GitBook: [master] 2 pages modified

adchia · gitbook-bot · commit bf5dc7d1bf1e · 2021-09-15T17:09:46.000Z
diff --git a/docs/getting-started/faq.md b/docs/getting-started/faq.md
@@ -22,6 +22,10 @@ No, there are [feature views without entities](concepts/data-model-and-concepts/
 
 Feast currently does not support any access control other than the access control required for the Provider's environment \(for example, GCP and AWS permissions\).
 
+### Does Feast support streaming sources?
+
+Feast is actively working on this right now. Please reach out to the Feast team if you're interested in giving feedback! 
+
 ### Does Feast support composite keys?
 
 A feature view can be defined with multiple entities. Since each entity has a unique join\_key, using multiple entities will achieve the effect of a composite key.
@@ -30,6 +34,21 @@ A feature view can be defined with multiple entities. Since each entity has a un
 
 Please see a detailed comparison of Feast vs. Tecton [here](https://www.tecton.ai/feast/). For another comparison, please see [here](https://mlops.community/learn/feature-store/).
 
+### What are the performance/latency characteristics of Feast?
+
+Feast is designed to work at scale and support low latency online serving. Benchmarks to be released soon, and active work is underway to support very latency sensitive use cases.
+
+### Does Feast support embeddings and list features?
+
+Yes. Specifically:
+
+* Simple lists / dense embeddings: 
+  * BigQuery supports list types natively 
+  * Redshift does not support list types, so you'll need to serialize these features into strings \(e.g. json or protocol buffers\)
+  * Feast's implementation of online stores serializes features into Feast protocol buffers and supports list types \(see [reference](https://github.com/feast-dev/feast/blob/master/docs/specs/online_store_format.md#appendix-a-value-proto-format)\)
+* Sparse embeddings \(e.g. one hot encodings\)
+  * One way to do this efficiently is to have a protobuf or string representation of [https://www.tensorflow.org/guide/sparse\_tensor](https://www.tensorflow.org/guide/sparse_tensor)
+
 ### Does Feast support X storage engine?
 
 The list of supported offline and online stores can be found [here](../reference/offline-stores/) and [here](../reference/online-stores/), respectively. The [roadmap](../roadmap.md) indicates the stores for which we are planning to add support. Finally, our Provider abstraction is built to be extensible, so you can plug in your own implementations of offline and online stores. Please see more details about custom providers [here](../how-to-guides/creating-a-custom-provider.md).
diff --git a/docs/reference/feature-server.md b/docs/reference/feature-server.md
@@ -1,4 +1,4 @@
-# Feature Server (Experimental)
+# Feature Server
 
 **Warning**: This is an _experimental_ feature. It's intended for early testing and feedback, and could change without warnings in future releases.
 
@@ -44,6 +44,7 @@ INFO:     Uvicorn running on http://127.0.0.1:6566 (Press CTRL+C to quit)
 ```
 
 After the server starts, we can execute cURL commands from another terminal tab:
+
 ```bash
 $  curl -X POST \
   "http://localhost:6566/get-online-features" \
@@ -106,7 +107,8 @@ $  curl -X POST \
 ```
 
 It's also possible to specify a feature service name instead of the list of features:
-```
+
+```text
 curl -X POST \
   "http://localhost:6566/get-online-features" \
   -d '{
@@ -115,4 +117,5 @@ curl -X POST \
       "driver_id": [1001, 1002, 1003]
     }
   }' | jq
-```
+```
+
