Skip to content

Commit

Permalink
docs(ai): add AIServiceRegistry CLI flag (#675)
Browse files Browse the repository at this point in the history
This commit ensures that node operators are aware they have to use the `AIServiceRegistry` flag for processing or requesting AI jobs.

---------

Co-authored-by: Rafał Leszko <[email protected]>
  • Loading branch information
rickstaa and leszko authored Nov 7, 2024
1 parent ea07ffb commit 902fa49
Show file tree
Hide file tree
Showing 4 changed files with 26 additions and 33 deletions.
1 change: 1 addition & 0 deletions ai/gateways/onchain.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ for more information. Here’s a summary of the key steps:
<Step title="Launch the AI Gateway">
Now launch your AI Gateway node. The process is similar to the **docker** or **binary** setup in the [previous section](/ai/gateways/start-gateway), but requires additional flags to enable on-chain functionality. Example:

- `-AIServiceRegistry`: Ensures that the Gateway is connected to the Livepeer AI network.
- `-network=arbitrum-one-mainnet`: Connects the AI Gateway to the Arbitrum Mainnet network.
- `-ethUrl=https://arb1.arbitrum.io/rpc`: Sets the Arbitrum Mainnet RPC URL. Replace it with your own if necessary.
- `-ethKeystorePath=/root/.lpData/arbitrum-one-mainnet/keystore`: Sets the path to the Ethereum keystore file for the AI Gateway.
Expand Down
17 changes: 7 additions & 10 deletions ai/gateways/start-gateway.mdx
Original file line number Diff line number Diff line change
@@ -1,11 +1,8 @@
### Start your AI Gateway

The Livepeer AI network is currently in **Beta** and is not yet integrated into
the main [go-livepeer](https://github.com/livepeer/go-livepeer) software. To
enable AI inference capabilities on your Gateway node, use the `ai-video` branch
of [go-livepeer](https://github.com/livepeer/go-livepeer/tree/ai-video), which
includes the necessary software for running the AI Gateway. You can run the
Livepeer AI software in two ways:
The Livepeer AI network is currently in **Beta** but is already integrated into
the main [go-livepeer](https://github.com/livepeer/go-livepeer) software. You
can run the Livepeer AI software using one of the following methods:

- **Docker** (Recommended): The simplest and preferred method.
- **Pre-built Binaries**: An alternative if you prefer not to use Docker.
Expand All @@ -21,7 +18,7 @@ Follow the steps below to start your Livepeer AI Gateway node:
Fetch the latest [Livepeer AI Docker image](https://hub.docker.com/r/livepeer/go-livepeer) with the following command:

```bash
docker pull livepeer/go-livepeer:ai-video
docker pull livepeer/go-livepeer:master
```
</Step>
<Step title="Launch an Off-chain AI Gateway">
Expand All @@ -33,7 +30,7 @@ Follow the steps below to start your Livepeer AI Gateway node:
-v ~/.lpData2/:/root/.lpData2 \
-p 8937:8937 \
--network host \
livepeer/go-livepeer:ai-video \
livepeer/go-livepeer:master \
-datadir ~/.lpData2 \
-gateway \
-orchAddr <ORCH_LIST> \
Expand Down Expand Up @@ -65,7 +62,7 @@ Follow the steps below to start your Livepeer AI Gateway node:
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
wget https://build.livepeer.live/go-livepeer/livepeer-<OS>-<ARCH>.tar.gz
```

Replace `<OS>` and `<ARCH>` with your operating system and architecture (e.g., `linux-amd64` for Linux AMD64). For more details, see the [go-livepeer installation guide](/orchestrators/guides/install-go-livepeer#install-using-a-binary-release).
Expand Down Expand Up @@ -105,7 +102,7 @@ Follow the steps below to start your Livepeer AI Gateway node:
</Steps>

<Note>
If binaries are unavailable for your system, you can build the [ai-video branch](https://github.com/livepeer/go-livepeer/tree/ai-video) of [go-livepeer](https://github.com/livepeer/go-livepeer) from source. Refer to the [Livepeer installation guide](/orchestrators/guides/install-go-livepeer#install-using-a-binary-release) or reach out to the Livepeer community on [Discord](https://discord.gg/livepeer) for assistance.
If binaries are unavailable for your system, you can build the [master branch](https://github.com/livepeer/go-livepeer/tree/master) of [go-livepeer](https://github.com/livepeer/go-livepeer) from source. Refer to the [Livepeer installation guide](/orchestrators/guides/install-go-livepeer#install-using-a-binary-release) or reach out to the Livepeer community on [Discord](https://discord.gg/livepeer) for assistance.
</Note>
</Tab>

Expand Down
13 changes: 7 additions & 6 deletions ai/orchestrators/onchain.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -16,13 +16,12 @@ to the Livepeer AI network and earn fees for processing AI inference jobs.

## Ensure you can Redeem Tickets

Since the Livepeer AI network is in its **Beta** phase,
[its software](https://github.com/livepeer/go-livepeer/tree/ai-video) isn't
integrated with the Mainnet Transcoding Network
[software stack](https://github.com/livepeer/go-livepeer) yet. This means that
The Livepeer AI network is currently in **Beta** but is already integrated into
the main [go-livepeer](https://github.com/livepeer/go-livepeer) software.
However, it still uses a separate port for the AI Orchestrator. This means that
your **Mainnet Transcoding Network Orchestrator** is currently unable to
directly redeem AI-related tickets. However, there are two methods to enable
your AI Orchestrator node to redeem tickets:
directly redeem AI-related tickets. There are two methods to enable your AI
Orchestrator node to redeem tickets:

<Tabs>
<Tab title="Set Ticket Recipient (recommended)">
Expand Down Expand Up @@ -158,6 +157,8 @@ network. The commands to start the AI Orchestrator are similar to those for the
[off-chain Orchestrator](/ai/orchestrators/start-orchestrator), but with
additional flags to enable on-chain functionality:

- `-AIServiceRegistry`: Ensures that the Gateway is connected to the Livepeer AI
network.
- `-network=arbitrum-one-mainnet`: Connects the AI Orchestrator node to the
Arbitrum Mainnet network.
- `-ethUrl=https://arb1.arbitrum.io/rpc`: Sets the Arbitrum Mainnet RPC URL. You
Expand Down
28 changes: 11 additions & 17 deletions ai/orchestrators/start-orchestrator.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -8,18 +8,12 @@ title: Start your AI Orchestrator
or Gateway node may cause stability issues. Please proceed with caution.
</Warning>

The Livepeer AI network is not yet integrated into the main
[go-livepeer](https://github.com/livepeer/go-livepeer) software due to its
**Beta** status. To equip your Orchestrator node with AI inference capabilities,
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 Orchestrator. Currently, there
are two methods to run the Livepeer AI network software:

- **Docker**: This is the most straightforward and recommended method to run the
AI Orchestrator node.
- **Pre-built Binaries**: Pre-built binaries are available if you prefer not to
use Docker.
The Livepeer AI network is currently in **Beta** but is already integrated into
the main [go-livepeer](https://github.com/livepeer/go-livepeer) software. You
can run the Livepeer AI software using one of the following methods:

- **Docker** (Recommended): The simplest and preferred method.
- **Pre-built Binaries**: An alternative if you prefer not to use Docker.

## Orchestrator Node Architecture

Expand Down Expand Up @@ -51,7 +45,7 @@ Please follow the steps below to start your **combined AI orchestrator** node.
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
docker pull livepeer/go-livepeer:master
```
</Step>
<Step title="Fetch the Latest AI Runner Docker Image">
Expand Down Expand Up @@ -95,7 +89,7 @@ Please follow the steps below to start your **combined AI orchestrator** node.
-v /var/run/docker.sock:/var/run/docker.sock \
--network host \
--gpus all \
livepeer/go-livepeer:ai-video \
livepeer/go-livepeer:master \
-orchestrator \
-transcoder \
-serviceAddr 0.0.0.0:8936 \
Expand Down Expand Up @@ -139,13 +133,13 @@ Please follow the steps below to start your **combined AI orchestrator** node.
Download the latest Livepeer AI binary for your system:

```bash
wget https://build.livepeer.live/go-livepeer/ai-video/stable/livepeer-<OS>-gpu-<ARCH>.tar.gz
wget https://build.livepeer.live/go-livepeer/livepeer-<OS>-gpu-<ARCH>.tar.gz
```

Replace `<OS>` and `<ARCH>` with your system's operating system and architecture. For example, for a Linux system with an AMD64 architecture, the command would be:

```bash
wget https://build.livepeer.live/go-livepeer/ai-video/stable/livepeer-linux-gpu-amd64.tar.gz
wget https://build.livepeer.live/go-livepeer/livepeer-linux-gpu-amd64.tar.gz
```

See the [go-livepeer installation guide](/orchestrators/guides/install-go-livepeer#install-using-a-binary-release) for more information on the available binaries.
Expand Down Expand Up @@ -225,7 +219,7 @@ Please follow the steps below to start your **combined AI orchestrator** node.
</Step>
</Steps>
<Note>
If no binaries are available for your system, you can build the [ai-video branch](https://github.com/livepeer/go-livepeer/tree/ai-video) of [go-livepeer](https://github.com/livepeer/go-livepeer) from source by following the instructions in the [Livepeer repository](/orchestrators/guides/install-go-livepeer) or by reaching out to the Livepeer community on [Discord](https://discord.gg/livepeer).
If no binaries are available for your system, you can build the [master branch](https://github.com/livepeer/go-livepeer/tree/master) of [go-livepeer](https://github.com/livepeer/go-livepeer) from source by following the instructions in the [Livepeer repository](/orchestrators/guides/install-go-livepeer) or by reaching out to the Livepeer community on [Discord](https://discord.gg/livepeer).
</Note>
</Tab>

Expand Down

0 comments on commit 902fa49

Please sign in to comment.