feast-dev · SIDDHESH1564 · Jul 7, 2026
@@ -166,6 +166,7 @@
   * [Aerospike](reference/online-stores/aerospike.md)
   * [Elasticsearch](reference/online-stores/elasticsearch.md)
   * [Qdrant](reference/online-stores/qdrant.md)
+  * [Pinecone](reference/online-stores/pinecone.md)
   * [Faiss](reference/online-stores/faiss.md)
   * [Hybrid](reference/online-stores/hybrid.md)
 * [Registries](reference/registries/README.md)

@@ -16,6 +16,7 @@ Below are supported vector databases and implemented features:
 | SQLite          | [x]       | [ ]      | [x]         | [x]         |
 | Qdrant          | [x]       | [x]      | []          | []          |
 | ScyllaDB        | [x]       | [x]      | [x]         | [x]         |
+| Pinecone        | [x]       | [x]      | [x]         | [x]         |
 
 *Note: V2 Support means the SDK supports retrieval of features along with vector embeddings from vector similarity search.
 
@@ -190,7 +191,7 @@ print('\n'.join([c.message.content for c in response.choices]))
 
 ### Configuration and Installation
 
-We offer [Milvus](https://milvus.io/), [PGVector](https://github.com/pgvector/pgvector), [SQLite](https://github.com/asg017/sqlite-vec), [Elasticsearch](https://www.elastic.co) and [Qdrant](https://qdrant.tech/) as Online Store options for Vector Databases.
+We offer [Milvus](https://milvus.io/), [PGVector](https://github.com/pgvector/pgvector), [SQLite](https://github.com/asg017/sqlite-vec), [Elasticsearch](https://www.elastic.co), [Qdrant](https://qdrant.tech/) and [Pinecone](https://www.pinecone.io/) as Online Store options for Vector Databases.
 
 Milvus offers a convenient local implementation for vector similarity search. To use Milvus, you can install the Feast package with the Milvus extra.
 
@@ -210,6 +211,12 @@ pip install feast[elasticsearch]
 ```bash
 pip install feast[qdrant]
 ```
+#### Installation with Pinecone
+
+```bash
+pip install feast[pinecone]
+```
+
 #### Installation with SQLite
 
 If you are using `pyenv` to manage your Python versions, you can install the SQLite extension with the following command:

@@ -90,6 +90,10 @@ Please see [Online Store](../../getting-started/components/online-store.md) for
 [milvus.md](milvus.md)
 {% endcontent-ref %}
 
+{% content-ref url="pinecone.md" %}
+[pinecone.md](pinecone.md)
+{% endcontent-ref %}
+
 {% content-ref url="faiss.md" %}
 [faiss.md](faiss.md)
 {% endcontent-ref %}

