[CLOUDP-372679] Update code snippets for auto embedding for vector search

.evergreen-functions.yml

@@ -50,6 +50,8 @@ variables:
       - VERSION_UPGRADE_HOOK_VERSION
       - BUILD_SCENARIO
       - MDB_BASH_DEBUG
+      - AI_MONGODB_EMBEDDING_INDEXING_KEY
+      - AI_MONGODB_EMBEDDING_QUERY_KEY
 
 functions:
 
@@ -743,6 +745,8 @@ functions:
           - code_snippets_reset
           - task_name
           - MDB_BASH_DEBUG
+          - AI_MONGODB_EMBEDDING_INDEXING_KEY
+          - AI_MONGODB_EMBEDDING_QUERY_KEY
         add_to_path:
           - ${workdir}/bin
         script: |

docs/search/01-search-community-deploy/code_snippets/01_0322_create_auto_embed_mongodb_search_resource.sh

@@ -0,0 +1,28 @@
+# create a Kubernetes secret that would have embedding model's API Keys
+kubectl create secret generic "${AUTO_EMBEDDING_API_KEY_SECRET_NAME}" \
+  --from-literal=query-key="${AUTO_EMBEDDING_API_QUERY_KEY}" \
+  --from-literal=indexing-key="${AUTO_EMBEDDING_API_INDEXING_KEY}" --context "${K8S_CTX}" -n "${MDB_NS}"
+
+# create MongoDBSearch resource, enabling the auto embedding using the API Keys provided above
+kubectl apply --context "${K8S_CTX}" -n "${MDB_NS}" -f - <<EOF
+apiVersion: mongodb.com/v1
+kind: MongoDBSearch
+metadata:
+  name: ${MDB_RESOURCE_NAME}
+spec:
+  security:
+    tls:
+      certificateKeySecretRef:
+        name: ${MDB_SEARCH_TLS_SECRET_NAME}
+  resourceRequirements:
+    limits:
+      cpu: "3"
+      memory: 5Gi
+    requests:
+      cpu: "2"
+      memory: 3Gi
+  autoEmbedding:
+    providerEndpoint: ${PROVIDER_ENDPOINT}
+    embeddingModelAPIKeySecret:
+      name: ${AUTO_EMBEDDING_API_KEY_SECRET_NAME}
+EOF

docs/search/01-search-community-deploy/env_variables.sh

@@ -37,3 +37,10 @@ export OPERATOR_ADDITIONAL_HELM_VALUES=""
 export MDB_CONNECTION_STRING="mongodb://mdb-user:${MDB_USER_PASSWORD}@${MDB_RESOURCE_NAME}-0.${MDB_RESOURCE_NAME}-svc.${MDB_NS}.svc.cluster.local:27017/?replicaSet=${MDB_RESOURCE_NAME}&tls=true&tlsCAFile=/tls/ca.crt"
 
 export CERT_MANAGER_NAMESPACE="cert-manager"
+
+# Vector Search auto embedding related configurations
+export AUTO_EMBEDDING_API_KEY_SECRET_NAME="voyage-api-keys"
+export AUTO_EMBEDDING_API_QUERY_KEY="<embedding-model-query-key>"
+export AUTO_EMBEDDING_API_INDEXING_KEY="<embedding-model-indexing-key>"
+export PROVIDER_ENDPOINT="https://ai.mongodb.com/v1/embeddings"
+export EMBEDDING_MODEL="voyage-4"

docs/search/01-search-community-deploy/env_variables_e2e_private.sh

@@ -5,3 +5,6 @@ source "${PROJECT_DIR}/scripts/dev/contexts/e2e_mdb_community"
 OPERATOR_ADDITIONAL_HELM_VALUES="$(get_operator_helm_values | tr ' ' ',')"
 export OPERATOR_ADDITIONAL_HELM_VALUES
 export OPERATOR_HELM_CHART="${PROJECT_DIR}/helm_chart"
+
+export AUTO_EMBEDDING_API_INDEXING_KEY="${AI_MONGODB_EMBEDDING_INDEXING_KEY}"
+export AUTO_EMBEDDING_API_QUERY_KEY="${AI_MONGODB_EMBEDDING_QUERY_KEY}"

