cpu: "100m"

qdrant-backup-restore/k8s/configmap-snapshot.yaml

@@ -6,6 +6,12 @@ metadata:
     app: qdrant-snapshots-file
     component: script
 data:
+  # this is used to provide a list of snapshots to restore
   snapshots: |
     ,_default_256,_default_256-5528114518172461-2026-01-29-11-44-26.snapshot
     ,midlib,midlib-567156434043892-2026-01-29-11-44-27.snapshot
+
+  # this is used to provide a list of collections to restore
+  collections: |
+    ,_default_256
+    ,Assistant_SapSenMarkdownHeaderMetadataSectionClean_Assistant-Hybrid-Index-1024-SAP-SEN

qdrant-backup-restore/k8s/restore-job.yaml

@@ -47,19 +47,21 @@ spec:
                   name: qdrant-credentials-minio
                   key: QDRANT_API_KEY
             - name: QDRANT_SOURCE_HOSTS
-              value: "http://qdrant-headless:6333" # change this to your source qdrant kubernetes headless service name
+              value: "" # leave empty if source host is not available
             - name: QDRANT_S3_ENDPOINT_URL
               value: "http://minio.default.svc.cluster.local:9000" # change this to your s3 endpoint url
             - name: QDRANT_RESTORE_HOSTS
-              value: "http://qdrantr2-headless:6333" # change this to your target qdrant kubernetes headless service name
+              value: "http://qdrant-headless:6333"  # change this to your target qdrant kubernetes headless service name
             - name: GET_PEERS_FROM_CLUSTER_INFO
-              value: "true"
+              value: "false"
             - name: QDRANT_SNAPSHOT_DATETIME_FILTER
-              value: "" # change tis to filter snapshts based on date (glob matching is used)
+              value: "" # set this to filter snapshots based on date (glob matching is used) e.g "2026-01-29" = all snapshots in 29th January 2026, "2026-01" = all snapshots in January 2026.
             - name: CURL_TIMEOUT
               value: "3000" # increase if more time is needed for a single restore
             - name: MC_CONFIG_DIR
               value: "mc" # sets the configuration location for mc S3 client
+            - name: BACKUP_COLLECTION_ALIASES_ON_S3
+              value: "true"
           resources:
             requests:
               cpu: "100m"

qdrant-backup-restore/k8s/restore-specific-snapshot-job.yaml

@@ -47,19 +47,21 @@ spec:
                   name: qdrant-credentials-minio
                   key: QDRANT_API_KEY
             - name: QDRANT_SOURCE_HOSTS
-              value: "http://qdrant-headless:6333" # change this to your source qdrant kubernetes headless service name
+              value: "" # leave empty if source host is not available
             - name: QDRANT_S3_ENDPOINT_URL
               value: "http://minio.default.svc.cluster.local:9000" # change this to your s3 endpoint url
             - name: QDRANT_RESTORE_HOSTS
-              value: "http://qdrantr2-headless:6333" # change this to your target qdrant kubernetes headless service name
+              value: "http://qdrant-headless:6333" # change this to your target qdrant kubernetes headless service name
             - name: GET_PEERS_FROM_CLUSTER_INFO
-              value: "true"
+              value: "false"
             - name: CURL_TIMEOUT
               value: "3000" # increase if more time is needed for a single restore
             - name: QDRANT_SNAPSHOT_DATETIME_FILTER
               value: "" # change tis to filter snapshts based on date (glob matching is used)
             - name: MC_CONFIG_DIR
               value: "mc" # sets the configuration location for mc S3 client
+            - name: BACKUP_COLLECTION_ALIASES_ON_S3
+              value: "true"
           resources:
             requests:
               cpu: "100m"
@@ -71,7 +73,12 @@ spec:
           - name: qdrant-backup-restore-script
             mountPath: /scripts/qdrant_backup_recovery.sh
             subPath: qdrant_backup_recovery.sh
+          # this is used to restore specific collections
           - name: qdrant-snapshots-file
+            mountPath: /scripts/collections
+            subPath: collections
+          # this is used to restore specific snapshots
+          - name: qdrant-collections-file
             mountPath: /scripts/snapshots
             subPath: snapshots
           - name: scripts

qdrant-backup-restore/qdrant_backup_recovery.sh

@@ -74,7 +74,11 @@ get_collections() {
   fi
   _printf "fetching collections!\n"
 
-  local host="${source_hosts[0]}"
+  local host="${source_hosts[0]:-}"
+  if [[ -z "$host" ]]; then
+    _printf "source host is not available for fetching collections. Please ensure QDRANT_SOURCE_HOSTS is set correctly in your environment variables.\n"
+    exit 1
+  fi
 
   collections_count=0
 
@@ -132,7 +136,11 @@ create_snapshot_from_peer() {
 
 # creates and appends created collection snapshot from a qdrant node to $QDRANT_SNAPSHOTS_FILE
 track_created_collection_snapshot() {
-    local host="${source_hosts[0]}"
+    local host="${source_hosts[0]:-}"
+    if [[ -z "$host" ]]; then
+      _printf "source host is not available for fetching collection snapshots. Please ensure QDRANT_SOURCE_HOSTS is set correctly in your environment variables.\n"
+      exit 1
+    fi
     local collection_name="$1"
     local result=""
     local status=""
@@ -537,7 +545,11 @@ recover_collection_snapshots(){
 
 # gets the collection aliases from a qdrant node and appends it to $QDRANT_COLLECTION_ALIASES file
 get_collection_aliases() {
-  local host="${source_hosts[0]}"
+  local host="${source_hosts[0]:-}"
+  if [[ -z "$host" ]]; then
+    _printf "source host is not available for fetching collection aliases. Please ensure QDRANT_SOURCE_HOSTS is set correctly in your environment variables.\n"
+    exit 1
+  fi
   local result=""
   local status=""
 
@@ -638,7 +650,11 @@ recover_collection_alias() {
 # restores collection aliases to a qdrant node and appends progress to $QDRANT_ALIAS_RECOVERY_HISTORY_FILE
 recover_collection_aliases() {
 
-  local host="${restore_hosts[0]}"
+  local host="${restore_hosts[0]:-}"
+  if [[ -z "$host" ]]; then
+    _printf "restore host is not available for recovering collection aliases. Please ensure QDRANT_RESTORE_HOSTS is set correctly in your environment variables.\n"
+    exit 1
+  fi
 
 
   if [ "$BACKUP_COLLECTION_ALIASES_ON_S3" = "true" ]; then
@@ -708,7 +724,12 @@ delete_files() {
 
 # gets qdrant peer host url using cluster info endpoint. Sets the port to $QDRANT_HTTP_PORT the http port.
 get_peers_from_cluster_info() {
-  local host="${source_hosts[0]}"
+  local host="${source_hosts[0]:-}"
+  if [[ -z "$host" ]]; then
+    _printf "source host is not available. Please ensure QDRANT_SOURCE_HOSTS is set correctly in your environment variables. If restoring snapshots set QDRANT_SOURCE_HOSTS and GET_PEERS_FROM_CLUSTER_INFO to empty string.\n"
+    exit 1
+  fi
+
   result=$(_curl GET "$host/cluster" --header "api-key: $QDRANT_API_KEY")
   entries=$(jq -r '.result.peers // {}' <<< "$result")
   peer_uri_entries=$(jq -r 'to_entries[] | "\(.key) \(.value.uri)"' <<< "$entries")