feast-dev
@@ -205,7 +205,10 @@
 * [\[Beta\] On demand feature view](reference/beta-on-demand-feature-view.md)
 * [\[Alpha\] Static Artifacts Loading](reference/alpha-static-artifacts.md)
 * [\[Alpha\] Vector Database](reference/alpha-vector-database.md)
+* [\[Alpha\] OpenAI-Compatible Vector Store API](reference/alpha-vector-database.md#alpha-openai-compatible-vector-store-api)
+
 * [Data Quality Monitoring](reference/dqm.md)
+* [\[Deprecated\] Data quality monitoring (Great Expectations)](reference/dqm.md)
 * [\[Alpha\] Streaming feature computation with Denormalized](reference/denormalized.md)
 * [\[Alpha\] Feature View Versioning](reference/alpha-feature-view-versioning.md)
 * [OpenLineage Integration](reference/openlineage.md)

@@ -37,6 +37,8 @@ The Feature Server operates as a stateless service backed by two key components:
 | `/push`                      | Pushes feature data to the online and/or offline store.                 |
 | `/materialize`               | Materializes features within a specific time range to the online store. |
 | `/materialize-incremental`   | Incrementally materializes features up to the current timestamp.        |
-| `/retrieve-online-documents` | Supports Vector Similarity Search for RAG (Alpha end-ponit)             |
+| `/search` | Vector similarity search for RAG (Alpha endpoint) |
+| `/v1/vector_stores/{id}/search` | OpenAI-compatible vector search with server-side embedding |
+| `/retrieve-online-documents` | **Deprecated.** Use `/search` instead. |
 | `/docs`                      | API Contract for available endpoints                                    | 
 
@@ -226,7 +226,8 @@ The MCP integration uses the `fastapi_mcp` library to automatically transform yo
 The fastapi_mcp integration automatically exposes your Feast feature server's FastAPI endpoints as MCP tools. This means AI assistants can:
 
 * **Call `/get-online-features`** to retrieve features from the feature store
-* **Call `/retrieve-online-documents`** to perform vector similarity search
+* **Call `/search`** to perform vector similarity search (`/retrieve-online-documents` is a deprecated alias)
+* **Call `/v1/vector_stores/{feature_view}/search`** for OpenAI-compatible text search with server-side embedding
 * **Call `/write-to-online-store`** to persist agent state (memory, notes, interaction history)
 * **Use `/health`** to check server status  
 

@@ -33,6 +33,240 @@ backwards compatibility and the adopt industry standard naming conventions.
 
 **Note**: Milvus, SQLite, and ScyllaDB implement the v2 `retrieve_online_documents_v2` method in the SDK. This will be the longer-term solution so that Data Scientists can easily enable vector similarity search by just flipping a flag.
 
