Skip to content

Commit

Permalink
edited instructions in quick start and made small edits to index page…
Browse files Browse the repository at this point in the history
… and system requirements
  • Loading branch information
TheCyberMaven committed Aug 26, 2024
1 parent 9c68fdd commit ad9c08f
Show file tree
Hide file tree
Showing 3 changed files with 32 additions and 19 deletions.
12 changes: 6 additions & 6 deletions docs/intro.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,20 +5,20 @@ sidebar_position: 1
# Overview

GaiaNet is a decentralized computing infrastructure that enables everyone to create, deploy, scale, and monetize their own AI agents that reflect their styles, values, knowledge, and expertise.
It allows individuals and businesses to create AI agents. Each GaiaNet node provides
It allows individuals and businesses to create AI agents. Each GaiaNet node provides:

* a web-based chatbot UI. [Chat with a GaiaNet node](https://vitalik.gaianet.network/chatbot-ui/index.html) that is an expert on Ethereum.
* a web-based chatbot UI [Chat with a GaiaNet node](https://vitalik.gaianet.network/chatbot-ui/index.html) that is an expert on Ethereum.
* an OpenAI compatible API. [See how](user-guide/apps/dify) to use a GaiaNet node as a drop-in OpenAI replacement in your favorite AI agent app.

The API approach allows any agent application in the OpenAI ecosystem, which is 100% of AI agents today, to use GaiaNet as an alternative to OpenAI. Furthermore, while the OpenAI API is backed by a handful of models to give generic responses, each GaiaNet node can be heavily customized with a finetuned model supplemented by domain knowledge. For example, a GaiaNet node for a financial analyst agent can write SQL code to query SEC 10K filings to respond to user questions.
100% of today's AI agents are applications in the OpenAI ecosystem. With our API approach, GaiaNet is an alternative to OpenAI. Each GaiaNet node has the ability to be customized with a fine-tuned model supplemented by domain knowledge which eliminates the generic responses many have come to expect. For example, a GaiaNet node for a financial analyst agent can write SQL code to query SEC 10K filings to respond to user questions.

Similar GaiaNet nodes are organized into GaiaNet domains, which provide stable services by load balancing across the nodes. GaiaNet domains have public-facing URLs and promote agent services to their communities. When a user or an agent app sends an API request to the domain's API endpoint URL, the domain is responsible for directing the request to a node that is ready.
Similar GaiaNet nodes are organized into GaiaNet domains, to provide stable services by load balancing across the nodes. GaiaNet domains have public-facing URLs and promote agent services to their communities. When a user or an agent app sends an API request to the domain's API endpoint URL, the domain is responsible for directing the request to a node that is ready.

## Next steps:

### Users

If you are an end user of AI agent applications, you can
If you are an end user of AI agent applications, you can:

* [Find a list of interesting GaiaNet nodes you can chat with on the web, or access via API](./user-guide/nodes.md).
* [Use a GaiaNet node as the backend AI engine for your favorite AI agent apps](./category/agent-frameworks-and-apps).
Expand All @@ -32,7 +32,7 @@ If you are interested in running GaiaNet nodes, you can

### Creators

If you are a creator or knowledge worker interested in creating your own AI agent service, you can
If you are a creator or knowledge worker interested in creating your own AI agent service, you can:

* [Create your own knowledge base](./category/knowledge-bases).
* [Finetune a model to "speak" like you](./category/gaianet-node-with-finetuned-llms).
Expand Down
35 changes: 24 additions & 11 deletions docs/node-guide/quick-start.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,18 +3,31 @@ sidebar_position: 1
---

# Quick start with GaiaNet Node
This guide provides the requisite knowledge necessary to quickly get started with installing a GaiaNet node.

First, let's install GaiaNet a one-line installer on Mac, Linux, or Windows WSL. This installer will download the latest version of GaiaNet Node. Learn more about [system requirements](system-requirements).
### Prerequisites
Before you get started, ensure that you have the following on your system:

| System | Minimum Requirements |
|---|---|
| OSX with Apple Silicon (M1-M4 chip) | 16GB RAM (32GB recommended) |
| Ubuntu Linux 20.04 with Nvidia CUDA 12 SDK | 8GB VRAM on GPU |
| Azure/AWS | Nvidia T4 GPU Instance |

Learn more about [system requirements](system-requirements).

### Installing the node

1. Use the following command to download the latest version of the GaiaNet node:

```
curl -sSfL 'https://github.com/GaiaNet-AI/gaianet-node/releases/latest/download/install.sh' | bash
```

Next, run the command printed on the terminal to set up the environment path. The command is started with `source`.

2. Run the command printed on the terminal to set up the environment path, it is started with `source`.
![](quick-start.png)

Next, use the following command to initialize the GaiaNet node according to the configuration options
3. Use the following command to initialize the GaiaNet node according to the configuration options
in `$HOME/gaianet/config.json`.
By default, the GaiaNet is initialized with a [Phi-3](https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/) LLM and a [knowledge base about Paris](https://huggingface.co/datasets/gaianet/paris).
This command could take some time since it will download a very large LLM file.
Expand All @@ -23,28 +36,28 @@ This command could take some time since it will download a very large LLM file.
gaianet init
```

Finally, start your node.
4. Use the following command to start your node:

```
gaianet start
```

Upon a successful start, the command prints a public URL for the node. You can open a browser to that URL to see the node information and then chat with the AI agent on the node.
5. A successful start prints a public URL for the node. Opening a browser to that URL will display the node information and allow you to chat with the AI agent on the node.

```
... ... https://0xf63939431ee11267f4855a166e11cc44d24960c0.gaianet.xyz
```

The following command stops the node.
6. To stop the node:

```
gaianet stop
```

## Next steps

* [Customize](customize.md) your node. You probably do not wish to just run the default Phi-3 model and Paris knowledge base.
* [Register](register.md) and join the GaiaNet protocol network to receive payments.
* [Protect](tasks/protect.md) the node server to ensure stable service.
* Install and manage [multiple nodes](tasks/multiple.md) on a single machine.
- [Customize](customize.md) your node. You probably do not wish to just run the default Phi-3 model and Paris knowledge base.
- [Register](register.md) and join the GaiaNet protocol network to receive payments.
- [Protect](tasks/protect.md) the node server to ensure stable service.
- Install and manage [multiple nodes](tasks/multiple.md) on a single machine.

4 changes: 2 additions & 2 deletions docs/node-guide/system-requirements.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,13 +13,13 @@ You can install the GaiaNet on a wide variety of devices and operating systems w
If you are hosting the node in your home or office, it needs access to the public Internet to join the GaiaNet network.

## Supproted on
## Supported on

GaiaNet node software is designed to be cross-platform, allowing it to run on various CPU and GPU architectures. The GaiaNet installer automatically detects the presence of NVIDIA CUDA drivers and leverages the power of GPU accelerators on the device. More hardwares support are on the way.

### GPU

The GaianNet node can run on all types of NVIDIA GPU products from H100 to NVIDIA Jetson series of hardware.
The GaiaNet node can run on all types of NVIDIA GPU products from H100 to NVIDIA Jetson series of hardware.
It also runs on all Apple Silicon M-series GPUs.

### CPU
Expand Down

0 comments on commit ad9c08f

Please sign in to comment.