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.

docs/source/distributions/self_hosted_distro/cerebras.md

@@ -8,7 +8,7 @@ The `llamastack/distribution-cerebras` distribution consists of the following pr
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `remote::cerebras` |
+| inference | `remote::cerebras`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |

docs/source/distributions/self_hosted_distro/dell.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-dell` distribution consists of the following provid
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `remote::tgi` |
+| inference | `remote::tgi`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |

docs/source/distributions/self_hosted_distro/fireworks.md

@@ -18,7 +18,7 @@ The `llamastack/distribution-fireworks` distribution consists of the following p
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `remote::fireworks` |
+| inference | `remote::fireworks`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |

docs/source/distributions/self_hosted_distro/ollama.md

@@ -23,7 +23,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
-| vector_io | `inline::faiss`, `inline::sqlite_vec`, `remote::chromadb`, `remote::pgvector` |
+| vector_io | `inline::sqlite-vec`, `remote::chromadb`, `remote::pgvector` |
 
 
 You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration.

docs/source/distributions/self_hosted_distro/remote-vllm.md

@@ -17,7 +17,7 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `remote::vllm` |
+| inference | `remote::vllm`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |

docs/source/distributions/self_hosted_distro/tgi.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-tgi` distribution consists of the following provide
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `remote::tgi` |
+| inference | `remote::tgi`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |

docs/source/distributions/self_hosted_distro/together.md

@@ -18,7 +18,7 @@ The `llamastack/distribution-together` distribution consists of the following pr
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
-| inference | `remote::together` |
+| inference | `remote::together`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |