Skip to content

Commit

Permalink
Merge pull request #32 from gizatechxyz/feature/add-arbitrum-tutorial
Browse files Browse the repository at this point in the history 
Add Arbitrum tutorial
  • Loading branch information
@Gonmeso
Gonmeso authored Apr 16, 2024
2 parents eb87f3e + 190c7fc commit 64e2167
Show file tree
Hide file tree
Showing 2 changed files with 289 additions and 2 deletions.
4 changes: 2 additions & 2 deletions examples/agents/mnist_agent_tutorial.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -126,8 +126,8 @@
"from giza_actions.task import task\n",
"\n",
"# Make sure to fill these in\n",
"MODEL_ID = 148\n",
"VERSION_ID = 1\n",
"MODEL_ID = ...\n",
"VERSION_ID = ...\n",
"# As we are executing in sepolia, we need to specify the chain\n",
"CHAIN = \"ethereum:sepolia:geth\"\n",
"# The address of the deployed contract\n",
Expand Down
287 changes: 287 additions & 0 deletions examples/agents/using_arbitrum.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,287 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Using Arbitrum with Agents\n",
"\n",
"In the previous tutorial we have seen how to use the `GizaAgent` class to create a simple agent that can interact with the Ethereum blockchain. In this tutorial we will see how to use other chains with the `GizaAgent` class.\n",
"\n",
"As we rely on `ape` to interact with the blockchain, we can use any chain that ape supports. The list of supported chains via plugins can be found [here](https://docs.apeworx.io/).\n",
"\n",
"In this tutorial we will use `Arbitrum` as an example. The `Arbitrum` is a layer 2 solution for Ethereum that provides low cost and fast transactions. The `Arbitrum` is supported by `ape` and we can use it with the `GizaAgent` class.\n",
"\n",
"## Before you begin\n",
"\n",
"1. Python 3.11 or later must be installed on your machine\n",
"2. Giza CLI must be installed on your machine. You can install it by running `pip install giza-cli`\n",
"3. Actions-SDK should be installed with the extra `agents`. You can install it by running `pip install giza-actions[agents]`\n",
"4. You must have an active Giza account. If you don't have one, you can create one [here](https://cli.gizatech.xyz/examples/basic).\n",
"5. You must have a model deployed on Giza. You can follow the tutorial [Build a Verifiable Neural Network with Giza Actions](https://actions.gizatech.xyz/tutorials/build-a-verifiable-neural-network-with-giza-actions) to deploy a MNIST model on Giza.\n",
"6. During the tutorial, you will need to interact with the Giza CLI, Ape's framework, and provide multiple inputs, like `model-id`, `version-id`, `account name`, etc.\n",
"7. You have to be logged in to the Giza CLI or have an API KEY.\n",
"\n",
"## Installing the required libraries\n",
"\n",
"Let's start by installing the required libraries.\n",
"\n",
"```bash\n",
"pip install giza-actions[agents]\n",
"```\n",
"\n",
"This will install the `giza-actions` library along with the `agents` extra, which contains the necessary tools to create an AI Agent.\n",
"\n",
"## Creating an account\n",
"\n",
"Before we can create an AI Agent, we need to create an account using Ape's framework. We can do this by running the following command:\n",
"\n",
"```bash\n",
"$ ape accounts generate <account name>\n",
"Enhance the security of your account by adding additional random input:\n",
"Show mnemonic? [Y/n]: n\n",
"Create Passphrase to encrypt account:\n",
"Repeat for confirmation:\n",
"SUCCESS: A new account '0x766867bB2E3E1A6E6245F4930b47E9aF54cEba0C' with HDPath m/44'/60'/0'/0/0 has been added with the id '<account name>'\n",
"```\n",
"\n",
"This will create a new account under `$HOME/.ape/accounts` using the keyfile structure from the [eth-keyfile library](https://github.com/ethereum/eth-keyfile)\n",
", for more information on the account management, you can refer to the [Ape's framework documentation](https://docs.apeworx.io/ape/stable/userguides/accounts.html#keyfile-accounts).\n",
"\n",
"In this account generation we will be prompted to enter a passphrase to encrypt the account, this passphrase will be used to unlock the account when needed, so **make sure to keep it safe**.\n",
"\n",
"We encourage the creation of a new account for each agent, as it will allow you to manage the agent's permissions and access control more effectively, but importing accounts is also possible.\n",
"\n",
"## Creating an AI Agent\n",
"\n",
"Now that we have a funded account, we can create an AI Agent. We can do this by running the following command:\n",
"\n",
"```bash\n",
"giza agents create --model-id <model-id> --version-id <version-id> --name <agent name> --description <agent description>\n",
"\n",
"# or if you have the endpoint-id\n",
"\n",
"giza agents create --endpoint-id <endpoint-id> --name <agent name> --description <agent description>\n",
"```\n",
"\n",
"This command will prompt you to choose the account you want to use with the agent, once you select the account, the agent will be created and you will receive the agent id. The output will look like this:\n",
"\n",
"```console\n",
"[giza][2024-04-10 11:50:24.005] Creating agent ✅\n",
"[giza][2024-04-10 11:50:24.006] Using endpoint id to create agent, retrieving model id and version id\n",
"[giza][2024-04-10 11:50:53.480] Select an existing account to create the agent.\n",
"[giza][2024-04-10 11:50:53.480] Available accounts are:\n",
"┏━━━━━━━━━━━━━┓\n",
"┃ Accounts ┃\n",
"┡━━━━━━━━━━━━━┩\n",
