chore: move embedding deps to RAG tool where they are needed (#1210)

`EMBEDDING_DEPS` were wrongly associated with `vector_io` providers. They are needed by https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/utils/memory/vector_store.py#L142 and related code and is used by the RAG tool and as such should only be needed by the `inline::rag-runtime` provider.
2025-06-28 02:53:30 +00:00 · 2025-02-21 11:33:41 -08:00 · 2025-02-21 11:33:41 -08:00 · 992f865b2e
commit 992f865b2e
parent 11697f85c5
34 changed files with 85 additions and 132 deletions
--- a/llama_stack/templates/cerebras/build.yaml
+++ b/llama_stack/templates/cerebras/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - remote::cerebras
+    - inline::sentence-transformers
    safety:
    - inline::llama-guard
    vector_io:
--- a/llama_stack/templates/cerebras/cerebras.py
+++ b/llama_stack/templates/cerebras/cerebras.py
@ -20,7 +20,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::cerebras"],
+        "inference": ["remote::cerebras", "inline::sentence-transformers"],
        "safety": ["inline::llama-guard"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/dell/build.yaml
+++ b/llama_stack/templates/dell/build.yaml
@ -5,6 +5,7 @@ distribution_spec:
  providers:
    inference:
    - remote::tgi
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/dell/dell.py
+++ b/llama_stack/templates/dell/dell.py
@ -20,7 +20,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::tgi"],
+        "inference": ["remote::tgi", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/fireworks/build.yaml
+++ b/llama_stack/templates/fireworks/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - remote::fireworks
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/fireworks/fireworks.py
+++ b/llama_stack/templates/fireworks/fireworks.py
@ -25,7 +25,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::fireworks"],
+        "inference": ["remote::fireworks", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/hf-serverless/build.yaml
+++ b/llama_stack/templates/hf-serverless/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - remote::hf::serverless
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/hf-serverless/hf_serverless.py
+++ b/llama_stack/templates/hf-serverless/hf_serverless.py
@ -21,7 +21,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::hf::serverless"],
+        "inference": ["remote::hf::serverless", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/ollama/build.yaml
+++ b/llama_stack/templates/ollama/build.yaml
@ -5,8 +5,7 @@ distribution_spec:
    inference:
    - remote::ollama
    vector_io:
-    - inline::faiss
-    - inline::sqlite_vec
+    - inline::sqlite-vec
    - remote::chromadb
    - remote::pgvector
    safety:
--- a/llama_stack/templates/ollama/ollama.py
+++ b/llama_stack/templates/ollama/ollama.py
@ -13,10 +13,6 @@ from llama_stack.distribution.datatypes import (
    ShieldInput,
    ToolGroupInput,
 )
-from llama_stack.providers.inline.inference.sentence_transformers import (
-    SentenceTransformersInferenceConfig,
-)
-from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
 from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -25,7 +21,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
    providers = {
        "inference": ["remote::ollama"],
-        "vector_io": ["inline::faiss", "inline::sqlite_vec", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
        "telemetry": ["inline::meta-reference"],
@ -45,19 +41,9 @@ def get_distribution_template() -> DistributionTemplate:
        provider_type="remote::ollama",
        config=OllamaImplConfig.sample_run_config(),
    )
-    embedding_provider = Provider(
-        provider_id="sentence-transformers",
-        provider_type="inline::sentence-transformers",
-        config=SentenceTransformersInferenceConfig.sample_run_config(),
-    )
-    vector_io_provider_faiss = Provider(
-        provider_id="faiss",
-        provider_type="inline::faiss",
-        config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
-    )
    vector_io_provider_sqlite = Provider(
-        provider_id="sqlite_vec",
-        provider_type="inline::sqlite_vec",
+        provider_id="sqlite-vec",
+        provider_type="inline::sqlite-vec",
        config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
    )

@ -104,19 +90,16 @@ def get_distribution_template() -> DistributionTemplate:
        run_configs={
            "run.yaml": RunConfigSettings(
                provider_overrides={
-                    "inference": [inference_provider, embedding_provider],
-                    "vector_io": [vector_io_provider_faiss, vector_io_provider_sqlite],
+                    "inference": [inference_provider],
+                    "vector_io": [vector_io_provider_sqlite],
                },
-                default_models=[inference_model, embedding_model],
+                default_models=[inference_model],
                default_tool_groups=default_tool_groups,
            ),
            "run-with-safety.yaml": RunConfigSettings(
                provider_overrides={
-                    "inference": [
-                        inference_provider,
-                        embedding_provider,
-                    ],
-                    "vector_io": [vector_io_provider_faiss, vector_io_provider_faiss],
+                    "inference": [inference_provider],
+                    "vector_io": [vector_io_provider_sqlite],
                    "safety": [
                        Provider(
                            provider_id="llama-guard",
--- a/llama_stack/templates/ollama/run-with-safety.yaml
+++ b/llama_stack/templates/ollama/run-with-safety.yaml
@ -16,24 +16,11 @@ providers:
    provider_type: remote::ollama
    config:
      url: ${env.OLLAMA_URL:http://localhost:11434}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-    config: {}
  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
+      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@ -16,19 +16,9 @@ providers:
    provider_type: remote::ollama
    config:
      url: ${env.OLLAMA_URL:http://localhost:11434}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-    config: {}
  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
-  - provider_id: sqlite_vec
-    provider_type: inline::sqlite_vec
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
    config:
      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
  safety:
@ -97,12 +87,6 @@ models:
  model_id: ${env.INFERENCE_MODEL}
  provider_id: ollama
  model_type: llm
- metadata:
-    embedding_dimension: 384
-  model_id: all-MiniLM-L6-v2
-  provider_id: ollama
-  provider_model_id: all-minilm:latest
-  model_type: embedding
 shields: []
 vector_dbs: []
 datasets: []
--- a/llama_stack/templates/remote-vllm/build.yaml
+++ b/llama_stack/templates/remote-vllm/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - remote::vllm
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/remote-vllm/vllm.py
+++ b/llama_stack/templates/remote-vllm/vllm.py
@ -23,7 +23,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::vllm"],
+        "inference": ["remote::vllm", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/tgi/build.yaml
+++ b/llama_stack/templates/tgi/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - remote::tgi
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/tgi/tgi.py
+++ b/llama_stack/templates/tgi/tgi.py
@ -23,7 +23,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::tgi"],
+        "inference": ["remote::tgi", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/together/build.yaml
+++ b/llama_stack/templates/together/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - remote::together
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/together/together.py
+++ b/llama_stack/templates/together/together.py
@ -25,7 +25,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::together"],
+        "inference": ["remote::together", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
--- a/llama_stack/templates/vllm-gpu/build.yaml
+++ b/llama_stack/templates/vllm-gpu/build.yaml
@ -4,6 +4,7 @@ distribution_spec:
  providers:
    inference:
    - inline::vllm
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
--- a/llama_stack/templates/vllm-gpu/vllm.py
+++ b/llama_stack/templates/vllm-gpu/vllm.py
@ -20,7 +20,7 @@ from llama_stack.templates.template import (

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["inline::vllm"],
+        "inference": ["inline::vllm", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],