more rewritign

Author: Tyler Romero

docs/docs/getting-started/getting-started.mdx

@@ -1,41 +1,70 @@
 # Getting Started with Groundlight
 
-## Build Computer Vision Applications in Minutes with Groundlight's Python SDK
+## Build Powerful Computer Vision Applications in Minutes
 
-Welcome to Groundlight AI! This guide will help you build your first computer vision application quickly and easily using our Python SDK.
+Welcome to Groundlight AI! This guide will help you create your first computer vision application
+quickly and easily using our intuitive Python SDK. Whether you're monitoring wildlife,
+automating quality control, or building smart security systems, Groundlight makes computer vision
+accessible to everyone.
 
-Don't code? [Contact our team](mailto:support@groundlight.ai) and we'll build a custom solution for you.
+Don't code? No problem! [Contact our team](mailto:support@groundlight.ai) and we'll build a custom solution tailored to your needs.
 
 ### Prerequisites
-Before you begin, make sure you have:
-1. A [Groundlight account](https://dashboard.groundlight.ai/)!
-2. An API token from the [Groundlight dashboard](https://dashboard.groundlight.ai/reef/my-account/api-tokens). See our [guide to API Tokens](http://localhost:3000/python-sdk/docs/getting-started/api-tokens) for more info.
-3. Python 3.9 or newer installed
+Before diving in, you'll need:
+1. A [Groundlight account](https://dashboard.groundlight.ai/) (sign up is quick and easy!)
+2. An API token from your [Groundlight dashboard](https://dashboard.groundlight.ai/reef/my-account/api-tokens). Check out our [API Tokens guide](http://localhost:3000/python-sdk/docs/getting-started/api-tokens) for details.
+3. Python 3.9 or newer installed on your system.
 
-### Installing the Groundlight SDK
+### Setting Up Your Environment
 
-You can install the Groundlight SDK via pip. When installing python packages, it is a best practice to install them
-inside of virtual environments. Run the following in the command line to create a new environment:
+Let's set up a clean Python environment for your Groundlight project! The Groundlight SDK is available on PyPI and can be installed with [pip](https://packaging.python.org/en/latest/tutorials/installing-packages/#use-pip-for-installing).
+
+First, let's create a virtual environment to keep your Groundlight dependencies isolated from other Python projects:
 ```bash
 python3 -m venv groundlight-env
 ```
+Now, activate your virtual environment:
+```bash
+# MacOS / Linux
+source groundlight-env/bin/activate
+```
+```
+# Windows
+.\groundlight-env\Scripts\activate
+```
 
-Activate the virtual environment using
-- On macOS or Linux, `source groundlight-env/bin/activate`
-- On Windows, `.\groundlight-env\Scripts\activate`
-
-Now, you can install the Groundlight SDK using pip:
+With your environment ready, install the Groundlight SDK with a simple pip command:
 ```bash
 pip install groundlight
 ```
 
-For more detailed installation instructions, see the [installation guide](/docs/installation/).
+Let's also install [framegrab](https://github.com/groundlight/framegrab) with YouTube support -
+this useful library will let us capture frames from YouTube livestreams, webcams, and other video
+sources, making it easy to get started!
+```bash
+pip install framegrab[youtube]
+```
+:::tip Camera Support
+Framegrab is versatile! It works with:
+- Webcams and USB cameras
+- RTSP streams (security cameras)
+- Professional cameras (Basler USB/GigE)
+- Depth cameras (Intel RealSense)
+- Video files and streams (mp4, mov, mjpeg, avi)
+- YouTube livestreams
+
+This makes it perfect for quickly prototyping your computer vision applications!
+:::
+
+Need more options? Check out our detailed [installation guide](/docs/installation/) for advanced setup instructions.
 
 ### Authentication
-The Groundlight SDK uses API tokens to authenticate your requests to the Groundlight API.
-When you make API calls, the SDK automatically uses your token to verify your identity and permissions. It
-does this by checking the `GROUNDLIGHT_API_TOKEN` environment variable. In order to set this environment
-variable, run:
+
+Now let's set up your credentials so you can start making API calls. Groundlight uses API tokens to securely authenticate your requests.
+
+If you don't have an API token yet, refer to our [API Tokens guide](/docs/getting-started/api-tokens) to create one.
+
+The SDK will automatically look for your token in the `GROUNDLIGHT_API_TOKEN` environment variable. Set it up with:
 ```bash
 # MacOS / Linux
 export GROUNDLIGHT_API_TOKEN='your-api-token'
@@ -44,7 +73,7 @@ export GROUNDLIGHT_API_TOKEN='your-api-token'
 # Windows
 setx GROUNDLIGHT_API_TOKEN "your-api-token"
 ```
-:::important
+:::important API Tokens
 Keep your API token secure! Anyone who has access to it can impersonate you and can access to your Groundlight data.
 :::
 
@@ -55,49 +84,48 @@ visual question you want to answer, while an `ImageQuery` is a request to analyz
 
 The Groundlight system is designed to provide consistent, highly confident answers for similar images
 (such as frames from the same camera) when asked the same question repeatedly. This makes it ideal for
-monitoring scenarios where you need reliable visual detection.
+scenarios where you need reliable visual detection.
 
