|
| 1 | +--- |
| 2 | +sidebar_position: 4 |
| 3 | +--- |
| 4 | + |
| 5 | +# Working with eliza |
| 6 | + |
| 7 | +eliza is a simple, fast, and lightweight AI agent framework. Recently, eliza has integrated Gaia as one of the [model service provider](https://github.com/elizaOS/eliza/pull/762). This means you can now use Gaia as the LLM service backend for the Eliza framework. |
| 8 | + |
| 9 | +### Build a Trump agent with eliza and Gaia |
| 10 | + |
| 11 | +This guide demonstrates how to create an agent with Trump-like characteristics using [the Get Started guide from eliza](https://elizaos.github.io/eliza/docs/quickstart/). |
| 12 | + |
| 13 | +#### Set up the environment |
| 14 | + |
| 15 | +> Note: Ensure your Node.js version is above 0.23.0 before proceeding. |
| 16 | +
|
| 17 | +Firstly, clone the Eliza repository: |
| 18 | + |
| 19 | +``` |
| 20 | +git clone https://github.com/elizaos/eliza.git |
| 21 | +cd eliza |
| 22 | +``` |
| 23 | + |
| 24 | +Next, install the required dependencies. |
| 25 | + |
| 26 | +``` |
| 27 | +pnpm install |
| 28 | +``` |
| 29 | + |
| 30 | +Then, build the local libraries. |
| 31 | + |
| 32 | +``` |
| 33 | +pnpm build |
| 34 | +``` |
| 35 | + |
| 36 | +#### Choose Gaia as the model service provider |
| 37 | + |
| 38 | +After that, we will need to configure the environment and use a Gaia node as model service provider. |
| 39 | + |
| 40 | +``` |
| 41 | +cp .env.example .env |
| 42 | +``` |
| 43 | + |
| 44 | +Then, edit the `.env` file to include Gaia-related configuration values: |
| 45 | + |
| 46 | +``` |
| 47 | +# Gaianet Configuration |
| 48 | +GAIANET_MODEL=llama3b |
| 49 | +GAIANET_SERVER_URL=https://llama3b.gaia.domains/v1 |
| 50 | +
|
| 51 | +SMALL_GAIANET_MODEL= # Default: llama3b |
| 52 | +SMALL_GAIANET_SERVER_URL= # Default: https://llama3b.gaia.domains/v1 |
| 53 | +MEDIUM_GAIANET_MODEL= # Default: llama |
| 54 | +MEDIUM_GAIANET_SERVER_URL= # Default: https://llama8b.gaia.domains/v1 |
| 55 | +LARGE_GAIANET_MODEL= # Default: qwen72b |
| 56 | +LARGE_GAIANET_SERVER_URL= # Default: https://qwen72b.gaia.domains/v1 |
| 57 | +
|
| 58 | +GAIANET_EMBEDDING_MODEL=nomic-embed |
| 59 | +USE_GAIANET_EMBEDDING=TRUE # Set to TRUE for GAIANET/768, leave blank for local |
| 60 | +``` |
| 61 | +By using this configuration, the system will utilize the Llama 3b Gaia domain as the LLM backend. You can replace `GAIANET_SERVER_URL` with a URL for your custom node or domain. |
| 62 | + |
| 63 | +#### Create the Trump agent |
| 64 | + |
| 65 | +The default character templates are located in the `characters` folder. |
| 66 | + |
| 67 | +Update the `modelProvider` for the desired character. For Gaia, the provider name is `gaianet`. |
| 68 | + |
| 69 | +``` |
| 70 | + "name": "trump", |
| 71 | + "clients": [], |
| 72 | + "modelProvider": "gaianet", |
| 73 | + "settings": { |
| 74 | + "secrets": {}, |
| 75 | + "voice": { |
| 76 | + "model": "en_US-male-medium" |
| 77 | + } |
| 78 | + }, |
| 79 | + "plugins": [], |
| 80 | +``` |
| 81 | + |
| 82 | +Then, we can use the following command line to start running the agent. |
| 83 | + |
| 84 | +``` |
| 85 | +pnpm run dev --character="characters/trump.character.json" |
| 86 | +``` |
| 87 | + |
| 88 | +After the service runs successfully, we can launch the client UI to interact with the agent: |
| 89 | + |
| 90 | +``` |
| 91 | +pnpm start:client |
| 92 | +``` |
| 93 | + |
| 94 | +Finally, open `http://localhost:5174/` on your browser to start chatting with the agent. |
| 95 | +<img width="1274" alt="image" src="https://github.com/user-attachments/assets/48474b35-1d40-4334-8ed0-c97f373c2b0b" /> |
| 96 | + |
| 97 | + |
| 98 | +### Advanced use case |
| 99 | + |
| 100 | +For more inspiration, refer to[Nader Fabit's example on building a Twitter AI bot](https://x.com/dabit3/status/1863772029565981144). |
| 101 | + |
| 102 | + |
| 103 | + |
| 104 | + |
| 105 | + |
0 commit comments