Update docs

README.md

@@ -6,70 +6,64 @@
 
 <br>
 
-# Model serving at scale
+# Deploy, manage, and scale machine learning models in production
 
-Cortex is a platform for deploying, managing, and scaling machine learning in production.
+Cortex is a cloud native model serving platform for machine learning engineering teams.
 
 <br>
 
-## Key features
+## Use cases
 
-* Run realtime inference, batch inference, and training workloads.
-* Deploy TensorFlow, PyTorch, ONNX, and other models to production.
-* Scale to handle production workloads with server-side batching and request-based autoscaling.
-* Configure rolling updates and live model reloading to update APIs without downtime.
-* Serve models efficiently with multi-model caching and spot / preemptible instances.
-* Stream performance metrics and structured logs to any monitoring tool.
-* Perform A/B tests with configurable traffic splitting.
+* **Realtime machine learning** - build NLP, computer vision, and other APIs and integrate them into any application.
+* **Large-scale inference** - scale realtime or batch inference workloads across hundreds or thousands of instances.
+* **Consistent MLOps workflows** - create streamlined and reproducible MLOps workflows for any machine learning team.
 
 <br>
 
-## How it works
+## Deploy
 
-### Implement a Predictor
+* Deploy TensorFlow, PyTorch, ONNX, and other models using a simple CLI or Python client.
+* Run realtime inference, batch inference, asynchronous inference, and training jobs.
+* Define preprocessing and postprocessing steps in Python and chain workloads seamlessly.
 
-```python
-# predictor.py
+```text
+$ cortex deploy apis.yaml
 
-from transformers import pipeline
+• creating text-generator (realtime API)
+• creating image-classifier (batch API)
+• creating video-analyzer (async API)
 
-class PythonPredictor:
-    def __init__(self, config):
-        self.model = pipeline(task="text-generation")
-
-    def predict(self, payload):
-        return self.model(payload["text"])[0]
-```
-
-### Configure a realtime API
-
-```yaml
-# text_generator.yaml
-
-- name: text-generator
-  kind: RealtimeAPI
-  predictor:
-    type: python
-    path: predictor.py
-  compute:
-    gpu: 1
-    mem: 8Gi
-  autoscaling:
-    min_replicas: 1
-    max_replicas: 10
+all APIs are ready!
 ```
 
-### Deploy
+## Manage
 
-```bash
-$ cortex deploy text_generator.yaml
+* Create A/B tests and shadow pipelines with configurable traffic splitting.
+* Automatically stream logs from every workload to your favorite log management tool.
+* Monitor your workloads with pre-built Grafana dashboards and add your own custom dashboards.
 
-# creating http://example.com/text-generator
+```text
+$ cortex get
 
+API                 TYPE        GPUs
+text-generator      realtime    32
+image-classifier    batch       64
+video-analyzer      async       16
 ```
 
-### Serve prediction requests
+## Scale
+
+* Configure workload and cluster autoscaling to efficiently handle large-scale production workloads.
+* Create clusters with different types of instances for different types of workloads.
+* Spend less on cloud infrastructure by letting Cortex manage spot or preemptible instances.
+
+```text
+$ cortex cluster info
 
-```bash
-$ curl http://example.com/text-generator -X POST -H "Content-Type: application/json" -d '{"text": "hello world"}'
+provider: aws
+region: us-east-1
+instance_types: [c5.xlarge, g4dn.xlarge]
+spot_instances: true
+min_instances: 10
+max_instances: 100
 ```

cli/cmd/root.go

@@ -148,7 +148,7 @@ func initTelemetry() {
 var _rootCmd = &cobra.Command{
 	Use:     "cortex",
 	Aliases: []string{"cx"},
-	Short:   "model serving at scale",
+	Short:   "deploy machine learning models to production",
 }
 
 func Execute() {

docs/README.md

@@ -1 +1 @@
-**Please view our documentation at [docs.cortex.dev](https://docs.cortex.dev/)**
+**Please view our documentation at [docs.cortex.dev](https://docs.cortex.dev)**

docs/summary.md

@@ -8,7 +8,6 @@
 * [CLI commands](clients/cli.md)
 * [Python API](clients/python.md)
 * [Environments](clients/environments.md)
-* [Telemetry](clients/telemetry.md)
 * [Uninstall](clients/uninstall.md)
 
 ## Workloads

pkg/cortex/client/README.md

@@ -1 +1 @@
-Model serving at scale - [docs.cortex.dev](https://www.docs.cortex.dev)
+Deploy machine learning models to production - [docs.cortex.dev](https://www.docs.cortex.dev)

pkg/cortex/client/setup.py

@@ -77,7 +77,7 @@ def run(self):
 setup(
     name="cortex",
     version="master",  # CORTEX_VERSION
-    description="Model serving at scale",
+    description="Deploy machine learning models to production",
     author="cortex.dev",
     author_email="dev@cortex.dev",
     license="Apache License 2.0",