docs/search/01-search-community-deploy/env_variables_e2e_public.sh

@@ -1 +1,4 @@
 export K8S_CTX="${CLUSTER_NAME}"
+
+export AUTO_EMBEDDING_API_INDEXING_KEY="${AI_MONGODB_EMBEDDING_INDEXING_KEY}"
+export AUTO_EMBEDDING_API_QUERY_KEY="${AI_MONGODB_EMBEDDING_QUERY_KEY}"

docs/search/01-search-community-deploy/test.sh

@@ -28,6 +28,8 @@ run 01_0310_create_mongodb_community_resource.sh
 run_for_output 01_0315_wait_for_community_resource.sh
 run 01_0320_create_mongodb_search_resource.sh
 run 01_0325_wait_for_search_resource.sh
+run 01_0322_create_auto_embed_mongodb_search_resource.sh
+run 01_0325_wait_for_search_resource.sh
 run_for_output 01_0330_wait_for_community_resource.sh
 run_for_output 01_0335_show_running_pods.sh
 

docs/search/03-search-query-usage/code_snippets/03_0437_create_auto_embed_vector_search_index.sh

@@ -0,0 +1,10 @@
+kubectl exec --context "${K8S_CTX}" -n "${MDB_NS}" mongodb-tools-pod -- \
+  mongosh --quiet "${MDB_CONNECTION_STRING}" \
+    --eval "use sample_mflix" \
+    --eval 'db.movies.createSearchIndex("vector_auto_embed_index", "vectorSearch",
+      { "fields": [ {
+        "type": "autoEmbed",
+        "modality": "text",
+        "path": "plot",
+        "model": "'"${EMBEDDING_MODEL}"'"
+      } ] });'

docs/search/03-search-query-usage/code_snippets/03_0447_list_auto_embed_vector_search_indexes.sh

@@ -0,0 +1,4 @@
+kubectl exec --context "${K8S_CTX}" -n "${MDB_NS}" mongodb-tools-pod -- \
+  mongosh --quiet "${MDB_CONNECTION_STRING}" \
+    --eval "use sample_mflix" \
+    --eval 'db.runCommand({"listSearchIndexes": "movies"});'

docs/search/03-search-query-usage/code_snippets/03_0456_execute_auto_embed_vector_search_query.sh

@@ -0,0 +1,30 @@
+mdb_script=$(cat <<'EOF'
+use sample_mflix;
+db.movies.aggregate([
+   {
+     "$vectorSearch": {
+       "index": "vector_auto_embed_index",
+       "path": "plot",
+       "query": "spy thriller",
+       "numCandidates": 150,
+       "limit": 10
+     }
+   },
+   {
+     "$project": {
+       "_id": 0,
+       "plot": 1,
+       "title": 1,
+       "score": { "$meta": "vectorSearchScore" }
+     }
+   }
+ ]);
+EOF
+)
+
+kubectl exec --context "${K8S_CTX}" -n "${MDB_NS}" \
+  mongodb-tools-pod -- /bin/bash -eu -c "$(cat <<EOF
+echo '${mdb_script}' > /tmp/mdb_script.js
+mongosh --quiet "${MDB_CONNECTION_STRING}" < /tmp/mdb_script.js
+EOF
+)"

docs/search/03-search-query-usage/test.sh

@@ -15,10 +15,23 @@ run 03_0410_run_mongodb_tools_pod.sh
 run_for_output 03_0420_import_movies_mflix_database.sh
 run 03_0430_create_search_index.sh
 run 03_0435_create_vector_search_index.sh
+# don't create auto embedding vector search if it's not community deployment.
+# since we set EMBEDDING_MODEL env var just in community, we can check that env var.
+if [ -n "${EMBEDDING_MODEL:-}" ]; then
+    run 03_0437_create_auto_embed_vector_search_index.sh
+else
+    echo "Skipping creation of autoEmbed vector search index for non community deployments."
+fi
 run_for_output 03_0440_wait_for_search_index_ready.sh
 run_for_output 03_0444_list_search_indexes.sh
 run_for_output 03_0445_list_vector_search_indexes.sh
+run_for_output 03_0447_list_auto_embed_vector_search_indexes.sh
 run_for_output 03_0450_execute_search_query.sh
 run_for_output 03_0455_execute_vector_search_query.sh
+if [ -n "${EMBEDDING_MODEL:-}" ]; then
+    run_for_output 03_0456_execute_auto_embed_vector_search_query.sh
+else
+    echo "Skipping running autoEmbed vector search query for non community deployments."
+fi
 
 cd -