[memory refactor][5/n] Migrate all vector_io providers (#835)

See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.

This PR finishes off all the stragglers and migrates everything to the
new naming.

llama_stack/templates/bedrock/bedrock.py

@@ -10,7 +10,7 @@ from llama_models.sku_list import all_registered_models
 
 from llama_stack.apis.models import ModelInput
 from llama_stack.distribution.datatypes import Provider, ToolGroupInput
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.bedrock.bedrock import MODEL_ALIASES
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -18,7 +18,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::bedrock"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["remote::bedrock"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -34,7 +34,7 @@ def get_distribution_template() -> DistributionTemplate:
         ],
     }
     name = "bedrock"
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -78,7 +78,7 @@ def get_distribution_template() -> DistributionTemplate:
         run_configs={
             "run.yaml": RunConfigSettings(
                 provider_overrides={
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=default_models,
                 default_tool_groups=default_tool_groups,

llama_stack/templates/bedrock/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::bedrock
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/bedrock/run.yaml

@@ -5,17 +5,17 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -104,7 +104,7 @@ models:
   provider_model_id: meta.llama3-1-405b-instruct-v1:0
   model_type: llm
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/cerebras/build.yaml

@@ -6,7 +6,7 @@ distribution_spec:
     - remote::cerebras
     safety:
     - inline::llama-guard
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/cerebras/cerebras.py

@@ -13,7 +13,7 @@ from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupIn
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
 from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@@ -23,7 +23,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::cerebras"],
         "safety": ["inline::llama-guard"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "agents": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],
         "datasetio": ["remote::huggingface", "inline::localfs"],
@@ -68,7 +68,7 @@ def get_distribution_template() -> DistributionTemplate:
             "embedding_dimension": 384,
         },
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -100,7 +100,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=default_models + [embedding_model],
                 default_shields=[],

llama_stack/templates/cerebras/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: cerebras
@@ -24,7 +24,7 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -106,7 +106,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/experimental-post-training/run.yaml

@@ -60,7 +60,7 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -82,7 +82,7 @@ metadata_store:
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
 models: []
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/fireworks/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::fireworks
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/fireworks/fireworks.py

@@ -18,7 +18,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
 from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@@ -27,7 +27,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::fireworks"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -107,7 +107,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=default_models + [embedding_model],
                 default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
@@ -119,7 +119,7 @@ def get_distribution_template() -> DistributionTemplate:
                         inference_provider,
                         embedding_provider,
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                     "safety": [
                         Provider(
                             provider_id="llama-guard",

llama_stack/templates/fireworks/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: fireworks
@@ -20,7 +20,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -161,7 +161,7 @@ shields:
   provider_id: llama-guard-vision
 - shield_id: CodeScanner
   provider_id: code-scanner
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/fireworks/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: fireworks
@@ -20,7 +20,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -150,7 +150,7 @@ models:
   model_type: embedding
 shields:
 - shield_id: meta-llama/Llama-Guard-3-8B
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/hf-endpoint/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::hf::endpoint
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.tgi import InferenceEndpointImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -22,7 +22,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::hf::endpoint"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -48,7 +48,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -97,7 +97,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -115,7 +115,7 @@ def get_distribution_template() -> DistributionTemplate:
                             ),
                         ),
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[
                     inference_model,

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: hf-endpoint
@@ -25,7 +25,7 @@ providers:
     config:
       endpoint_name: ${env.SAFETY_INFERENCE_ENDPOINT_NAME}
       api_token: ${env.HF_API_TOKEN}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -113,7 +113,7 @@ models:
   model_type: embedding
 shields:
 - shield_id: ${env.SAFETY_MODEL}
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/hf-endpoint/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: hf-endpoint
@@ -20,7 +20,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -103,7 +103,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/hf-serverless/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::hf::serverless
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/hf-serverless/hf_serverless.py

@@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.tgi import InferenceAPIImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -22,7 +22,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::hf::serverless"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -49,7 +49,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -98,7 +98,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -116,7 +116,7 @@ def get_distribution_template() -> DistributionTemplate:
                             ),
                         ),
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[
                     inference_model,

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: hf-serverless
@@ -25,7 +25,7 @@ providers:
     config:
       huggingface_repo: ${env.SAFETY_MODEL}
       api_token: ${env.HF_API_TOKEN}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -113,7 +113,7 @@ models:
   model_type: embedding
 shields:
 - shield_id: ${env.SAFETY_MODEL}
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/hf-serverless/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: hf-serverless
@@ -20,7 +20,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -103,7 +103,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/meta-reference-gpu/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - inline::meta-reference
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -19,14 +19,14 @@ from llama_stack.providers.inline.inference.meta_reference import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
 
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["inline::meta-reference"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -103,7 +103,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -122,7 +122,7 @@ def get_distribution_template() -> DistributionTemplate:
                             ),
                         ),
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[
                     inference_model,

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: meta-reference-inference
@@ -27,7 +27,7 @@ providers:
       model: ${env.SAFETY_MODEL}
       max_seq_len: 4096
       checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:null}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -115,7 +115,7 @@ models:
   model_type: embedding
 shields:
 - shield_id: ${env.SAFETY_MODEL}
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: meta-reference-inference
@@ -21,7 +21,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -104,7 +104,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - inline::meta-reference-quantized
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py

