Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Metrics #642

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions ai/builders/get-started.mdx
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
---
title: Building on the AI Subnet
title: Building on the Livepeer AI Network
---

The AI Subnet, currently in its **Alpha** stage, is fully operational and
Livepeer AI, currently in its **Beta** stage, is fully operational and
already hosts several quality applications. At this stage, efforts are concentrated on
**network optimization** and **user experience enhancement**. While official
SDKs are still under development, developers can interact directly with the AI
subnet using the endpoints exposed by Livepeer network Gateway nodes. For a
comprehensive understanding of the AI Subnet endpoints and to experiment with
SDKs are still under development, developers can interact directly with Livepeer AI
using the endpoints exposed by Livepeer network Gateway nodes. For a
comprehensive understanding of Livepeer AI endpoints and to experiment with
the API, please refer to the
[AI Subnet API Reference](/ai/api-reference/text-to-image).
[Livepeer AI API Reference](/ai/api-reference/text-to-image).

<CardGroup cols={3}>
<Card
Expand All @@ -26,10 +26,10 @@ the API, please refer to the
icon="rectangle-terminal"
iconType="duotone"
>
Explore and interact with the AI Subnet API.
Explore and interact with Livepeer AI API.
</Card>
<Card title="Showcase" href="/ai/builders/showcase" icon="star">
Explore projects built on the AI Subnet.
Explore projects built on the Livepeer AI Network.
</Card>
</CardGroup>

Expand Down
2 changes: 1 addition & 1 deletion ai/builders/showcase.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ title: Showcase
>
<img src="/images/ai/showcase/dream.png" alt="Dream website" noZoom />
An open-source platform, built on **Stability-AI/StableStudio**, designed for
experimenting with all pipelines on the AI Subnet.
experimenting with all pipelines on the Livepeer AI Network.
</Card>
<Card title="Letsgenerate.ai" href="https://letsgenerate.ai">
<img
Expand Down
12 changes: 6 additions & 6 deletions ai/contributors/developers.mdx
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
---
title: Develop the AI Subnet
title: Contribute to Livepeer AI
---

It's great to see the decision to contribute to the Livepeer AI Subnet and help
It's great to see the decision to contribute to Livepeer AI and help
achieve the mission of **building a decentralized AI ecosystem**. Here are the
steps to get started:

Expand All @@ -12,11 +12,11 @@ steps to get started:
2. **Join the Livepeer Discord**: Join the Livepeer Discord at
https://discord.gg/7w2R6v and introduce yourself in the `ai-video` channel.
Share your background and what you are interested in building.
3. **Get familiar with the AI Subnet**: Read through the
[AI Subnet documentation](/ai/introduction) to understand the architecture
3. **Get familiar with Livepeer AI**: Read through the
[Livepeer AI documentation](/ai/introduction) to understand the architecture
and how it works.
4. **Follow the Developer Guides**: Read through the developer guides below to
get started with building on the AI Subnet.
get started with building on the Livepeer AI Network.

## Developer Guides

Expand All @@ -35,6 +35,6 @@ steps to get started:
iconType="duotone"
href="/ai/guides/add-pipeline"
>
Add a new pipeline to the AI Subnet.
Add a new pipeline to Livepeer AI.
</Card>
</CardGroup>
18 changes: 9 additions & 9 deletions ai/contributors/get-started.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,23 +2,23 @@
title: Get Started
---

It's fantastic to see interest in contributing to the Livepeer AI Subnet! There
It's fantastic to see interest in contributing to Livepeer AI! There
are many ways to contribute, and excitement is high to build a decentralized AI
ecosystem together ❤️. Here are a few ways to get started:

- **Orchestrators**: With GPUs that have at least 16GB of VRAM, contribution is
possible by setting up an AI Orchestrator node and processing AI tasks on the
AI Subnet. Check out the
Livepeer AI Network. Check out the
[Orchestrator Setup Guide](/ai/orchestrators/get-started) page to learn more.
- **Gateways**: Server hardware can be used to connect customers to the AI
Subnet by setting up an AI Gateway node. Check out the
- **Gateways**: Server hardware can be used to connect customers to Livepeer AI
by setting up an AI Gateway node. Check out the
[Set up AI Gateway](/ai/gateways/setup-gateway) page to learn more.
- **Founder**: Founders can contribute by building AI applications on the AI
Subnet. Check out the [Build on the AI Subnet](/ai/builders) page to learn
- **Founder**: Founders can contribute by building AI applications on the Livepeer AI
Network. Check out the [Build on the Livepeer AI Network](/ai/builders) page to learn
more.
- **Developers**: Open Source Developers can contribute by improving the AI
Subnet codebase. Check out the guide on
[Contributing to the AI Subnet](/ai/contribute-to-ai-subnet) to learn more.
- **Developers**: Open Source Developers can contribute by improving the Livepeer AI
codebase. Check out the guide on
[Contributing to Livepeer AI](/ai/contribute-to-ai-subnet) to learn more.