+## Feature server search endpoints
+
+| Endpoint | Use when |
+|----------|----------|
+| `POST /search` | You have an embedding vector (or use `api_version: 2` with `query_string`) and want Feast's native online-features response format. |
+| `GET /v1/vector_stores` | You want to discover available vector stores and their `vs_{hash}` IDs (OpenAI-compatible). |
+| `GET /v1/vector_stores/{id}` | You want metadata for a specific vector store (OpenAI-compatible). |
+| `POST /v1/vector_stores/{id}/search` | You want plain-text queries with server-side embedding and an OpenAI-compatible response. |
+
+`POST /retrieve-online-documents` is deprecated; use `POST /search` instead.
+
+## [Alpha] OpenAI-Compatible Vector Store API
+
+{% hint style="warning" %}
+**Alpha feature.** This API surface is functional and tested, but may change in future releases. Feedback and contributions are welcome.
+{% endhint %}
+
+Feast exposes a set of [OpenAI-compatible vector store endpoints](https://platform.openai.com/docs/api-reference/vector-stores) that let clients discover, inspect, and search vector stores using plain text queries with server-side embedding. This enables integration with AI agents, LLM tool-calling frameworks, and any OpenAI-compatible client without requiring the caller to produce raw embedding vectors.
+
+### Vector store IDs
+
+Each feature view with at least one `vector_index=True` field is automatically assigned a deterministic identifier of the form `vs_{hash}`, where `{hash}` is the first 24 characters of `SHA-256(project + ":" + feature_view_name)`. These IDs are stable across server restarts and registry refreshes.
+
+For example, a feature view named `product_catalog` in project `my_project` always maps to the same `vs_...` identifier. The listing endpoints return these IDs so clients can discover stores at runtime.
+
+### Endpoints
+
+| Method | Path | Permission | Description |
+|--------|------|------------|-------------|
+| `GET` | `/v1/vector_stores` | `DESCRIBE` | List all vector stores the caller has access to |
+| `GET` | `/v1/vector_stores/{vector_store_id}` | `DESCRIBE` | Get metadata for a single vector store |
+| `POST` | `/v1/vector_stores/{vector_store_id}/search` | `READ_ONLINE` | Search a vector store with a plain text query |
+
+All endpoints enforce RBAC when authentication is configured. The listing endpoint filters out stores the caller cannot `DESCRIBE`.
+
+### Requirements
+
+1. **Embedding model** — an `embedding_model` section in `feature_store.yaml`. Feast uses [Sentence Transformers](https://www.sbert.net/) by default for local embedding — no external API key required (`pip install sentence-transformers`):
+
+   ```yaml
+   embedding_model:
+     provider: sentence_transformers   # default; can be omitted
+     model: all-MiniLM-L6-v2
+   ```
+
+2. **Vector-indexed feature view** — at least one feature view with `vector_index=True` on a vector field, materialized to an online store that supports vector search.
+
+3. **Numeric filtering (optional)** — for metadata filters that use numeric or boolean comparisons, set `enable_openai_compatible_store: true` on your online store config and run `feast apply` to add the required `value_num` column.
+
+### Custom embedding providers
+
+The built-in Sentence Transformers provider works for most use cases. To use a different embedding backend (OpenAI, Cohere, a custom model, etc.), implement the `EmbeddingProvider` protocol and pass an instance to `FeatureStore`:
+
+```python
+from feast.embedder import EmbeddingProvider
+
+class MyEmbeddingProvider:
+    def embed(self, texts: list[str]) -> list[list[float]]:
+        # Call your embedding API here
+        return my_model.encode(texts)
+
+    async def aembed(self, texts: list[str]) -> list[list[float]]:
+        return await my_model.aencode(texts)
+
+store = FeatureStore(
+    repo_path=".",
+    embedding_provider=MyEmbeddingProvider(),
+)
+```
+
+### Numeric storage (`enable_openai_compatible_store`)
+
+By default, feature values are stored as text in the online store. This means string-ordered comparisons apply (e.g., `'9' > '100'` is `true`). When `enable_openai_compatible_store: true` is set on the online store config, Feast adds a `value_num` column that stores `int`, `float`, `double`, and `bool` values natively so that numeric filters produce correct results.
+
+```yaml
+online_store:
+  type: postgres  # or sqlite
+  # ... connection settings ...
+  enable_openai_compatible_store: true
+```
+
+After changing this setting, run `feast apply` to update the database schema.
+
+### List vector stores
+
+```bash
+curl http://localhost:6566/v1/vector_stores
+```
+
+```json
+{
+  "object": "list",
+  "data": [
+    {
+      "id": "vs_a1b2c3d4e5f6a1b2c3d4e5f6",
+      "object": "vector_store",
+      "name": "product_catalog",
+      "status": "completed",