 Let's see how to use Groundlight to analyze an image:
 ```python title="ask.py"
-from groundlight import Groundlight, Detector, ImageQuery
 from framegrab import FrameGrabber
+from groundlight import Groundlight, Detector, ImageQuery
 
 gl = Groundlight()
 detector: Detector = gl.get_or_create_detector(
     name="eagle-detector",
     query="Is there an eagle visible?",
 )
 
-# Big Bear Bald Eagle Nest live-stream
+# Big Bear Bald Eagle Nest livestream
 youtube_live_url = 'https://www.youtube.com/watch?v=B4-L2nfGcuE'
 
-config = {
+framegrab_config = {
     'input_type': 'youtube_live',
     'id': {'youtube_url': youtube_live_url},
 }
 
-with FrameGrabber.create_grabber({
-    'input_type': 'youtube_live', 'id': {'youtube_url': youtube_live_url},
-}) as grabber:
+with FrameGrabber.create_grabber(framegrab_config) as grabber:
     frame = grabber.grab()
     if frame is None:
-        raise Exception("No frame captured")
+        raise RuntimeError("No frame captured")
 
-image_query = gl.submit_image_query(detector=detector, image=frame)
+iq: ImageQuery = gl.submit_image_query(detector=detector, image=frame)
 
-print(f"The answer is {image_query.result.label}")
-print(image_query)
+print(f"{detector.query} -- Answer: {iq.result.label} with confidence={iq.result.confidence:.3f}\n")
+print(iq)
 ```
 
 Run the code using `python ask.py`. The code will submit an image from the live-stream to the Groundlight API and print the result:
 ```
-The answer is YES
+Is there an eagle visible? -- Answer: YES with confidence=0.988
+
 ImageQuery(
     id='iq_2pL5wwlefaOnFNQx1X6awTOd119',
     query="Is there an eagle visible?,
     detector_id='det_2owcsT7XCsfFlu7diAKgPKR4BXY',
     result=BinaryClassificationResult(
-        confidence=0.9995857543478209,
+        confidence=0.9884857543478209,
         label=<Label.YES: 'YES'>
     ),
     created_at=datetime.datetime(2025, 2, 25, 11, 5, 57, 38627, tzinfo=tzutc()),
@@ -108,26 +136,26 @@ ImageQuery(
     metadata=None
 )
 ```
+## What's Next?
 
-For more information on the Groundlight SDK, see the [API Reference](/docs/api-reference/), or check out our [guide to building applications with the Groundlight SDK](/docs/guide/).
+🎉 **Amazing job!** You've just built your first computer vision application with Groundlight. In just a few lines of code, you've created an eagle detector that can analyze live video streams!
 
-### Using Your Computer Vision Application
+### Supercharge Your Application
 
-Congratulations! You now have a fully functional computer vision application. You can easily customize the code and configure detectors for your specific use cases.
+Take your application to the next level:
 
-Monitor and enhance your detector's performance through the [Groundlight Dashboard](https://dashboard.groundlight.ai/).
-Groundlight's human-in-the-loop technology intelligently monitors your image feed for anomalies and unexpected changes.
-By reviewing and verifying results, you continuously improve the system's accuracy. Through the dashboard, you can also
-[configure text and email notifications](/docs/guide/alerts) to alert you when important events are detected in your video stream.
+- **Monitor in real-time** through the [Groundlight Dashboard](https://dashboard.groundlight.ai/) - see your detections, review results, and track performance
+- **Get instant alerts** when important events happen - [set up text and email notifications](/docs/guide/alerts) for critical detections
+- **Improve continuously** with Groundlight's human-in-the-loop technology that learns from your feedback
 
 ### Next Steps
 
-Now that you've built your first application, you can:
-    1. Learn how to [write effective queries](/docs/getting-started/writing-queries).
-    2. Proceed to [capture images from a wide variety of sources](/docs/guide/grabbing-images) using [`framegrab`](https://github.com/groundlight/framegrab).
-    3. Read our guide to [confidence thresholds](/docs/guide/managing-confidence).
-
-
+| What You Want To Do | Resource |
+|---|---|
+| 📝 Create better detectors | [Writing effective queries](/docs/getting-started/writing-queries) |
+| 📷 Connect to cameras, RTSP, or other sources | [Grabbing images from various sources](/docs/guide/grabbing-images) |
+| 🎯 Fine-tune detection accuracy | [Managing confidence thresholds](/docs/guide/managing-confidence) |
+| 📚 Explore the full API | [SDK Reference](/docs/api-reference/) |
 
 Ready to explore more possibilities? Visit our [Guides](https://www.groundlight.ai/guides) to discover sample
 applications built with Groundlight AI — from [industrial inspection workflows](https://www.groundlight.ai/blog/lkq-corporation-uses-groundlight-ai-to-revolutionize-quality-control-and-inspection)