feast-dev · jyejare · Jul 30, 2026 · Apr 16, 2026 · Apr 16, 2026 · Jul 24, 2026
@@ -477,6 +477,7 @@ def materialize_incremental_command(
             "milvus",
             "ray",
             "ray_rag",
+            "rag",
             "pytorch_nlp",
         ],
         case_sensitive=False,

@@ -0,0 +1,99 @@
+# City Information Q&A — RAG Demo with Feast
+
+A complete Retrieval-Augmented Generation (RAG) demo using Feast for feature management and Milvus for vector search.
+
+
+## Project Structure
+
+```
+rag/
+├── feature_repo/
+│   ├── data/
+│   │   └── city_wikipedia_summaries_with_embeddings.parquet  # Sample data (US cities)
+│   ├── example_repo.py       # Entity, Feature Views, Feature Service definitions
+│   ├── feature_store.yaml    # Feast config (Milvus online store, file offline store)
+│   └── test_workflow.py      # End-to-end demo: apply → materialize → search
+└── README.md
+```
+
+## Quick Start
+
+### 1. Initialize the template
+
+```bash
+feast init -t rag my_city_qa
+cd my_city_qa/feature_repo
+```
+
+### 2. Install dependencies
+
+```bash
+pip install feast torch transformers pymilvus
+```
+
+### 3. Apply feature definitions
+
+```bash
+feast apply
+```
+
+### 4. Explore in the Feast UI
+
+```bash
+feast ui
+```
+
+### 5. Run the demo workflow
+
+```bash
+python test_workflow.py
+```
+
+
+## Key Commands
+
+| Command | Description |
+|---------|-------------|
+| `feast apply` | Register entities, feature views, and feature services |
+| `feast materialize --disable-event-timestamp` | Load parquet data into the online store (Milvus) for vector search. Optionally add `-v city_summary_embeddings -v city_metadata` to materialize only those views. |
+| `feast feature-views list` | List registered feature views |
+| `feast entities list` | List registered entities |
+| `feast feature-services list` | List registered feature services |
+| `feast ui` | Start the Feast UI at http://localhost:8888 |
+
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│                        City Q&A Pipeline                        │
+├─────────────────────────────────────────────────────────────────┤
+│                                                                 │
+│  User Question                                                  │
+│       │                                                         │
+│       ▼                                                         │
+│  ┌─────────────┐                                                │
+│  │ Embed Query │ (MiniLM 384-dim)                               │
+│  └─────────────┘                                                │
+│       │                                                         │
+│       ▼                                                         │
+│  ┌─────────────────────────────────────┐                        │
+│  │ city_summary_embeddings (Milvus)    │ ← Vector Search        │
+│  │   - vector (COSINE similarity)      │                        │
+│  │   - sentence_chunks                 │                        │
+│  └─────────────────────────────────────┘                        │
+│       │                                                         │
+│       ▼ (top-k city_ids)                                        │
+│  ┌─────────────────────────────────────┐                        │
+│  │ city_metadata (Feast Online Store)  │ ← Metadata Lookup      │
+│  │   - state                           │                        │
+│  │   - wiki_summary                    │                        │
+│  └─────────────────────────────────────┘                        │
+│       │                                                         │
+│       ▼                                                         │
+│  ┌─────────────┐                                                │
+│  │ LLM Answer  │ (optional: GPT/Claude)                         │
+│  └─────────────┘                                                │
+│                                                                 │
+└─────────────────────────────────────────────────────────────────┘
+```
@@ -0,0 +1 @@
+
@@ -0,0 +1,56 @@
+def bootstrap():
+    # Bootstrap() is called from init_repo() during `feast init`
+    import pathlib
+    from datetime import datetime
+
+    import numpy as np
+    import pandas as pd
+
+    repo_path = pathlib.Path(__file__).parent.absolute() / "feature_repo"
+    data_path = repo_path / "data"
+    data_path.mkdir(exist_ok=True)
+
+    # Minimal city data with embeddings (384-d to match feature_store embedding_dim)
+    embedding_dim = 384
+    now = datetime.now().replace(microsecond=0, tzinfo=None)
+    cities = [
+        (
+            1,
+            "New York",
+            "New York",
+            "New York City is the most populous city in the United States.",
+        ),
+        (
+            2,
+            "Los Angeles",
+            "California",
+            "Los Angeles is the second most populous city in the United States.",
+        ),
+        (
+            3,
+            "Chicago",
+            "Illinois",
+            "Chicago is the third most populous city in the United States.",
+        ),
+    ]
+    rows = []
+    for city_id, city_name, state, wiki_summary in cities:
+        vec = np.random.randn(embedding_dim).astype(np.float32)
+        vec = (vec / np.linalg.norm(vec)).tolist()
+        rows.append(
+            {
+                "city_id": city_id,
+                "event_timestamp": pd.Timestamp(now),
