Update README.md

README.md

-# Tenosrflow serving metrics with Grafana 
+# Monitor Machine Learning Models Deployed on Tensorflow Serving
 
-To run Grafana, Prometheus, and Tensorflow serving: 
+This is a demo showing possible ways to monitor machine learning models deployed on Tensorflow Serving using prometheus, Loki & Grafana. 
+
+## How to run it 
+
+After cloning the repo, on the command line type
 
 `docker-compose up`
 
+## Model Registering 
+
+There are different techniques with which you can register your trained model for deployment. For the purpose of simplicity, we're registering a pre-trained half plus two model which is already included in this repo. 
+
+## Prediction Example 
+
+To pbtain the predection, input instances are passed as follows 
+
+`!curl -X POST -H "Content-Type: application/json" -d '{"instances": [1.0, 2.0, 5.0]}' http://10.5.0.6/prediction`
+
+The expected output should look something like this 
+
+`{ "predictions": [2.5, 3.0, 4.5] }` 
+
+More info about Tensorlow Serving (docker) is found (here)[https://www.tensorflow.org/tfx/serving/docker]
+
+
+## IPs & Ports to use for setup in Grafana  
+
+To setup Grafana, use the following url, 
+
+Grafana: http://localhost:3000  (username: admin, password: admin)
+
+To setup Prometheus and Loki as data sources, use the following urls
+
+Prometheus: http://10.5.0.7:9090
 
+Loki: http://10.5.0.9:3100
 
-- Grafana: http://localhost:3000
 
-- Prometheus: http://localhost:9090 
 
-- Predicrion example (for halp plus two model): curl -d '{"instances": [1.0, 2.0, 5.0]}'     -X POST http://localhost:8501/v1/models/half_plus_two:predict