[WIP] Docs: /start

README.md

@@ -91,7 +91,7 @@ Workflows allow you to extend simple model predictions to build computer vision
 
 ## 📟 connecting via api
 
-Once you've installed Infernece, your machine is a fully-featured CV center.
+Once you've installed Inference, your machine is a fully-featured CV center.
 You can use its API to run models and workflows on images and video streams.
 By default, the server is running locally on
 [`localhost:9001`](http://localhost:9001).
@@ -201,9 +201,11 @@ via the Roboflow UI.
 
 ## 🔑 connect to the cloud
 
-Without an API Key, you can access a wide range of pre-trained and foundational models and run Workflows via our JSON API.
+Without an API Key, you can access a wide range of pre-trained and foundational models and run public Workflows.
 
-Pass an optional [Roboflow API Key](https://app.roboflow.com/settings/api) to the `inference_sdk` or API to access additional features.
+Pass an optional [Roboflow API Key](https://app.roboflow.com/settings/api) to the `inference_sdk` or API to access additional features enhanced by Roboflow's Cloud
+platform. When running with an API Key, usage is metered according to
+Roboflow's [pricing tiers](https://roboflow.com/pricing).
 
 |                         | Open Access | With API Key |
 |-------------------------|-------------|--------------|
@@ -361,7 +363,7 @@ This is untested and performance improvements are not guaranteed.
 <details>
 <summary><b>Other Edge Devices</b></summary>
 <br />
-Roboflow has <a href="https://docs.roboflow.com/deploy/supported-deployment-devices">SDKs for running object detection natively</a> on other deployment targets like <a href="https://docs.roboflow.com/deploy/sdks/web-browser">Tensorflow.js in a web browser</a>, <a href="https://docs.roboflow.com/deploy/sdks/mobile-ios-on-device">Native Swift on iOS</a> via CoreML, and <a href="https://docs.roboflow.com/deploy/sdks/luxonis-oak">Luxonis OpenCV AI Kit (OAK)</a>.
+Roboflow has <a href="https://docs.roboflow.com/deploy/supported-deployment-devices">SDKs for running object detection natively</a> on other deployment targets like <a href="https://docs.roboflow.com/deploy/sdks/web-browser">Tensorflow.js in a web browser</a>, <a href="https://docs.roboflow.com/deploy/sdks/mobile-ios-on-device">Native Swift on iOS</a> via CoreML, and <a href="https://docs.roboflow.com/deploy/sdks/lens-studio">Snap Lens Studio</a>.
 <br /><br />
 Connect to an Inference Server via its API for additional functionality beyond object detection (like running Workflows).
 <br />

docs/inputs/images.md

@@ -0,0 +1 @@
+# Image Files

docs/inputs/index.md

@@ -0,0 +1 @@
+# Getting Images and Video into Inference

docs/inputs/industrial/basler.md

@@ -0,0 +1 @@
+# Use a Basler Camera with Inference

docs/inputs/industrial/flir.md

@@ -0,0 +1 @@
+# Use a FLIR Camera with Inference

docs/inputs/industrial/index.md

@@ -0,0 +1 @@
+# Industrial and Machine Vision Cameras

docs/inputs/industrial/lucid.md

@@ -0,0 +1 @@
+# Use a Lucid Camera with Inference

docs/inputs/rtsp/index.md

@@ -0,0 +1,4 @@
+# Streaming over RTSP
+
+The easiest way to stream video from most security cameras
+or IP cameras is over RTSP.

docs/inputs/rtsp/reolink.md

@@ -0,0 +1 @@
+# RTSP from a Reolink Camera

docs/inputs/rtsp/unifi.md

@@ -0,0 +1 @@
+# RTSP from a Ubiquiti UniFi Camera

docs/inputs/video.md

@@ -0,0 +1 @@
+# Recorded Video Files

docs/inputs/webcam.md

@@ -0,0 +1 @@
+# Using a Webcam

docs/install/cloud/aws.md

@@ -0,0 +1,71 @@
+# Deploy on AWS
+
+You can run Roboflow Inference on machines hosted on Amazon Web Services.
+
+This is ideal if you want to benefit from all of the features Inference has to offer but also want to manage your own cloud infrastructure.
+
+## Set up an AWS EC2 instance
+
+To get started, you will need an EC2 instance running on AWS.
+
+For deploying instances, we recommend SkyPilot, a tool designed to help you set up cloud instances for AI projects.
+
+To get started, run the following command on your own machine:
+
+```
+pip install inference "skypilot[gcp,aws]"
+```
+
+Follow the [SkyPilot AWS documentation](https://docs.skypilot.co/en/latest/getting-started/installation.html#cloud-account-setup) to authenticate with AWS
+
+Then, run:
+
+```
+inference cloud deploy --provider aws --compute-type gpu
+```
+
+This will provision a GPU-capable instance in AWS.
+
+The latest version of Roboflow Inference will be automatically installed on the machine.
+
+When the command has run, you should see a message like:
+
+```
+Deployed Roboflow Inference to aws on gpu, deployment name is ...
+To get a list of your deployments: inference status
+To delete your deployment: inference undeploy ...
+To ssh into the deployed server: ssh ...
+The Roboflow Inference Server is running at http://34.66.116.66:9001
+```
+
+You can then use the API endpoint for your server for use in running models.
+
+You can run any model that Inference supports, including object detection, segmentation, classification, and keypoint models that you have available on Roboflow, and foundation models like CLIP, PaliGemma, SAM-2, and more.
+
+## Run inference
+
+You can run inference with Roboflow models using the following code:
+
+```python
+from inference_sdk import InferenceHTTPClient
+
+# initialize the client
+CLIENT = InferenceHTTPClient(
+    api_url="https://yourendpoint.com"
+    api_key="YOUR_API_KEY"
+)
+
+# infer on a local image
+result = CLIENT.infer("YOUR_IMAGE.jpg", model_id="counting-screws/3")
+```
+
+Replace:
+
+1. The API URL with your AWS EC2 instance IP and port.
+2. API Key with your Roboflow API key.
+3. YOUR_IMAGE with the image you want to run inference on.
+4. Your model ID with your [Roboflow model ID](https://docs.roboflow.com/api-reference/workspace-and-project-ids).
+
+You can also run Roboflow Workflows on your deployment.
+
+[Learn how to run Workflows with Inference](http://127.0.0.1:8000/start/getting-started/#install-the-sdk).

docs/install/cloud/azure.md

@@ -0,0 +1,71 @@
+# Deploy on Azure
+
+You can run Roboflow Inference on machines hosted on Azure.
+
+This is ideal if you want to benefit from all of the features Inference has to offer but also want to manage your own cloud infrastructure.
+
+## Set up an Azure Cloud Compute VM
+
+To get started, you will need a cloud compute instance running on Azure.
+
+For deploying instances, we recommend SkyPilot, a tool designed to help you set up cloud instances for AI projects.
+
+To get started, run the following command on your own machine:
+
+```
+pip install inference "skypilot[azure]"
+```
+
+Follow the [SkyPilot Azure documentation](https://docs.skypilot.co/en/latest/getting-started/installation.html#cloud-account-setup) to authenticate with AWS
+
+Then, run:
+
+```
+inference cloud deploy --provider azure --compute-type gpu
+```
+
+This will provision a GPU-capable instance in Azure.
+
+The latest version of Roboflow Inference will be automatically installed on the machine.
+
+When the command has run, you should see a message like:
+
+```
+Deployed Roboflow Inference to azure on gpu, deployment name is ...
+To get a list of your deployments: inference status
+To delete your deployment: inference undeploy ...
+To ssh into the deployed server: ssh ...
+The Roboflow Inference Server is running at http://34.66.116.66:9001
+```
+
+You can then use the API endpoint for your server for use in running models.
+
+You can run any model that Inference supports, including object detection, segmentation, classification, and keypoint models that you have available on Roboflow, and foundation models like CLIP, PaliGemma, SAM-2, and more.
+
+## Run inference
+
+You can run inference with Roboflow models using the following code:
+
+```python
+from inference_sdk import InferenceHTTPClient
+
+# initialize the client
+CLIENT = InferenceHTTPClient(
+    api_url="https://yourendpoint.com"
+    api_key="YOUR_API_KEY"
+)
+
+# infer on a local image
+result = CLIENT.infer("YOUR_IMAGE.jpg", model_id="counting-screws/3")
+```
+
+Replace:
+
+1. The API URL with your Azure instance IP and port.
+2. API Key with your Roboflow API key.
+3. YOUR_IMAGE with the image you want to run inference on.
+4. Your model ID with your [Roboflow model ID](https://docs.roboflow.com/api-reference/workspace-and-project-ids).
+
+You can also run Roboflow Workflows on your deployment.
+
+[Learn how to run Workflows with Inference](/start/getting-started/#install-the-sdk).