+      "created_at": 1717200000
+    }
+  ]
+}
+```
+
+### Get a single vector store
+
+```bash
+curl http://localhost:6566/v1/vector_stores/vs_a1b2c3d4e5f6a1b2c3d4e5f6
+```
+
+Returns the same object shape as a single entry in the list response. Returns `404` if the ID does not match any vector-indexed feature view.
+
+### Search
+
+Start the feature server with `feast serve`, then send a search request:
+
+```bash
+curl -X POST http://localhost:6566/v1/vector_stores/vs_a1b2c3d4e5f6a1b2c3d4e5f6/search \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": "wireless noise-cancelling headphones",
+    "max_num_results": 5
+  }'
+```
+
+#### Request fields
+
+| Field | Type | Default | Description |
+|-------|------|---------|-------------|
+| `query` | `string` or `list[string]` | (required) | Plain text search query. Lists are joined with spaces before embedding. |
+| `max_num_results` | `int` | `10` | Maximum number of results to return. |
+| `filters` | `object` | `null` | OpenAI-style filters (see below). |
+| `ranking_options` | `object` | `null` | Accepted for forward compatibility, but currently ignored. Setting `score_threshold` or `ranker` inside it will return a 422 error. |
+| `rewrite_query` | `bool` | `null` | `false` (the default/no-op) is accepted. `true` is not yet supported and will return a 422 error. |
+| `metadata` | `object` | `null` | Optional. `metadata.features_to_retrieve` selects specific features. |
+
+### Filters
+
+The endpoint supports OpenAI-style filters for narrowing results beyond vector similarity.
+
+**Comparison operators:** `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`
+
+```json
+{"type": "eq", "key": "category", "value": "Electronics"}
+```
+
+**Compound operators:** `and`, `or` (nest to arbitrary depth)
+
+```json
+{
+  "type": "and",
+  "filters": [
+    {"type": "eq", "key": "category", "value": "Electronics"},
+    {"type": "gte", "key": "rating", "value": 4.5}
+  ]
+}
+```
+
+For Postgres and SQLite backends, all filtering (including string equality) requires `enable_openai_compatible_store: true` in the online store config. After enabling, run `feast apply` to update the database schema.
+
+ScyllaDB supports vector retrieval via `retrieve_online_documents_v2`, but OpenAI-style metadata filtering is not implemented yet. Passing `filters` raises `NotImplementedError`.
+
+### Response format
+
+Responses follow the OpenAI `vector_store.search_results.page` schema:
+
+```json
+{
+  "object": "vector_store.search_results.page",
+  "search_query": ["wireless noise-cancelling headphones"],
+  "data": [
+    {
+      "file_id": "vs_a1b2c3d4e5f6a1b2c3d4e5f6_42",
+      "filename": "vs_a1b2c3d4e5f6a1b2c3d4e5f6",
+      "score": 0.92,
+      "attributes": {"name": "...", "category": "..."},
+      "content": [
+        {"type": "text", "text": "..."}
+      ]
+    }
+  ],
+  "has_more": false,
+  "next_page": null
+}
+```
+
+The `file_id` and `filename` fields use the `vs_{hash}` identifier, not raw feature view names.
+
+The `score` field is a higher-is-better relevance score derived from the raw vector distance using a metric-dependent conversion:
+
+| Distance metric | Conversion | Range |
+|----------------|------------|-------|
+| L2 (default) | `1 / (1 + distance)` | (0, 1] |
+| Cosine | `1 - distance` | [0, 1] |
+| Inner product / dot | `-distance` | varies |
+
+The metric is determined by `vector_search_metric` on the feature view's vector field, not by an API parameter. When `features_to_retrieve` is omitted, all non-vector features are returned by default (vector embedding columns are excluded).
+
+Pagination is not yet implemented; `has_more` is always `false`.
+
+### SDK usage
+
+The OpenAI-compatible search is also available directly via the Python SDK:
+
+```python
+import asyncio
+from feast import FeatureStore
+
+store = FeatureStore(repo_path=".")
+
+result = asyncio.run(store.openai_search(
+    vector_store_id="product_catalog",
+    query="wireless noise-cancelling headphones",
+    max_num_results=5,
+    filters={"type": "eq", "key": "category", "value": "Electronics"},
+))
+
+for item in result["data"]:
+    print(f"{item['score']:.3f}  {item['attributes']}")
+```
+
+### Supported online stores
+
+The OpenAI-compatible filtering has been implemented for the following online stores:
+
+| Online Store | Vector Search | Metadata Filtering | Notes |
+|-------------|--------------|-------------------|-------|
+| Milvus | Yes | Yes | Boolean expressions |
+| Elasticsearch | Yes | Yes | Query DSL clauses |
+| Postgres (pgvector) | Yes | Yes | Requires `enable_openai_compatible_store: true` |
+| SQLite (sqlite-vec) | Yes | Yes | Requires `enable_openai_compatible_store: true` |
+| MongoDB | Yes | Yes | Aggregation pipeline |
+| ScyllaDB | Yes | No | Vector search only; metadata filters are not supported yet |
+
 ## Examples
 
