LCORE-1037: address review nits in BYOK and RAG guides (#1842)

- Replace pdm with uv for embedding model download command
- Remove unnecessary OpenAI API key note
- Fix Ollama section: clarify no tool RAG but inline RAG supported
- Remove empty References section from RAG guide
- Fix incorrect embedding dimensions for all-mpnet-base-v2 (768, not 1024/384)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

Author: are-ces

docs/byok_guide.md

@@ -161,7 +161,7 @@ You can use the embedding generation step mentioned in the rag-content repo:
 
 ```bash
 mkdir ./embeddings_model
-pdm run python ./scripts/download_embeddings_model.py -l ./embeddings_model/ -r sentence-transformers/all-mpnet-base-v2 
+uv run python ./scripts/download_embeddings_model.py -l ./embeddings_model/ -r sentence-transformers/all-mpnet-base-v2
 ```
 
 #### Option 2: Manual Download and Configuration
@@ -340,10 +340,6 @@ rag:
     - company-docs
 ```
 
-> [!NOTE]
-> Your LLM inference provider (e.g., OpenAI, vLLM) must also be configured in your `run.yaml`.
-> For OpenAI, set the `OPENAI_API_KEY` environment variable.
-
 ### Example 2: Multiple Knowledge Sources with pgvector
 
 A configuration combining a local FAISS store (via `byok_rag`) with a remote pgvector store (configured directly in the Llama Stack configuration file):

docs/rag_guide.md

@@ -223,11 +223,7 @@ Not yet supported.
 
 ### Ollama
 
-The `remote::ollama` provider can be used for inference. However, it does not support tool calling, including RAG.  
-While Ollama also exposes an OpenAI compatible endpoint that supports tool calling, it cannot currently be used due to limitations in the `remote::openai` provider. 
-
-Tool calling with Ollama is not yet supported.  
-Currently, tool calling is not supported out of the box. Some experimental patches exist (including internal workarounds), but these are not officially released.  
+The `remote::ollama` provider does not support tool calling, so RAG as a tool is not available. However, inline RAG is supported.
 
 ### vLLM Mistral
 
@@ -386,7 +382,3 @@ You are a helpful assistant with access to a 'knowledge_search' tool. When users
 
 The top-level `vector_stores` block in [`run.yaml`](../examples/run.yaml) may include `annotation_prompt_params` to control whether extra RAG annotation instructions are injected into the model prompt (for example, citation-style markers). The default configuration sets `enable_annotations: false` under that block to avoid unwanted annotations.
 
----
-
-# References
-

examples/lightspeed-stack-byok-okp-rag.yaml

@@ -38,14 +38,14 @@ byok_rag:
   - rag_id: ocp-docs           # referenced in rag.inline / rag.tool
     rag_type: inline::faiss
     embedding_model: sentence-transformers/all-mpnet-base-v2
-    embedding_dimension: 1024
+    embedding_dimension: 768
     vector_db_id: vs_123       # Vector store ID (from index generation)
     db_path: /tmp/ocp.faiss
     score_multiplier: 1.0      # Weight for this vector store's results (Inline RAG only)
   - rag_id: knowledge-base     # referenced in rag.inline / rag.tool
     rag_type: inline::faiss
     embedding_model: sentence-transformers/all-mpnet-base-v2
-    embedding_dimension: 384
+    embedding_dimension: 768
     vector_db_id: vs_456       # Vector store ID (from index generation)
     db_path: /tmp/kb.faiss
     score_multiplier: 1.2      # Weight for this vector store's results (Inline RAG only)