LCORE-1330: vector store used for FAISS tests contains conflicting shield metadata

.github/workflows/e2e_tests.yaml

@@ -18,6 +18,7 @@ jobs:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       E2E_OPENAI_MODEL: ${{ vars.E2E_OPENAI_MODEL }}
       E2E_DEPLOYMENT_MODE: ${{ matrix.mode }}
+      FAISS_VECTOR_STORE_ID: ${{ vars.FAISS_VECTOR_STORE_ID }}
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/e2e_tests_providers.yaml

@@ -24,6 +24,7 @@ jobs:
       CLIENT_ID: ${{ secrets.CLIENT_ID }}
       TENANT_ID: ${{ secrets.TENANT_ID }}
       E2E_DEPLOYMENT_MODE: ${{ matrix.mode }}
+      FAISS_VECTOR_STORE_ID: ${{ vars.FAISS_VECTOR_STORE_ID }}
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/e2e_tests_rhaiis.yaml

@@ -18,6 +18,7 @@ jobs:
       RHAIIS_URL: ${{ secrets.RHAIIS_URL }}
       RHAIIS_API_KEY: ${{ secrets.RHAIIS_API_KEY }}
       RHAIIS_MODEL: ${{ vars.RHAIIS_MODEL }}
+      FAISS_VECTOR_STORE_ID: ${{ vars.FAISS_VECTOR_STORE_ID }}
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/e2e_tests_rhelai.yaml

@@ -18,6 +18,7 @@ jobs:
       RHEL_AI_API_KEY: ${{ secrets.RHEL_AI_API_KEY }}
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       RHEL_AI_MODEL: ${{ vars.RHEL_AI_MODEL }}
+      FAISS_VECTOR_STORE_ID: ${{ vars.FAISS_VECTOR_STORE_ID }}
 
     steps:
       - uses: actions/checkout@v4

docker-compose-library.yaml

@@ -66,6 +66,8 @@ services:
       - WATSONX_API_KEY=${WATSONX_API_KEY:-}
       # Enable debug logging if needed
       - LLAMA_STACK_LOGGING=${LLAMA_STACK_LOGGING:-}
+      # FAISS test
+      - FAISS_VECTOR_STORE_ID=${FAISS_VECTOR_STORE_ID:-}
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8080/liveness"]
       interval: 10s   # how often to run the check

docker-compose.yaml

@@ -60,6 +60,8 @@ services:
       - WATSONX_API_KEY=${WATSONX_API_KEY:-}
       # Enable debug logging if needed
       - LLAMA_STACK_LOGGING=${LLAMA_STACK_LOGGING:-}
+      # FAISS test
+      - FAISS_VECTOR_STORE_ID=${FAISS_VECTOR_STORE_ID:-}
     networks:
       - lightspeednet
     healthcheck:

tests/configuration/run.yaml

@@ -98,7 +98,7 @@ providers:
   - config:
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
 scoring_fns: []
@@ -147,4 +147,4 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model:
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2

tests/e2e-prow/rhoai/configs/run.yaml

@@ -58,7 +58,7 @@ providers:
   - config:
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
   agents:
@@ -131,6 +131,17 @@ registered_resources:
     provider_id: vllm
     model_type: llm
     provider_model_id: null
+  - model_id: all-mpnet-base-v2
+    model_type: embedding
+    provider_id: sentence-transformers
+    provider_model_id: all-mpnet-base-v2
+    metadata:
+      embedding_dimension: 768
+  vector_stores: 
+  - embedding_dimension: 768
+    embedding_model: sentence-transformers/all-mpnet-base-v2
+    provider_id: faiss
+    vector_store_id: vs_8c94967b-81cc-4028-a294-9cfac6fd9ae2 #TODO: parse this from the rag db
   shields:
   - shield_id: llama-guard
     provider_id: llama-guard
@@ -145,6 +156,6 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model:
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2
 safety:
   default_shield_id: llama-guard

