# APIs

## SDK Class Descriptions 📚

### 1. Settings Class (openmeta/config/settings.py) ⚙️

**Description**: This class manages the SDK’s configuration settings, allowing for retrieval and updating of configuration values.\
**Methods**:

* `get(key: str)`: Retrieves the configuration value based on the provided key.
* `set(key: str, value)`: Sets a configuration value for the specified key.

### 2. AgentCustomization Class (openmeta/core/agent\_customization.py) ✨

**Description**: This class allows for the customization of agent behavior, including custom settings for various tasks.\
**Methods**:

* `customize_behavior(agent_id: str, params: dict)`: Customizes the agent’s behavior based on the given agent ID and parameters.
* `get_current_customizations(agent_id: str)`: Retrieves the current customizations applied to the agent.

### 3. Agent Class (openmeta/core/agent.py) 🤖

**Description**: This class represents an agent capable of handling various tasks such as data processing, email sending, API integration, and blockchain logging.\
**Methods**:

* `add_task(task)`: Adds a new task to the agent's queue.
* `process_tasks()`: Processes all tasks in the agent's queue.
* `handle_task(task)`: Handles a specific task based on its type.
* `process_data(task, customizations)`: Processes data for a given task.
* `send_email(task, customizations)`: Sends an email for a task.
* `integrate_api(task, customizations)`: Integrates with an external API for the task.
* `log_to_blockchain(task, customizations)`: Logs data to the blockchain.

### 4. Memory Class (openmeta/core/memory.py) 💾

**Description**: This class stores and retrieves data in memory, allowing agents to store temporary information that can be accessed later.\
**Methods**:

* `store(data: str)`: Stores data in memory.
* `retrieve(index: int)`: Retrieves stored data by a specific index.

### 5. TaskQueue Class (openmeta/core/task\_queue.py) 🗂️

**Description**: This class manages a queue of tasks, allowing the agent to add tasks and process them sequentially.\
**Methods**:

* `add_to_queue(task)`: Adds a task to the queue.
* `process_queue()`: Processes all tasks in the queue.

### 6. Tool Class (openmeta/core/tools.py) 🔧

**Description**: This class is used to execute external tools, allowing various arguments and parameters to be used for the execution.\
**Methods**:

* `execute(*args, **kwargs)`: Executes an external tool with the provided arguments and parameters.

### 7. Web3Logger Class (openmeta/core/web3\_logger.py) 📡

**Description**: This class handles logging agent actions to the blockchain using Web3, enabling integration with blockchain networks.\
**Methods**:

* `log_to_blockchain(agent_id: str, action: str)`: Logs an agent’s action to the blockchain.
* `retrieve_log(agent_id: str)`: Retrieves the action logs for an agent from the blockchain.

### 8. BlockchainConnector Class (openmeta/integrations/blockchain.py) 🔗

**Description**: This class connects the SDK to a blockchain network (such as Ethereum or Binance), handling provider URL setup and Web3 connection.\
**Methods**:

* `get_provider_url(network: str)`: Returns the provider URL for the selected network.
* `connect()`: Connects to the specified blockchain network.

### 9. ExternalAPI Class (openmeta/integrations/external\_api.py) 🌐

**Description**: This class is used to integrate with and fetch data from an external API, allowing communication with other services.\
**Methods**:

* `fetch_data(endpoint: str, params: dict)`: Fetches data from an external API endpoint.

### 10. ErrorHandler Functions (openmeta/utils/errorhandler.py) ⚠️

**Description**: These functions handle errors by logging them and performing fallback actions, such as retrying or switching to a backup agent.\
**Methods**:

* `handle_error(exception: Exception, agent_id: Optional[str])`: Handles errors by logging them and executing fallback actions.
* `fallback_action(agent_id: Optional[str])`: Executes fallback actions, such as retrying a task.
* `retry_task(agent_id: str)`: Retries a task for a specified agent.

### 11. LoggingUtils Class (openmeta/utils/logging\_utils.py) 📜

**Description**: This class provides enhanced logging functionalities, allowing for messages to be logged at different severity levels.\
**Methods**:

* `log(message: str)`: Logs a message at the specified level.

### 12. Validator Class (openmeta/utils/validators.py) ✔️

**Description**: This class validates the data received by agents, ensuring that the input is in the correct format.\
**Methods**:

* `validate_data(data)`: Validates that the input data is a dictionary.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://evangelinelabs.gitbook.io/ethereal/setup/apis.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.