docs: Add rag-retriever example link to docs (feast-dev#5465)

Signed-off-by: Fiona Waters <[email protected]>

Author: Fiona-Waters

docs/SUMMARY.md

@@ -53,6 +53,7 @@
 * [Validating historical features with Great Expectations](tutorials/validating-historical-features.md)
 * [Building streaming features](tutorials/building-streaming-features.md)
 * [Retrieval Augmented Generation (RAG) with Feast](tutorials/rag-with-docling.md)
+* [RAG Fine Tuning with Feast and Milvus](../examples/rag-retriever/README.md)
 * [MCP - AI Agent Example](../examples/mcp_feature_store/README.md)
 
 ## How-to Guides

docs/getting-started/genai.md

@@ -156,6 +156,7 @@ For more detailed information and examples:
 
 * [Vector Database Reference](../reference/alpha-vector-database.md)
 * [RAG Tutorial with Docling](../tutorials/rag-with-docling.md)
+* [RAG Fine Tuning with Feast and Milvus](../../examples/rag-retriever/README.md)
 * [Milvus Quickstart Example](https://github.com/feast-dev/feast/tree/master/examples/rag/milvus-quickstart.ipynb)
 * [MCP Feature Store Example](../../examples/mcp_feature_store/)
 * [MCP Feature Server Reference](../reference/feature-servers/mcp-feature-server.md)

examples/README.md

@@ -12,6 +12,7 @@ The following examples illustrate various **Feast** use cases to enhance underst
 1. **[Remote Offline Store](remote-offline-store)**: Demonstrates how to set up and use a remote offline store.
 1. **[Podman/Podman Compose Local](podman_local)**: Demonstrates how to deploy Feast remote server components using Podman Compose locally.
 1. **[RHOAI Feast Demo](rhoai-quickstart)**: Showcases Feast's core functionality using a Jupyter notebook, including fetching online feature data from a remote server and retrieving metadata from a remote registry.
+1. **[RAG Fine Tuning with Feast and Milvus](rag-retriever)**: Demonstrates end-to-end RAG fine-tuning using Feast and Milvus, including data preparation, embedding generation, feature store setup, and RAG system implementation with custom FeastRagRetriever.
 
 # Feast Operator Examples
 

examples/rag-retriever/README.md

@@ -1,10 +1,10 @@
-# End-to-end RAG example using Feast and Milvus.
+# End-to-end RAG Fine Tuning example using Feast and Milvus.
 
 ## Introduction
-This example notebook provides a step-by-step demonstration of building and using a RAG system with Feast Feature Store and the custom FeastRagRetriever. The notebook walks through:
+This example notebook provides a step-by-step demonstration of building and using a RAG system with Feast and the custom FeastRagRetriever. The notebook walks through:
 
 1. Data Preparation
-   - Loads a subset of the Wikipedia DPR dataset (1% of training data)
+   - Loads a subset of the [Wikipedia DPR dataset](https://huggingface.co/datasets/facebook/wiki_dpr) (1% of training data)
    - Implements text chunking with configurable chunk size and overlap
    - Processes text into manageable passages with unique IDs
 
@@ -49,7 +49,7 @@ Navigate to the examples/rag-retriever directory. Here you will find the followi
   This is the Feast feature repository configuration that defines the schema and data source for Wikipedia passage embeddings. 
 
 * **__rag_feast.ipynb__**
-  This is a notebook demonstrating the implementation of a RAG system using Feast feature store. The notebook provides:
+  This is a notebook demonstrating the implementation of a RAG system using Feast. The notebook provides:
 
   - A complete end-to-end example of building a RAG system with:
     - Data preparation using the Wiki DPR dataset

sdk/python/feast/rag_retriever.py

@@ -63,6 +63,8 @@ def __init__(
             generator_tokenizer: Tokenizer for the generator model
             generator_model: The generator model
             feast_repo_path: Path to the Feast repository
+            feature_view: Feast FeatureView containing the document data
+            features: List of feature names to use from the feature view
             search_type: Type of search to perform (text, vector, or hybrid)
             config: Configuration for the retriever
             index: Index instance (must be FeastIndex)
@@ -141,7 +143,7 @@ def retrieve(  # type: ignore [override]
         Args:
             question_hidden_states (np.ndarray):
                 Hidden state representation of the question from the encoder.
-                Expected shape is (1, seq_len, hidden_dim).
+                Expected shape is (batch_size, seq_len, hidden_dim).
             n_docs (int):
                 Number of top documents to retrieve.
             query (Optional[str]):
@@ -151,11 +153,12 @@ def retrieve(  # type: ignore [override]
         Returns:
             Tuple containing:
                 - retrieved_doc_embeds (np.ndarray):
-                    Embeddings of the retrieved documents with shape (1, n_docs, embed_dim).
-                - doc_ids (list[str]):
-                    List of document IDs or passage identifiers.
-                - doc_dicts (list[dict[str, str]]):
-                    List of dictionaries containing document text fields.
+                    Embeddings of the retrieved documents with shape (batch_size, n_docs, embed_dim).
+                - doc_ids (np.ndarray):
+                    Array of document IDs or passage identifiers with shape (batch_size, n_docs).
+                - doc_dicts (list[dict]):
+                    List of dictionaries containing document metadata and text.
+                    Each dictionary has keys "text", "id", and "title".
         """
 
         batch_size = question_hidden_states.shape[0]