Added ranking explainer demo (#187)

* added ranking explanation demo in ml4ir * fixed config param * fixed config param * added ranking explanation demo in ml4ir * updated feature config * updated with latest omnixai api * updated demo notebook * Update explanations notebook * added optional req omnixai * Update python/optional_requirements.yaml Co-authored-by: Ashish Bharadwaj Srinivasa <[email protected]> * added optional req omnixai * Added reference to notebook in README * Dummy commit Co-authored-by: Ashish Bharadwaj Srinivasa <[email protected]>
salesforce · Sep 1, 2022 · 3af0577 · 3af0577
1 parent 6ff9238
commit 3af0577
Show file tree

Hide file tree

Showing 5 changed files with 3,402 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -4,6 +4,7 @@
 
 **Quickstart &rarr;** **[ml4ir Read the Docs](https://ml4ir.readthedocs.io/en/latest/)** | **[ml4ir pypi](https://pypi.org/project/ml4ir/)** | **[python ReadMe](python/)**
 
+
 ml4ir is an open source library for training and deploying deep learning models for search applications. ml4ir is built on top of **python3** and **tensorflow 2.x** for training and evaluation. It also comes packaged with scala utilities for **JVM inference**.
 
 ml4ir is designed as modular subcomponents which can each be combined and customized to build a variety of search ML models such as:

diff --git a/python/README.md b/python/README.md
@@ -149,6 +149,8 @@ To use ml4ir as a deep learning library to build relevance models, look at the f
 
 * **Text Classification** : The `EntityPredictionDemo` notebook walks you through training a model to predict entity type given a user context and query.
 
+* **Ranking Explanations** : The `Ranking_Explanations` notebook walks you through per-query explanations for a trained ml4ir model
+
 Enter the following command to spin up Jupyter notebook on your browser to run the above notebooks
 ```
 cd path/to/ml4ir/python/