@@ -14,14 +14,14 @@ from llama_stack.providers.inline.inference.meta_reference import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
 
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["inline::meta-reference-quantized"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -64,7 +64,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -93,7 +93,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: meta-reference-inference
@@ -23,7 +23,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -106,7 +106,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/nvidia/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::nvidia
-    memory:
+    vector_io:
     - inline::faiss
     safety:
     - inline::llama-guard

llama_stack/templates/nvidia/nvidia.py

@@ -17,7 +17,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::nvidia"],
-        "memory": ["inline::faiss"],
+        "vector_io": ["inline::faiss"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],

llama_stack/templates/nvidia/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: nvidia
@@ -17,7 +17,7 @@ providers:
     config:
       url: https://integrate.api.nvidia.com
       api_key: ${env.NVIDIA_API_KEY}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -136,7 +136,7 @@ models:
   provider_model_id: meta/llama-3.2-90b-vision-instruct
   model_type: llm
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/ollama/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::ollama
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/ollama/ollama.py

@@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -24,7 +24,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::ollama"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -49,7 +49,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -98,7 +98,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -109,7 +109,7 @@ def get_distribution_template() -> DistributionTemplate:
                         inference_provider,
                         embedding_provider,
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                     "safety": [
                         Provider(
                             provider_id="llama-guard",

llama_stack/templates/ollama/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: ollama
@@ -19,7 +19,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -110,7 +110,7 @@ shields:
   provider_id: llama-guard
 - shield_id: CodeScanner
   provider_id: code-scanner
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/ollama/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: ollama
@@ -19,7 +19,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -99,7 +99,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/remote-vllm/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::vllm
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: vllm-inference
@@ -27,7 +27,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -115,7 +115,7 @@ models:
   model_type: embedding
 shields:
 - shield_id: ${env.SAFETY_MODEL}
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/remote-vllm/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: vllm-inference
@@ -21,7 +21,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -104,7 +104,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/remote-vllm/vllm.py

@@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -24,7 +24,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::vllm"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],
@@ -52,7 +52,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -100,7 +100,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -118,7 +118,7 @@ def get_distribution_template() -> DistributionTemplate:
                         ),
                         embedding_provider,
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[
                     inference_model,

llama_stack/templates/tgi/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - remote::tgi
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/tgi/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: tgi-inference
@@ -20,7 +20,7 @@ providers:
     provider_type: remote::tgi
     config:
       url: ${env.TGI_SAFETY_URL}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -103,7 +103,7 @@ models:
   model_type: llm
 shields:
 - shield_id: ${env.SAFETY_MODEL}
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/tgi/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: tgi-inference
@@ -19,7 +19,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -102,7 +102,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/tgi/tgi.py

@@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.tgi import TGIImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -24,7 +24,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::tgi"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -52,7 +52,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::sentence-transformers",
         config=SentenceTransformersInferenceConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -101,7 +101,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -118,7 +118,7 @@ def get_distribution_template() -> DistributionTemplate:
                             ),
                         ),
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[
                     inference_model,

llama_stack/templates/together/run-with-safety.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: together
@@ -20,7 +20,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -156,7 +156,7 @@ shields:
   provider_id: llama-guard-vision
 - shield_id: CodeScanner
   provider_id: code-scanner
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/together/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- vector_io
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: together
@@ -145,6 +145,7 @@ models:
   model_type: embedding
 shields:
 - shield_id: meta-llama/Llama-Guard-3-8B
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/together/together.py

@@ -18,7 +18,7 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.together import TogetherImplConfig
 from llama_stack.providers.remote.inference.together.together import MODEL_ALIASES
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@@ -27,7 +27,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::together"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -48,7 +48,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="remote::together",
         config=TogetherImplConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -105,7 +105,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=default_models + [embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -117,7 +117,7 @@ def get_distribution_template() -> DistributionTemplate:
                         inference_provider,
                         embedding_provider,
                     ],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                     "safety": [
                         Provider(
                             provider_id="llama-guard",

llama_stack/templates/vllm-gpu/build.yaml

@@ -4,7 +4,7 @@ distribution_spec:
   providers:
     inference:
     - inline::vllm
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector

llama_stack/templates/vllm-gpu/run.yaml

@@ -5,11 +5,11 @@ apis:
 - datasetio
 - eval
 - inference
-- memory
 - safety
 - scoring
 - telemetry
 - tool_runtime
+- vector_io
 providers:
   inference:
   - provider_id: vllm
@@ -23,7 +23,7 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -106,7 +106,7 @@ models:
   provider_id: sentence-transformers
   model_type: embedding
 shields: []
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []

llama_stack/templates/vllm-gpu/vllm.py

@@ -10,7 +10,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
 from llama_stack.providers.inline.inference.vllm import VLLMConfig
-from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
 from llama_stack.templates.template import (
     DistributionTemplate,
     RunConfigSettings,
@@ -21,7 +21,7 @@ from llama_stack.templates.template import (
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["inline::vllm"],
-        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -43,7 +43,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="inline::vllm",
         config=VLLMConfig.sample_run_config(),
     )
-    memory_provider = Provider(
+    vector_io_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
         config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@@ -93,7 +93,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
-                    "memory": [memory_provider],
+                    "vector_io": [vector_io_provider],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,