For any questions or help needed, reach out in the `ai-video` channel of the
[Livepeer Discord](https://discord.gg/7w2R6v). Support is available to help get
Expand Down
12 changes: 6 additions & 6 deletions ai/contributors/guides/add-model.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,14 +2,14 @@
title: Add new Model
---

Adding support for a new model to the AI Subnet is a great way to get started
with contributing to the Livepeer AI Subnet. This guide will walk you through
the steps to add a new model to the AI Subnet.
Adding support for a new model to Livepeer AI is a great way to get started
with contributing to Livepeer AI. This guide will walk you through
the steps to add a new model to Livepeer AI.

## Video Guide

In this video, one of the Livepeer ecosystem's core Developers will walk you
through the steps to add a new model to the AI Subnet.
through the steps to add a new model to Livepeer AI.

<iframe
width="560"
Expand All @@ -23,7 +23,7 @@ through the steps to add a new model to the AI Subnet.

## Step-by-Step Guide

Adding a new model to the AI Subnet is relatively straightforward since each
Adding a new model to Livepeer AI is relatively straightforward since each
supported [pipeline](/ai/guides/add-pipeline) is designed to support multiple
diffusion models in the respective diffusion pipeline. To add a new model, you
will need to follow these steps:
Expand All @@ -34,7 +34,7 @@ will need to follow these steps:
2. **Clone the Repository**: Clone the forked repository to your local machine.
3. **Find a Model**: Find a diffusion model from
[Hugging Face](https://huggingface.co/models?pipeline_tag=image-to-video)
that you would like to add to the AI Subnet. Replace the `image-to-video`
that you would like to add to Livepeer AI. Replace the `image-to-video`
pipeline tag in the URL with the pipeline tag of your choice.
4. **Download the Model**: Update the
[runner/dl_checkpoints.sh](https://github.com/livepeer/ai-worker/blob/main/runner/dl_checkpoints.sh#L73)
Expand Down
8 changes: 4 additions & 4 deletions ai/contributors/guides/add-pipeline.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,15 +2,15 @@
title: Add new Pipeline
---

Adding support for a new model to the AI Subnet offers the opportunity to expand
Adding support for a new model to Livepeer AI offers the opportunity to expand
its capabilities and provide more options for developers to build on top of the
Livepeer network. This guide will walk you through the steps to add a new model
to the AI Subnet.
to Livepeer AI.

## Video Guide

In this video, one of the Livepeer ecosystem's core Developers will walk you
through the steps to add a new pipeline to the AI Subnet.
through the steps to add a new pipeline to Livepeer AI.

<iframe
width="560"
Expand All @@ -24,7 +24,7 @@ through the steps to add a new pipeline to the AI Subnet.

## Step-by-Step Guide

Adding a new pipeline to the AI Subnet is more involved than
Adding a new pipeline to Livepeer AI is more involved than
[adding a new model](ai/contribute/guides), but it is still relatively
straightforward. To add a new pipeline, you will need to follow these steps:

Expand Down
4 changes: 2 additions & 2 deletions ai/gateways/get-started.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@
title: Get Started
---

If you're exploring joining the AI Subnet as a Gateway (formerly known as a
_Broadcaster_) to perform **AI inference task routing** on the Livepeer network
If you're exploring joining the Livepeer AI Network as a Gateway (formerly known as a
_Broadcaster_) to perform **AI inference task routing** on Livepeer Network
and provide inference services to customers, this guide is for you. It's
tailored to help you navigate the setup process of an AI Gateway node, mirroring
the [Gateway Setup Guide](/gateways/guides/gateway-overview) for the Mainnet
Expand Down
14 changes: 7 additions & 7 deletions ai/gateways/onchain.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,8 @@ title: On-chain Setup
---

The previous section covered the **off-chain** configuration of the AI Gateway
node. This section will explain how to connect an AI Gateway node to the AI
subnet and request AI inference jobs on-chain.
node. This section will explain how to connect an AI Gateway node to the Livepeer AI
Network and request AI inference jobs on-chain.

## Prerequisites

Expand All @@ -14,16 +14,16 @@ subnet and request AI inference jobs on-chain.

## Launch your On-chain AI Gateway

After setting up your AI Gateway **off-chain**, it's time to connect it to the
AI Subnet for on-chain AI inference jobs. This process is similar to the Mainnet
Transcoding Network Gateway setup, with a few extra flags due to AI Subnet
After setting up your AI Gateway **off-chain**, it's time to connect it to
Livepeer AI for on-chain AI inference jobs. This process is similar to the Mainnet
Transcoding Network Gateway setup, with a few extra flags due to Livepeer AI
software limitations. See the
[Mainnet Transcoding Network Gateway](/gateways/guides/gateway-overview) guide
for details. Below is a summary:

<Steps>
<Step title="Verify Off-chain AI Gateway">
Verify that your AI Gateway node is functioning correctly **off-chain** before connecting it to the AI Subnet. Refer to [the previous section](/ai/gateways/start-gateway) for more details.
Verify that your AI Gateway node is functioning correctly **off-chain** before connecting it to Livepeer AI. Refer to [the previous section](/ai/gateways/start-gateway) for more details.
</Step>
<Step title="Prepare your Ethereum account">
Ensure your Ethereum account has enough ETH to cover gas fees and AI inference jobs. Refer to the [Fund Gateway Guide](/gateways/guides/fund-gateway) for more details.
Expand All @@ -32,7 +32,7 @@ for details. Below is a summary:
Fund your AI Gateway to ensure it has sufficient **deposit** and **reserve** to pay for AI inference requests. Refer to the [Deposit Gateway Funds via Livepeer CLI](/gateways/guides/fund-gateway#deposit-gateway-funds-via-livepeer-cli) guide for more information.
</Step>
<Step title="Configure Transcoding Options">
Configure transcoding options, even though the AI Gateway is not a transcoding node, due to current AI Subnet software limitations. Refer to the [Transcoding Options](/gateways/guides/transcoding-options) guide for more details.
Configure transcoding options, even though the AI Gateway is not a transcoding node, due to current Livepeer AI software limitations. Refer to the [Transcoding Options](/gateways/guides/transcoding-options) guide for more details.
</Step>
<Step title="Launch an AI Gateway">
Launch your AI Gateway node. This process is similar to the **docker** or **binary** steps in the [previous section](/ai/gateways/start-gateway), but requires additional flags to enable on-chain functionality. Here's an example:
Expand Down
12 changes: 12 additions & 0 deletions ai/gateways/start-gateway/gateway-metrics.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
---
title: Gateway Metrics
---

The following AI Metrics are applicable to the Livepeer Gateway:

`Ticket_value_sent`: The value of the AI tickets that are send to the Orchestrators.
`Tickets_send`: The total amount of tickets send to the Orchestrators.
`ai_models_requested`: Tracks the number of requests per capability and model.
`ai_request_latency_score`: Measures latency scores per model request per orchestrator.
`ai_request_price`: Records the price paid per unit for each model request.
`ai_request_errors`: Logs AI request errors per orchestrator. If no orchestrator is specified, this indicates a general request scenario where no orchestrators were found.
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,13 @@
title: Start your AI Gateway
---

The AI Subnet is not yet integrated into the main
Livepeer AI is not yet integrated into the main
[go-livepeer](https://github.com/livepeer/go-livepeer) software due to its
**Alpha** status. To enable AI inference capabilities on your Gateway node,
**Beta** status. To enable AI inference capabilities on your Gateway node,
please use the `ai-video` branch of
[go-livepeer](https://github.com/livepeer/go-livepeer/tree/ai-video). This
branch contains the necessary software for the AI Gateway node. Currently, there
are two methods to run the AI Subnet software:
are two methods to run the Livepeer AI software:

- **Docker**: This is the most straightforward and recommended method to run the
AI Gateway node.
Expand All @@ -17,20 +17,20 @@ are two methods to run the AI Subnet software:

## Start the AI Gateway

Please follow the steps below to start your AI Subnet Gateway node:
Please follow the steps below to start your Livepeer AI Gateway node:

<Tabs>
<Tab title="Use Docker (Recommended)">
<Steps>
<Step title="Retrieve the AI Subnet Docker Image">
Fetch the latest AI Subnet Docker image from the [Livepeer Docker Hub](https://hub.docker.com/r/livepeer/go-livepeer) with the following command:
<Step title="Retrieve the Livepeer AI Docker Image">
Fetch the latest Livepeer AI Docker image from the [Livepeer Docker Hub](https://hub.docker.com/r/livepeer/go-livepeer) with the following command:

```bash
docker pull livepeer/go-livepeer:ai-video
```
</Step>
<Step title="Launch an (Offchain) AI Gateway">
Execute the AI Subnet Docker image using the following command:
Execute the Livepeer AI Docker image using the following command:

```bash
docker run \
Expand All @@ -50,7 +50,7 @@ Please follow the steps below to start your AI Subnet Gateway node:
This launches an **offchain** AI Gateway node. The flags are similar to those used for a Mainnet Transcoding Network Gateway node. For more information, see the [go-livepeer CLI reference](/references/go-livepeer/cli-reference).
</Step>
<Step title="Confirm Successful Startup of the AI Gateway">
If your AI Subnet Gateway node is functioning correctly, you should see the following output:
If your Livepeer AI Gateway node is functioning correctly, you should see the following output:

```bash
I0501 11:07:47.609839 1 mediaserver.go:201] Transcode Job Type: [{P240p30fps16x9 600k 30 0 426x240 16:9 0 0 0s 0 0 0 0} {P360p30fps16x9 1200k 30 0 640x360 16:9 0 0 0s 0 0 0 0}]
Expand All @@ -59,15 +59,15 @@ Please follow the steps below to start your AI Subnet Gateway node:
```
</Step>
<Step title="Check Port Availability">
To make your AI Subnet Gateway node accessible from the internet, you need to configure your network settings. Ensure that port `8937` is unblocked on your machine. Additionally, consider setting up port forwarding on your router, which will allow the Gateway node to be reachable from the internet.
To make your Livepeer AI Gateway node accessible from the internet, you need to configure your network settings. Ensure that port `8937` is unblocked on your machine. Additionally, consider setting up port forwarding on your router, which will allow the Gateway node to be reachable from the internet.
</Step>
</Steps>
</Tab>
<Tab title="Use Binaries">
<Steps>
{/* TODO: Simplify this step */}
<Step title="Download the Latest AI Subnet Binary">
Download the latest AI subnet binary for your system:
<Step title="Download the Latest Livepeer AI Binary">
Download the latest Livepeer AI binary for your system:

```bash
wget https://build.livepeer.live/go-livepeer/ai-video/stable/livepeer-<OS>-<ARCH>.tar.gz
Expand All @@ -81,13 +81,13 @@ Please follow the steps below to start your AI Subnet Gateway node:

See the [go-livepeer installation guide](/orchestrators/guides/install-go-livepeer#install-using-a-binary-release) for more information on the available binaries.

<Info>The windows and MacOS (amd64) binaries of the AI Subnet are not available yet.</Info>
<Info>The windows and MacOS (amd64) binaries of Livepeer AI are not available yet.</Info>
</Step>
<Step title="Extract and Configure the Binary">
Once downloaded, extract the binary to a directory of your choice.
</Step>
<Step title="Launch an (Offchain) AI Gateway">
Run the following command to start your AI Subnet Gateway node:
Run the following command to start your Livepeer AI Gateway node:

```bash
./livepeer \
Expand All @@ -102,7 +102,7 @@ Please follow the steps below to start your AI Subnet Gateway node:
This command launches an **offchain** AI Gateway node. These flags are similar to running a Mainnet Transcoding Network Gateway node. For more information see the [go-livepeer CLI reference](/references/go-livepeer/cli-reference).
</Step>
<Step title="Confirm Successful Startup of the AI Gateway">
If your AI Subnet Gateway node is functioning correctly, you should see the following output:
If your Livepeer AI Gateway node is functioning correctly, you should see the following output:

```bash
I0501 11:07:47.609839 1 mediaserver.go:201] Transcode Job Type: [{P240p30fps16x9 600k 30 0 426x240 16:9 0 0 0s 0 0 0 0} {P360p30fps16x9 1200k 30 0 640x360 16:9 0 0 0s 0 0 0 0}]
Expand All @@ -111,7 +111,7 @@ Please follow the steps below to start your AI Subnet Gateway node:
```
</Step>
<Step title="Check Port Availability">
To make your AI Subnet Gateway node accessible from the internet, you need to configure your network settings. Ensure that port `8937` is unblocked on your machine. Additionally, consider setting up port forwarding on your router, which will allow the Gateway node to be reachable from the internet.
To make your Livepeer AI Gateway node accessible from the internet, you need to configure your network settings. Ensure that port `8937` is unblocked on your machine. Additionally, consider setting up port forwarding on your router, which will allow the Gateway node to be reachable from the internet.
</Step>
</Steps>
<Note>
Expand All @@ -123,7 +123,7 @@ Please follow the steps below to start your AI Subnet Gateway node:

## Confirm the AI Gateway is Operational

After launching the AI Subnet Gateway node, verify its operation by sending an
After launching the Livepeer AI Gateway node, verify its operation by sending an
AI inference request directly to it. This requires an active **off-chain** AI
Orchestrator node. For guidance on setting up an AI Orchestrator node, refer to
the [AI Orchestrator Setup Guide](/ai/orchestrators/get-started).
Expand Down
Loading