+                "vector": vec,
+                "sentence_chunks": wiki_summary[:200],
+                "state": f"{city_name}, {state}",
+                "wiki_summary": wiki_summary,
+            }
+        )
+    df = pd.DataFrame(rows)
+    parquet_path = data_path / "city_wikipedia_summaries_with_embeddings.parquet"
+    df.to_parquet(path=str(parquet_path), index=False)
+
+
+if __name__ == "__main__":
+    bootstrap()
@@ -0,0 +1 @@
+
@@ -0,0 +1,137 @@
+from datetime import timedelta
+
+from feast import (
+    Entity,
+    FeatureService,
+    FeatureView,
+    Field,
+    FileSource,
+    PushSource,
+)
+from feast.data_format import ParquetFormat
+from feast.types import Array, Float32, String
+from feast.value_type import ValueType
+
+# Entity: Identifies each city document/chunk in the knowledge base
+city = Entity(
+    name="city_id",
+    value_type=ValueType.INT64,
+    description="Unique identifier for each city Wikipedia summary (document chunk ID).",
+    join_keys=["city_id"],
+)
+
+# Data Source: Parquet file containing city summaries with pre-computed embeddings
+city_summaries_source = FileSource(
+    name="city_summaries_source",
+    file_format=ParquetFormat(),
+    path="./data/city_wikipedia_summaries_with_embeddings.parquet",
+    timestamp_field="event_timestamp",
+    description="Wikipedia summaries of US cities (batch).",
+)
+
+# Push Source: same schema as batch; allows near real-time ingestion of new/updated docs
+city_summaries_push_source = PushSource(
+    name="city_summaries_push_source",
+    batch_source=city_summaries_source,
+    description="Push source for real-time updates to city summaries/embeddings.",
+)
+
+# Feature View 1: City embeddings for semantic/vector search (RAG retrieval)
+city_summary_embeddings = FeatureView(
+    name="city_summary_embeddings",
+    description="City Wikipedia summaries with embeddings for semantic search. ",
+    entities=[city],
+    schema=[
+        Field(
+            name="vector",
+            dtype=Array(Float32),
+            description="384-dimensional sentence embedding for semantic similarity search (MiniLM).",
+            vector_index=True,
+            vector_search_metric="COSINE",
+        ),
+        Field(
+            name="sentence_chunks",
+            dtype=String,
+            description="Chunked sentences from the Wikipedia summary.",
+        ),
+    ],
+    source=city_summaries_source,
+    ttl=timedelta(days=1),
+    online=True,
+    tags={"team": "ml-platform", "use_case": "city_qa", "type": "vector"},
+)
+
+# Feature View 2: City metadata for scalar lookups (no vector search)
+city_metadata = FeatureView(
+    name="city_metadata",
+    description="City metadata including state and full Wikipedia summary. ",
+    entities=[city],
+    schema=[
+        Field(
+            name="state",
+            dtype=String,
+            description="US state where the city is located (e.g., 'New York, New York').",
+        ),
+        Field(
+            name="wiki_summary",
+            dtype=String,
+            description="Full Wikipedia summary of the city.",
+        ),
+    ],
+    source=city_summaries_source,
+    ttl=timedelta(hours=2),
+    online=True,
+    tags={"team": "ml-platform", "use_case": "city_qa", "type": "metadata"},
+)
+
+# Feature View 3: Fresh embeddings (PushSource) for near real-time doc updates
+city_summary_embeddings_realtime = FeatureView(
+    name="city_summary_embeddings_realtime",
+    description="Same as city_summary_embeddings but with real-time ingestion (PushSource).",
+    entities=[city],
+    schema=[
+        Field(
+            name="vector",
+            dtype=Array(Float32),
+            description="384-dimensional sentence embedding for semantic similarity search.",
+            vector_index=True,
+            vector_search_metric="COSINE",
+        ),
+        Field(
+            name="sentence_chunks",
+            dtype=String,
+            description="Chunked sentences from the Wikipedia summary.",
+        ),
+    ],
+    source=city_summaries_push_source,
+    ttl=timedelta(hours=2),
+    online=True,
+    tags={
+        "team": "ml-platform",
+        "use_case": "city_qa",
+        "type": "vector",
+        "ingestion": "push",
+    },
+)
+
+# Feature Service: Bundles features for the City Q&A retrieval endpoint
+city_qa_v1 = FeatureService(
+    name="city_qa_v1",
+    features=[
+        city_summary_embeddings,
+        city_metadata,
+    ],
+    description="Feature service for City Information Q&A. ",
+    tags={"team": "ml-platform", "version": "v1"},
+)
+
+# Feature service that includes push-backed and request-time features
+city_qa_v2 = FeatureService(
+    name="city_qa_v2",
+    features=[
+        city_summary_embeddings_realtime,
+        city_metadata,
+    ],
+    description="City Q&A with push ingestion and request-time context (query_text, user_id).",
+    tags={"team": "ml-platform", "version": "v2"},
+)
@@ -0,0 +1,20 @@
+project: my_project
+
+project_description: |
+  This project is a smart City Q&A assistant that gives you accurate, detailed answers about any city instantly.
+provider: local
+registry: data/registry.db
+online_store:
+  type: milvus
+  path: data/online_store.db
+  vector_enabled: true
+  embedding_dim: 384
+  index_type: "FLAT"
+  metric_type: "COSINE"
+
+offline_store:
+  type: file
+entity_key_serialization_version: 3
+# By default, no_auth for authentication and authorization
+auth:
+  type: no_auth