tests/e2e/configs/run-azure.yaml

@@ -57,7 +57,7 @@ providers:
   - config:
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
   agents:
@@ -105,7 +105,10 @@ storage:
   backends:
     kv_default:
       type: kv_sqlite
-      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/rag/kv_store.db}
+      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db}
+    kv_rag: # Define the storage backend type for RAG
+      type: kv_sqlite
+      db_path: ${env.KV_RAG_PATH:=~/.llama/storage/rag/kv_store.db}
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db}
@@ -130,10 +133,21 @@ registered_resources:
     provider_id: azure
     model_type: llm
     provider_model_id: gpt-4o-mini
+  - model_id: all-mpnet-base-v2
+    model_type: embedding
+    provider_id: sentence-transformers
+    provider_model_id: all-mpnet-base-v2
+    metadata:
+      embedding_dimension: 768
   shields:
   - shield_id: llama-guard
     provider_id: llama-guard
     provider_shield_id: openai/gpt-4o-mini
+  vector_stores: 
+  - embedding_dimension: 768
+    embedding_model: sentence-transformers/all-mpnet-base-v2
+    provider_id: faiss
+    vector_store_id: ${env.FAISS_VECTOR_STORE_ID}
   datasets: []
   scoring_fns: []
   benchmarks: []
@@ -144,6 +158,6 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model:
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2
 safety:
   default_shield_id: llama-guard

tests/e2e/configs/run-ci.yaml

@@ -62,7 +62,7 @@ providers:
   - config: # Define the storage backend for RAG
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
   agents:
@@ -108,9 +108,12 @@ server:
   port: 8321
 storage:
   backends:
-    kv_default: # Define the storage backend type for RAG, in this case registry and RAG are unified i.e. information on registered resources (e.g. models, vector_stores) are saved together with the RAG chunks
+    kv_default:
+      type: kv_sqlite
+      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db}
+    kv_rag: # Define the storage backend type for RAG
       type: kv_sqlite
-      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/rag/kv_store.db}
+      db_path: ${env.KV_RAG_PATH:=~/.llama/storage/rag/kv_store.db}
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db}
@@ -131,22 +134,21 @@ storage:
       backend: kv_default
 registered_resources:
   models:
-  - model_id: sentence-transformers/all-mpnet-base-v2
+  - model_id: all-mpnet-base-v2
     model_type: embedding
     provider_id: sentence-transformers
-    provider_model_id: sentence-transformers/all-mpnet-base-v2
+    provider_model_id: all-mpnet-base-v2
     metadata:
       embedding_dimension: 768
-  # Commented out because the vector_store is already registered in the kv_store
-  # vector_stores: 
-  # - embedding_dimension: 768
-  #   embedding_model: sentence-transformers/nomic-ai/nomic-embed-text-v1.5
-  #   provider_id: faiss
-  #   vector_store_id: vs_503a2261-c256-45ff-90aa-580a80de64b8
   shields:
   - shield_id: llama-guard
     provider_id: llama-guard
     provider_shield_id: openai/gpt-4o-mini
+  vector_stores: 
+  - embedding_dimension: 768
+    embedding_model: sentence-transformers/all-mpnet-base-v2
+    provider_id: faiss
+    vector_store_id: ${env.FAISS_VECTOR_STORE_ID}
   datasets: []
   scoring_fns: []
   benchmarks: []
@@ -157,6 +159,6 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model: # Define the default embedding model for RAG
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2
 safety:
   default_shield_id: llama-guard