@@ -0,0 +1,109 @@
+# Pinecone online store
+
+## Description
+
+The [Pinecone](https://www.pinecone.io/) online store provides support for materializing feature values into a Pinecone vector database. It is particularly suited for AI workloads that require both low-latency feature serving and vector similarity search for RAG (Retrieval-Augmented Generation) applications.
+
+## Getting started
+
+In order to use this online store, you'll need to install the Pinecone extra (along with the dependency needed for the offline store of choice). E.g.
+
+`pip install 'feast[pinecone]'`
+
+You will also need a Pinecone account and API key. Set your API key via the `PINECONE_API_KEY` environment variable or directly in `feature_store.yaml`.
+
+## Examples
+
+{% code title="feature_store.yaml" %}
+```yaml
+project: my_feature_repo
+registry: data/registry.db
+provider: local
+online_store:
+  type: pinecone
+  api_key: ${PINECONE_API_KEY}
+  index_name: feast-online
+  embedding_dim: 384
+  metric: cosine
+  cloud: aws
+  region: us-east-1
+  vector_enabled: true
+```
+{% endcode %}
+
+### Using a custom namespace
+
+By default, Feast maps each feature view to a Pinecone namespace (`{project}_{feature_view_name}`). You can override this with a fixed namespace:
+
+{% code title="feature_store.yaml" %}
+```yaml
+online_store:
+  type: pinecone
+  api_key: ${PINECONE_API_KEY}
+  index_name: feast-online
+  namespace: my-custom-namespace
+  embedding_dim: 384
+```
+{% endcode %}
+
+### Vector similarity search
+
+Pinecone supports the `retrieve_online_documents_v2` API for vector similarity search:
+
+```python
+from feast import FeatureStore
+
+store = FeatureStore(repo_path=".")
+
+results = store.retrieve_online_documents_v2(
+    features=[
+        "city_embeddings:vector",
+        "city_embeddings:sentence_chunks",
+    ],
+    query=query_embedding,
+    top_k=5,
+    distance_metric="cosine",
+).to_df()
+```
+
+The full set of configuration options is available in [PineconeOnlineStoreConfig](https://rtd.feast.dev/en/latest/#feast.infra.online_stores.pinecone_online_store.pinecone.PineconeOnlineStoreConfig).
+
+## Configuration options
+
+| Option | Type | Default | Description |
+|:---|:---|:---|:---|
+| `type` | string | `"pinecone"` | Must be `pinecone` |
+| `api_key` | string | `None` | Pinecone API key (falls back to `PINECONE_API_KEY` env var) |
+| `index_name` | string | `"feast-online"` | Name of the Pinecone index |
+| `namespace` | string | `None` | Override namespace (default: `{project}_{fv_name}`) |
+| `embedding_dim` | int | `128` | Vector dimension |
+| `metric` | string | `"cosine"` | Distance metric: `cosine`, `euclidean`, or `dotproduct` |
+| `cloud` | string | `"aws"` | Cloud provider for serverless indexes |
+| `region` | string | `"us-east-1"` | Cloud region for serverless indexes |
+| `vector_enabled` | bool | `true` | Enable vector similarity search |
+| `batch_size` | int | `100` | Number of vectors per upsert batch |
+
+## Functionality Matrix
+
+The set of functionality supported by online stores is described in detail [here](overview.md#functionality).
+Below is a matrix indicating which functionality is supported by the Pinecone online store.
+
+|                                                           | Pinecone |
+|:----------------------------------------------------------|:---------|
+| write feature values to the online store                  | yes      |
+| read feature values from the online store                 | yes      |
+| update infrastructure (e.g. tables) in the online store   | yes      |
+| teardown infrastructure (e.g. tables) in the online store | yes      |
+| generate a plan of infrastructure changes                 | no       |
+| support for on-demand transforms                          | yes      |
+| readable by Python SDK                                    | yes      |
+| readable by Java                                          | no       |
+| readable by Go                                            | no       |
+| support for entityless feature views                      | yes      |
+| support for concurrent writing to the same key            | yes      |
+| support for ttl (time to live) at retrieval               | no       |
+| support for deleting expired data                         | no       |
+| collocated by feature view                                | no       |
+| collocated by feature service                             | no       |
+| collocated by entity key                                  | no       |
+| vector similarity search                                  | yes      |
diff --git a/pixi.lock b/pixi.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -119,6 +119,7 @@ postgres = ["psycopg[binary,pool]>=3.2.5"]
 # https://www.psycopg.org/psycopg3/docs/basic/install.html#local-installation
 postgres-c = ["psycopg[c,pool]>=3.2.5"]
 pytorch = ["torch>=2.7.0", "torchvision>=0.22.1"]
+pinecone = ["pinecone>=5.0"]
 qdrant = ["qdrant-client>=1.12.0"]
 rag = [
     "transformers>=4.36.0",
@@ -164,7 +165,7 @@ test = [
 ]
 
 ci = [
-    "feast[test, aws, azure, cassandra, clickhouse, couchbase, delta, docling, duckdb, elasticsearch, faiss, gcp, ge, go, grpcio, hazelcast, hbase, ibis, iceberg, image, k8s, mcp, milvus, mlflow, mongodb, mssql, mysql, openlineage, opentelemetry, oracle, scylladb, spark, trino, postgres, pytorch, qdrant, rag, ray, redis, singlestore, snowflake, sqlite_vec]",
+    "feast[test, aws, azure, cassandra, clickhouse, couchbase, delta, docling, duckdb, elasticsearch, faiss, gcp, ge, go, grpcio, hazelcast, hbase, ibis, iceberg, image, k8s, mcp, milvus, mlflow, mongodb, mssql, mysql, openlineage, opentelemetry, oracle, pinecone, scylladb, spark, trino, postgres, pytorch, qdrant, rag, ray, redis, singlestore, snowflake, sqlite_vec]",
     "build",
     "virtualenv==20.23.0",
     "dbt-artifacts-parser",

@@ -0,0 +1,6 @@
+from feast.infra.online_stores.pinecone_online_store.pinecone import (
+    PineconeOnlineStore,
+    PineconeOnlineStoreConfig,
+)
+
+__all__ = ["PineconeOnlineStore", "PineconeOnlineStoreConfig"]