Merge pull request #544 from komyg/update-quickstart-docs

Update docs for easier quickstart

docs/foundation/cogvlm.md

@@ -26,9 +26,13 @@ We recommend using CogVLM paired with inference HTTP API adjusted to run in GPU
 with our `inference-cli` tool. Run the following command to set up environment and run the API under 
 `http://localhost:9001`
 
+!!! warning
+    Make sure that you are running this at machine with an NVidia GPU! Otherwise CogVLM will not be available.
+
+
 ```bash
 pip install inference inference-cli inference-sdk
-inference server start  # make sure that you are running this at machine with GPU! Otherwise CogVLM will not be available
+inference server start
 ```
 
 Let's ask a question about the following image:

docs/quickstart/run_a_model.md

@@ -41,13 +41,24 @@ In the code above, we loaded a model and then we used that model's `infer(...)`
 Running inference is fun but it's not much to look at. Let's add some code to visualize our results.
 
 ```python
-from inference import get_model
+from io import BytesIO
+
+import requests
 import supervision as sv
-import cv2
+from inference import get_model
+from PIL import Image
+from PIL.ImageFile import ImageFile
 
-# define the image url to use for inference
-image_file = "people-walking.jpg"
-image = cv2.imread(image_file)
+
+def load_image_from_url(url: str) -> ImageFile:
+    response = requests.get(url)
+    response.raise_for_status()  # check if the request was successful
+    image = Image.open(BytesIO(response.content))
+    return image
+
+
+# load the image from an url
+image = load_image_from_url("https://media.roboflow.com/inference/people-walking.jpg")
 
 # load a pre-trained yolov8n model
 model = get_model(model_id="yolov8n-640")
@@ -59,21 +70,17 @@ results = model.infer(image)[0]
 detections = sv.Detections.from_inference(results)
 
 # create supervision annotators
-bounding_box_annotator = sv.BoundingBoxAnnotator()
+bounding_box_annotator = sv.BoxAnnotator()
 label_annotator = sv.LabelAnnotator()
 
 # annotate the image with our inference results
-annotated_image = bounding_box_annotator.annotate(
-    scene=image, detections=detections)
-annotated_image = label_annotator.annotate(
-    scene=annotated_image, detections=detections)
+annotated_image = bounding_box_annotator.annotate(scene=image, detections=detections)
+annotated_image = label_annotator.annotate(scene=annotated_image, detections=detections)
 
 # display the image
 sv.plot_image(annotated_image)
 ```
 
-The `people-walking.jpg` file is hosted <a href="https://media.roboflow.com/inference/people-walking.jpg" target="_blank">here</a>.
-
 ![People Walking Annotated](https://storage.googleapis.com/com-roboflow-marketing/inference/people-walking-annotated.jpg)
 
 ## Summary

mkdocs.yml

@@ -33,10 +33,10 @@ nav:
       - Enterprise Features: enterprise/enterprise.md
       - Inference Basics:
           - Roboflow Ecosystem: quickstart/roboflow_ecosystem.md
-          - "Models: Popular": quickstart/aliases.md
-          - "Models: Fine-tuned": quickstart/explore_models.md
-          - "Models: Universe": quickstart/load_from_universe.md
-          - "Models: Local Weights": models/from_local_weights.md
+          - 'Models: Popular': quickstart/aliases.md
+          - 'Models: Fine-tuned': quickstart/explore_models.md
+          - 'Models: Universe': quickstart/load_from_universe.md
+          - 'Models: Local Weights': models/from_local_weights.md
       - Supported Fine-Tuned Models:
           - YOLOv10: fine-tuned/yolov10.md
           - YOLOv9: fine-tuned/yolov9.md
@@ -56,6 +56,7 @@ nav:
           - Segment Anything 2 (Segmentation): foundation/sam2.md
           - YOLO-World (Object Detection): foundation/yolo_world.md
       - Run a Model:
+          - Getting started: quickstart/run_a_model.md
           - Predict on an Image Over HTTP: quickstart/run_model_on_image.md
           - Predict on a Video, Webcam or RTSP Stream: quickstart/run_model_on_rtsp_webcam.md
           - Predict Over UDP: quickstart/run_model_over_udp.md
@@ -104,7 +105,7 @@ nav:
   - Cookbooks: cookbooks.md
 
 theme:
-  name: "material"
+  name: 'material'
   logo: inference-icon.png
   favicon: inference-icon.png
   custom_dir: docs/theme
@@ -124,13 +125,13 @@ theme:
 
   palette:
     - scheme: default
-      primary: "custom"
+      primary: 'custom'
       toggle:
         icon: material/brightness-7
         name: Switch to dark mode
 
     - scheme: slate
-      primary: "custom"
+      primary: 'custom'
       toggle:
         icon: material/brightness-4
         name: Switch to light mode
@@ -166,6 +167,6 @@ markdown_extensions:
       permalink: true
 
 extra_javascript:
-  - "https://widget.kapa.ai/kapa-widget.bundle.js"
-  - "javascript/init_kapa_widget.js"
-  - "javascript/cookbooks.js"
+  - 'https://widget.kapa.ai/kapa-widget.bundle.js'
+  - 'javascript/init_kapa_widget.js'
+  - 'javascript/cookbooks.js'