tests/e2e/configs/run-rhaiis.yaml

@@ -58,7 +58,7 @@ providers:
   - config:
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
   agents:
@@ -106,7 +106,10 @@ storage:
   backends:
     kv_default:
       type: kv_sqlite
-      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/rag/kv_store.db}
+      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db}
+    kv_rag: # Define the storage backend type for RAG
+      type: kv_sqlite
+      db_path: ${env.KV_RAG_PATH:=~/.llama/storage/rag/kv_store.db}
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db}
@@ -131,10 +134,21 @@ registered_resources:
     provider_id: vllm
     model_type: llm
     provider_model_id: ${env.RHAIIS_MODEL}
+  - model_id: all-mpnet-base-v2
+    model_type: embedding
+    provider_id: sentence-transformers
+    provider_model_id: all-mpnet-base-v2
+    metadata:
+      embedding_dimension: 768
   shields:
   - shield_id: llama-guard
     provider_id: llama-guard
     provider_shield_id: openai/gpt-4o-mini
+  vector_stores: 
+  - embedding_dimension: 768
+    embedding_model: sentence-transformers/all-mpnet-base-v2
+    provider_id: faiss
+    vector_store_id: ${env.FAISS_VECTOR_STORE_ID}
   datasets: []
   scoring_fns: []
   benchmarks: []
@@ -145,6 +159,6 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model:
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2
 safety:
   default_shield_id: llama-guard

tests/e2e/configs/run-rhelai.yaml

@@ -58,7 +58,7 @@ providers:
   - config:
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
   agents:
@@ -106,7 +106,10 @@ storage:
   backends:
     kv_default:
       type: kv_sqlite
-      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/rag/kv_store.db}
+      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db}
+    kv_rag: # Define the storage backend type for RAG
+      type: kv_sqlite
+      db_path: ${env.KV_RAG_PATH:=~/.llama/storage/rag/kv_store.db}
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db}
@@ -131,10 +134,21 @@ registered_resources:
     provider_id: vllm
     model_type: llm
     provider_model_id: ${env.RHEL_AI_MODEL}
+  - model_id: all-mpnet-base-v2
+    model_type: embedding
+    provider_id: sentence-transformers
+    provider_model_id: all-mpnet-base-v2
+    metadata:
+      embedding_dimension: 768
   shields:
   - shield_id: llama-guard
     provider_id: llama-guard
     provider_shield_id: openai/gpt-4o-mini
+  vector_stores: 
+  - embedding_dimension: 768
+    embedding_model: sentence-transformers/all-mpnet-base-v2
+    provider_id: faiss
+    vector_store_id: ${env.FAISS_VECTOR_STORE_ID}
   datasets: []
   scoring_fns: []
   benchmarks: []
@@ -145,6 +159,6 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model:
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2
 safety:
   default_shield_id: llama-guard

tests/e2e/configs/run-vertexai.yaml

@@ -57,7 +57,7 @@ providers:
   - config:
       persistence:
         namespace: vector_io::faiss
-        backend: kv_default
+        backend: kv_rag
     provider_id: faiss
     provider_type: inline::faiss
   agents:
@@ -105,7 +105,10 @@ storage:
   backends:
     kv_default:
       type: kv_sqlite
-      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/rag/kv_store.db}
+      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db}
+    kv_rag: # Define the storage backend type for RAG
+      type: kv_sqlite
+      db_path: ${env.KV_RAG_PATH:=~/.llama/storage/rag/kv_store.db}
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db}
@@ -125,11 +128,22 @@ storage:
       namespace: prompts
       backend: kv_default
 registered_resources:
-  models: []
+  models:
+  - model_id: all-mpnet-base-v2
+    model_type: embedding
+    provider_id: sentence-transformers
+    provider_model_id: all-mpnet-base-v2
+    metadata:
+      embedding_dimension: 768
   shields:
   - shield_id: llama-guard
     provider_id: llama-guard
     provider_shield_id: openai/gpt-4o-mini
+  vector_stores: 
+  - embedding_dimension: 768
+    embedding_model: sentence-transformers/all-mpnet-base-v2
+    provider_id: faiss
+    vector_store_id: ${env.FAISS_VECTOR_STORE_ID}
   datasets: []
   scoring_fns: []
   benchmarks: []
@@ -140,6 +154,6 @@ vector_stores:
   default_provider_id: faiss
   default_embedding_model:
     provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
+    model_id: all-mpnet-base-v2
 safety:
   default_shield_id: llama-guard