 - See the v0 [Rag Demo](https://github.com/feast-dev/feast-workshop/blob/rag/module_4_rag) for an example on how to use vector database using the `retrieve_online_documents` method (planning migration and deprecation (planning migration and deprecation).

@@ -527,6 +527,42 @@ Prometheus adds an `instance` label per pod, so there is no
 duplication.  Use `sum(rate(...))` or `histogram_quantile(...)` across
 instances as usual.
 
+## Vector Search (`POST /search`)
+
+The feature server exposes `POST /search` for vector similarity search against online document embeddings. Pass a pre-computed embedding in `query`, or use `api_version: 2` with `query_string` for text-based search when the online store supports it.
+
+`POST /retrieve-online-documents` is a deprecated alias with the same request body and response; new integrations should use `/search`.
+
+## [Alpha] OpenAI-Compatible Vector Store API
+
+{% hint style="warning" %}
+**Alpha feature.** This API surface is functional and tested, but may change in future releases.
+{% endhint %}
+
+The feature server exposes OpenAI-compatible vector store endpoints. This allows clients (including LLM agents and tool-calling frameworks) to discover and search vector data with plain text queries, without computing embeddings client-side.
+
+Each feature view with vector-indexed fields gets a deterministic `vs_{hash}` identifier derived from `SHA-256(project + ":" + feature_view_name)`. These IDs are stable across server restarts.
+
+### Endpoints
+
+| Method | Path | RBAC | Description |
+|---|---|---|---|
+| `GET` | `/v1/vector_stores` | `DESCRIBE` | List all vector stores (filtered by caller permissions) |
+| `GET` | `/v1/vector_stores/{vector_store_id}` | `DESCRIBE` | Get metadata for a single vector store |
+| `POST` | `/v1/vector_stores/{vector_store_id}/search` | `READ_ONLINE` | Search a vector store with server-side embedding |
+
+### Configuration
+
+Add an `embedding_model` section to your `feature_store.yaml`:
+
+```yaml
+embedding_model:
+  provider: sentence_transformers   # default; can be omitted
+  model: all-MiniLM-L6-v2
+```
+
+Feast uses **Sentence Transformers** (default) for local embedding inference — no external API key required. Custom embedding providers can be plugged in by implementing the `EmbeddingProvider` protocol. See [\[Alpha\] Vector Database](../alpha-vector-database.md#alpha-openai-compatible-vector-store-api) for full configuration, custom providers, filter details, and SDK usage.
+
 ## Starting the feature server in TLS(SSL) mode
 