"│ my_account │\n",
"└─────────────┘\n",
"Enter the account name: my_account\n",
"{\n",
" \"id\": 1,\n",
" \"name\": <agent_name>,\n",
" \"description\": <agent_description>,\n",
" \"parameters\": {\n",
" \"model_id\": <model_id>,\n",
" \"version_id\": <version_id>,\n",
" \"endpoint_id\": <endpoint_id>,\n",
" \"alias\": \"my_account\"\n",
" },\n",
" \"created_date\": \"2024-04-10T09:51:04.226448\",\n",
" \"last_update\": \"2024-04-10T09:51:04.226448\"\n",
"}\n",
"```\n",
"\n",
"This will create an AI Agent that can be used to interact with the deployed MNIST model.\n",
"\n",
"## Use Agents in Arbitrum\n",
"\n",
"Let's start by installing the `ape-arbitrum` plugin."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!ape plugins install arbitrum"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can confirm if it has been installed by executing `ape networks list` in the terminal."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1;32marbitrum\u001b[0m\n",
"├── \u001b[1;32mgoerli\u001b[0m\n",
"│ ├── \u001b[1;32malchemy\u001b[0m\n",
"│ └── \u001b[1;32mgeth\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"├── \u001b[1;32mlocal\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"│ └── \u001b[1;32mtest\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"├── \u001b[1;32mmainnet\u001b[0m\n",
"│ ├── \u001b[1;32malchemy\u001b[0m\n",
"│ └── \u001b[1;32mgeth\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"└── \u001b[1;32msepolia\u001b[0m\n",
" ├── \u001b[1;32malchemy\u001b[0m\n",
" └── \u001b[1;32mgeth\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"\u001b[1;32methereum\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"├── \u001b[1;32mgoerli\u001b[0m\n",
"│ ├── \u001b[1;32malchemy\u001b[0m\n",
"│ └── \u001b[1;32mgeth\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"├── \u001b[1;32mlocal\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"│ ├── \u001b[1;32mgeth\u001b[0m\n",
"│ └── \u001b[1;32mtest\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"├── \u001b[1;32mmainnet\u001b[0m\n",
"│ ├── \u001b[1;32malchemy\u001b[0m\n",
"│ └── \u001b[1;32mgeth\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n",
"└── \u001b[1;32msepolia\u001b[0m\n",
" ├── \u001b[1;32malchemy\u001b[0m\n",
" └── \u001b[1;32mgeth\u001b[0m\u001b[1;2;39m (default)\u001b[0m\n"
]
}
],
"source": [
"!ape networks list"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Here we can se that we have multiple networks available, including `arbitrum`. So now we can use it when instantiating the `GizaAgent` class.\n",
"\n",
"For this execution, we will use Arbitrum mainnet and use a private RPC node, this is because public nodes have small quotas that can easily be reached.\n",
"\n",
"The contract is a verified contract selected at random from [arbiscan](https://arbiscan.io/), the mission is to showcase that we can read properties from this contract, which means that we could also be able to execute a write function.\n",
"\n",
"In this case as we are only executing a read function we dont need a funded wallet to do anything as we won't sign any transactions.\n",
"\n",
"Remember that we will need to specify the `<Account>_PASSPHRASE` if you are launching your operation as a script, exporting it will be enough:\n",
"\n",
"```bash\n",
"export <Account>_PASSPHRASE=your-passphrase\n",
"```\n",
"\n",
"If you are using it from a notebook you will need to launch the notebook instance from an environment with the passphrase variable or set it in the code prior to importing `giza_actions`:\n",
"\n",
"```python\n",
"import os\n",
"os.environ[\"<Account>_PASSPHRASE\"] = \"your-passphrase\"\n",
"\n",
"\n",
"from giza_actions.agent import GizaAgent\n",
"...\n",
"```\n",
"\n",
"Now we can instantiate the agent:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"<Account>_PASSPHRASE\"] = ...\n",
"\n",
"\n",
"from giza_actions.agent import GizaAgent\n",
"\n",
"MODEL_ID = ...\n",
"VERSION_ID = ...\n",
"ACCOUNT = ...\n",
"PRIVATE_RPC = ... # This can also be loaded from the environment or a .env file\n",
"\n",
"agent = GizaAgent(\n",
" id=MODEL_ID,\n",
" version_id=VERSION_ID,\n",
" chain=f\"arbitrum:mainnet:{PRIVATE_RPC}\",\n",
" account=ACCOUNT,\n",
" contracts={\n",
" \"random\": \"0x8606d62fD47473Fad2db53Ce7b2B820FdEab7AAF\"\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now that we have the agent instance we can enter the `execute()` context and call the read function from an Arbitrum smart contract:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"INFO: Connecting to a 'nitro' node.\n",
"WARNING: Danger! This account will now sign any transaction it's given.\n",
"Contract name is: FatalDoge\n"
]
}
],
"source": [
"with agent.execute() as contracts:\n",
" result = contracts.random.name()\n",
" print(f\"Contract name is: {result}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## What we have learned\n",
"\n",
"In this tutorial, we learned how to create an AI Agent and interact with Arbitrum.\n",
"\n",
"For this we needed to:\n",
"\n",
"* Install the arbitrum plugin\n",
"* Check that the new network is available\n",
"* Got a contract from arbiscan\n",
"* Use an agent to execute a function from an arbitrum smart contract\n",
"\n",
"Now this same steps can be followed to use any other network supported by `ape` and interact with different chains."
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

0 comments on commit 64e2167

Please sign in to comment.