Merge pull request #126 from cliveseldon/intro_slides

Add Overview Doc
SeldonIO · May 28, 2021 · e2ebec4 · e2ebec4
2 parents 4014f79 + 878d19d
commit e2ebec4
Show file tree

Hide file tree

Showing 12 changed files with 44 additions and 3 deletions.
diff --git a/docs/assets/example.png b/docs/assets/example.png
diff --git a/docs/assets/goals.png b/docs/assets/goals.png
diff --git a/docs/assets/graph-code.png b/docs/assets/graph-code.png
diff --git a/docs/assets/graph.png b/docs/assets/graph.png
diff --git a/docs/assets/graph2.png b/docs/assets/graph2.png
diff --git a/docs/overview/internals.png → docs/assets/internals.png b/docs/overview/internals.png → docs/assets/internals.png
diff --git a/docs/overview/model-pipeline.png → docs/assets/model-pipeline.png b/docs/overview/model-pipeline.png → docs/assets/model-pipeline.png
diff --git a/docs/overview/outlier-demo.png → docs/assets/outlier-demo.png b/docs/overview/outlier-demo.png → docs/assets/outlier-demo.png
diff --git a/docs/assets/steps.png b/docs/assets/steps.png
diff --git a/docs/index.rst b/docs/index.rst
@@ -7,6 +7,7 @@ Tempo
     :titlesonly:
     :caption: Documentation:
 
+    Overview <overview/overview.md>
     Quickstart <overview/quickstart.md>
     Architecture <overview/architecture.md>
     Workflow <workflow/workflow.md>

diff --git a/docs/overview/architecture.md b/docs/overview/architecture.md
@@ -2,14 +2,14 @@
 
 Overview of Tempo architecture.
 
-![internals](internals.png)
+![internals](../assets/internals.png)
 
 
 ## Model and Pipeline
 
 A Model is the core deployment artifact in tempo and describes the link to a saved machine learning component. A Pipeline is a custom python orchestrator that references other Tempo models or pipelines specied in its definition.
 
-![model-pipeline](model-pipeline.png)
+![model-pipeline](../assets/model-pipeline.png)
 
 
 A Model can be:
@@ -22,7 +22,7 @@ A Pipeline is custom python code (defined via a class or function) which referen
 
 An example is shown below for the [outlier demo](../examples/outlier/README.html). There we have a Pipeline which calls the outlier model and if the request is determined to be an outlier then the processing is halted otherwise the model is called.
 
-![outlier demo](outlier-demo.png)
+![outlier demo](../assets/outlier-demo.png)
 
 ## Runtimes
 

diff --git a/docs/overview/overview.md b/docs/overview/overview.md
@@ -0,0 +1,40 @@
+# Tempo Overview
+
+Tempo is a python SDK for data scientists to help them move their models to production. It has 4 core goals:
+
+  1. Data science friendly.
+  2. Pluggable runtimes.
+  3. Custom python inference components.
+  4. Powerful orchestration logic.
+
+![goals](../assets/goals.png)
+
+A simple model example is shown below. A data scientist need only fill some core details about their trained model.
+
+![example](../assets/example.png)
+
+Tempo allows you to combine business logic as custom python with models served on optimized servers.
+
+![example](../assets/graph.png)
+
+In the example below:
+
+  1. Train your sklearn model
+  2. Train your xgboost model
+  3. Create python logic to orchestrate the two
+
+![example](../assets/graph2.png)
+
+
+The Tempo code for the above example is shown below:
+
+
+![example code](../assets/graph-code.png)
+
+The steps to use tempo would be:
+
+ 1. Local training and unit tests
+ 2. Local tests of inference on Docker
+ 3. Push to production runtime, e.g. Kubernetes with Seldon Core
+
+![production steps](../assets/steps.png)