docs/install/cloud/gcp.md

@@ -0,0 +1,71 @@
+# Deploy on Google Cloud Platform
+
+You can run Roboflow Inference on machines hosted on Google Cloud Platform (GCP).
+
+This is ideal if you want to benefit from all of the features Inference has to offer but also want to manage your own cloud infrastructure.
+
+## Set up a Google Cloud Compute VM
+
+To get started, you will need a cloud compute instance running on GCP.
+
+For deploying instances, we recommend SkyPilot, a tool designed to help you set up cloud instances for AI projects.
+
+To get started, run the following command on your own machine:
+
+```
+pip install inference "skypilot[gcp]"
+```
+
+Follow the [SkyPilot GCP documentation](https://docs.skypilot.co/en/latest/getting-started/installation.html#cloud-account-setup) to authenticate with AWS
+
+Then, run:
+
+```
+inference cloud deploy --provider gcp --compute-type gpu
+```
+
+This will provision a GPU-capable instance in GCP.
+
+The latest version of Roboflow Inference will be automatically installed on the machine.
+
+When the command has run, you should see a message like:
+
+```
+Deployed Roboflow Inference to gcp on gpu, deployment name is ...
+To get a list of your deployments: inference status
+To delete your deployment: inference undeploy ...
+To ssh into the deployed server: ssh ...
+The Roboflow Inference Server is running at http://34.66.116.66:9001
+```
+
+You can then use the API endpoint for your server for use in running models.
+
+You can run any model that Inference supports, including object detection, segmentation, classification, and keypoint models that you have available on Roboflow, and foundation models like CLIP, PaliGemma, SAM-2, and more.
+
+## Run inference
+
+You can run inference with Roboflow models using the following code:
+
+```python
+from inference_sdk import InferenceHTTPClient
+
+# initialize the client
+CLIENT = InferenceHTTPClient(
+    api_url="https://yourendpoint.com"
+    api_key="YOUR_API_KEY"
+)
+
+# infer on a local image
+result = CLIENT.infer("YOUR_IMAGE.jpg", model_id="counting-screws/3")
+```
+
+Replace:
+
+1. The API URL with your GCP instance IP and port.
+2. API Key with your Roboflow API key.
+3. YOUR_IMAGE with the image you want to run inference on.
+4. Your model ID with your [Roboflow model ID](https://docs.roboflow.com/api-reference/workspace-and-project-ids).
+
+You can also run Roboflow Workflows on your deployment.
+
+[Learn how to run Workflows with Inference](/start/getting-started/#install-the-sdk).

docs/install/cloud/index.md

@@ -0,0 +1,13 @@
+# Deploy in Your Own Cloud
+
+You can run Roboflow Inference on major cloud platforms like AWS, Azure, or GCP.
+
+Deploying in your own cloud is ideal if you want to manage the infrastructure behind your deployment.
+
+Roboflow Inference has an integration with SkyPilot that makes deploying a cloud instance to run Inference as quick as running one command after you have authenticated with your cloud provider.
+
+Read our deployment guides for more information:
+
+- [Set up Inference with AWS](/install/cloud/aws/)
+- [Set up Inference with Azure](/install/cloud/azure/)
+- [Set up Inference with GCP](/install/cloud/gcp/)

docs/install/enterprise-considerations.md

@@ -0,0 +1,10 @@
+## Enterprise Considerations
+
+[A Helm Chart](https://github.com/roboflow/inference/tree/main/inference/enterprise/helm-chart)
+is available for enterprise cloud deployments. Enterprise networking solutions to support
+deployment in OT networks are also available upon request.
+
+Roboflow also offers customized support and installation packages and
+[a pre-configured Jetson-based edge device](https://roboflow.com/hardware)
+suitable for rapid prototyping. [Contact our sales team](https://roboflow.com/sales)
+if you're part of a large organization and interested in learning more.

docs/install/index.md

@@ -0,0 +1,43 @@
+# Local Installation
+
+Inference is built to be run at the edge. It loads and executes model
+weights and does computation locally. It can run fully offline (once
+model weights are downloaded) but it's often useful to maintain a
+network connection for interfacing with outside systems (like PLCs on
+the local network, or remote systems for storing data and sending
+notifications).
+
+## Run via Docker
+
+The preferred way to use Inference is via Docker 
+(see [Why Docker](/understand/architecture/#why-docker)).
+
+[Install Docker](https://docs.docker.com/engine/install/) (and
+[NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
+for GPU acceleration if you have a CUDA-enabled GPU). Then run:
+
+```bash
+pip install inference-cli
+inference server start
+```
+
+The `inference server start` command attempts to automatically choose 
+and configure the optimal container to optimize performance on your machine.
+
+
+!!! Tip
+    Special installation notes and performance tips by device are also available.
+    Browse the navigation on the left for detailed install guides.
+
+## Dev Mode
+
+The `--dev` parameter to `inference server start` starts in development mode.
+This spins up a companion Jupyter notebook server with a quickstart guide on 
+[`localhost:9002`](http://localhost:9002). Dive in there for a whirlwind tour
+of your new Inference Server's functionality!
+
+```bash
+inference server start --dev
+```
+
+--8<-- "docs/install/using-your-new-server.md"