 Enabling TLS mode ensures that data between the Feast client and server is transmitted securely. For an ideal production environment, it is recommended to start the feature server in TLS mode.
@@ -598,7 +634,11 @@ The [PyTorch NLP template](https://github.com/feast-dev/feast/tree/main/sdk/pyth
 | Endpoint                   | Resource Type                   | Permission                                            | Description                                                    |
 |----------------------------|---------------------------------|-------------------------------------------------------|----------------------------------------------------------------|
 | /get-online-features       | FeatureView,OnDemandFeatureView | Read Online                                           | Get online features from the feature store                     |
-| /retrieve-online-documents | FeatureView                     | Read Online                                           | Retrieve online documents from the feature store for RAG       |
+| /search | FeatureView                     | Read Online                                           | Vector similarity search for RAG (embedding vector or text query) |
+| /retrieve-online-documents | FeatureView              | Read Online                                           | **Deprecated.** Use `/search` instead.                           |
+| /v1/vector_stores | FeatureView                  | Describe                                              | [Alpha] List all vector stores                                 |
+| /v1/vector_stores/{id} | FeatureView                  | Describe                                              | [Alpha] Get a single vector store                              |
+| /v1/vector_stores/{id}/search | FeatureView                  | Read Online                                           | [Alpha] OpenAI-compatible vector search with server-side embedding |
 | /push                      | FeatureView                     | Write Online, Write Offline, Write Online and Offline | Push features to the feature store (online, offline, or both)  |
 | /write-to-online-store     | FeatureView                     | Write Online                                          | Write features to the online store                             |
 | /materialize               | FeatureView                     | Write Online                                          | Materialize features within a specified time range             |

@@ -111,6 +111,13 @@ result = store.retrieve_online_documents_v2(
 )
 ```
 
+### Metadata filtering (OpenAI-compatible)
+
+ScyllaDB supports vector similarity search, but OpenAI-style metadata filtering is **not supported yet**.
+Passing `filters` to `retrieve_online_documents_v2` or the OpenAI-compatible search endpoint raises `NotImplementedError`.
+
+For filtered vector search today, use one of the backends that implement metadata filters (for example Milvus, Elasticsearch, Postgres, SQLite, or MongoDB). See [Alpha Vector Database](../alpha-vector-database.md#supported-online-stores).
+
 ## Functionality Matrix
 
 The set of functionality supported by online stores is described in detail [here](overview.md#functionality).

@@ -16,6 +16,7 @@ def list_projects(self, allow_cache=True, tags=None):
 class _FakeStore:
     def __init__(self):
         self.config = SimpleNamespace()
+        self.project = "smoke_test"
         self.registry = _FakeRegistry()
         self._provider = SimpleNamespace(
             async_supported=SimpleNamespace(
@@ -32,6 +33,9 @@ async def initialize(self):
     def refresh_registry(self):
         return None
 
+    def list_feature_views(self):
+        return []
+
     async def close(self):
         return None
 

@@ -51,7 +51,7 @@ feature_server:
   mcp_server_version: "1.0.0"
 ```
 
-Once enabled, any MCP-compatible agent -- whether built with LangChain, LlamaIndex, CrewAI, AutoGen, or a custom framework -- can connect to `http://your-feast-server/mcp` and discover available tools like `get-online-features` for entity-based retrieval, `retrieve-online-documents` for vector similarity search, and `write-to-online-store` for persisting agent state.
+Once enabled, any MCP-compatible agent -- whether built with LangChain, LlamaIndex, CrewAI, AutoGen, or a custom framework -- can connect to `http://your-feast-server/mcp` and discover available tools like `get-online-features` for entity-based retrieval, `search` for vector similarity search, `vector_store_search` for OpenAI-compatible text search, and `write-to-online-store` for persisting agent state.
 
 ## A Concrete Example: Customer-Support Agent with Memory
 
@@ -338,7 +338,7 @@ export OPENAI_BASE_URL="http://localhost:11434/v1"
 export LLM_MODEL="llama3.1:8b"
 ./run_demo.sh
 
-# Any OpenAI-compatible provider (Azure, vLLM, LiteLLM, etc.)
+# Any OpenAI-compatible provider (Azure, vLLM, etc.)
 export OPENAI_API_KEY="your-key"  # pragma: allowlist secret
 export OPENAI_BASE_URL="https://your-endpoint/v1"
 export LLM_MODEL="your-model"