Remove Ray AIR serving guides (ray-project#37726)

For the serving guide, things are already covered well in the Ray Serve section (batching, `http_adapter` insofar it is useful -- in many cases it isn't useful and leads people towards sending bloated uncompressed JSON tensor data over the wire instead of compressed JPG and then uncompressing on the server side). In general we need to show people how to use their trained models for prediction on a minibatch and then they can easily serve it with Ray Serve. The RL guide is already covered well in https://docs.ray.io/en/latest/serve/tutorials/rllib.html
charleslai2000 · Jul 25, 2023 · 665cfa8 · 665cfa8
1 parent adae0b0
commit 665cfa8
Show file tree

Hide file tree

Showing 12 changed files with 1 addition and 4,915 deletions.
diff --git a/doc/source/_toc.yml b/doc/source/_toc.yml
@@ -53,7 +53,6 @@ parts:
  - file: ray-air/tuner
  - file: ray-air/predictors
  - file: ray-air/computer-vision
- - file: ray-air/examples/serving_guide
  - file: ray-air/deployment
  - file: ray-air/examples/index
  sections:
@@ -67,7 +66,6 @@ parts:
  - file: ray-air/examples/analyze_tuning_results
  - file: ray-air/examples/lightgbm_example
  - file: ray-air/examples/torch_incremental_learning
- - file: ray-air/examples/rl_serving_example
  - file: ray-air/examples/rl_online_example
  - file: ray-air/examples/rl_offline_example
  - file: ray-air/examples/upload_to_comet_ml

diff --git a/doc/source/ray-air/api/api.rst b/doc/source/ray-air/api/api.rst
@@ -17,4 +17,3 @@ Ray AIR API
  Results (Ray Train + Ray Tune)<../../tune/api/result_grid>
  AIR Checkpoint (All Libraries)<checkpoint.rst>
  Predictors (Ray Data + Ray Train)<predictor.rst>
- Model Serving in AIR (Ray Serve)<serve.rst>
diff --git a/doc/source/ray-air/api/serve.rst b/doc/source/ray-air/api/serve.rst
diff --git a/doc/source/ray-air/computer-vision.rst b/doc/source/ray-air/computer-vision.rst
@@ -315,8 +315,6 @@ To NumPy ndarrays like this:
  :end-before: __torch_online_predict_stop__
  :dedent:
 
- For more in-depth examples, see :doc:`/ray-air/examples/serving_guide`.
-
  .. tab-item:: TensorFlow
 
  To deploy a TensorFlow model to an endpoint, pass the checkpoint you created in `Creating checkpoints`_
@@ -334,5 +332,3 @@ To NumPy ndarrays like this:
  :start-after: __tensorflow_online_predict_start__
  :end-before: __tensorflow_online_predict_stop__
  :dedent:
-
- For more information, read :doc:`/ray-air/examples/serving_guide`.
diff --git a/doc/source/ray-air/examples/index.rst b/doc/source/ray-air/examples/index.rst
@@ -48,7 +48,6 @@ Logging & Observability
 RL (RLlib)
 ----------
 
-- :doc:`/ray-air/examples/rl_serving_example`
 - :doc:`/ray-air/examples/rl_online_example`
 - :doc:`/ray-air/examples/rl_offline_example`
 

diff --git a/doc/source/ray-air/examples/rl_serving_example.ipynb b/doc/source/ray-air/examples/rl_serving_example.ipynb