confidentialmind-core 0.1.11

Core functionality for interfacing with the ConfidentialMind stack

ConfidentialMind Core

Overview

The ConfidentialMind core package is a Python library that provides core functionality for interfacing with the ConfidentialMind stack. It manages configurations, handles connections between services, and provides utilities for both local development and deployment within the ConfidentialMind ecosystem.

Installation

pip install confidentialmind-core

Features

• Configuration management with real-time updates
• Service connectivity within the ConfidentialMind stack
• Support for local development and stack deployment

Usage

Initializing the ConfigManager

from confidentialmind_core.config_manager import ConfigManager, ConnectorSchema

config_manager = ConfigManager()
config_manager.init_manager(
    config_model=YourConfigModel,
    connectors=[ConnectorSchema(...)]
)

Using ConfigManager with Streamlit

(Requires Streamlit and the confidentialmind-app-helpers package)

from confidentialmind_app_helpers.streamlit_utils.config_manager_streamlit import init_config_manager

config_manager = init_config_manager(
    config_model=YourConfigModel,
    connectors=[ConnectorSchema(...)]
)

Accessing Configurations and Connectors

# Get the current configuration
config = config_manager.config

# Get the list of connectors
connectors = config_manager.connectors

# Get the stack ID for a specific connector
stack_id = config_manager.getStackIdForConnector("connector_config_id")

# Get the URL for a specific connector
url = config_manager.getUrlForConnector("connector_config_id")

Local Development

For local development:

1. Create a .env file in the root directory of your project.
2. Add the following lines to the .env file:

   CONFIDENTIAL_MIND_LOCAL_CONFIG=True
   

3. If your software has connectors and the respective service is also running locally, add the connector URLs to the .env file as well. For example, if the connector ID is llm_connector and the URL is http://localhost:8083, add the following line:

   llm_connector_URL=http://localhost:8083
   

4. If you want to connect a locally running service to a service running on a remote ConfidentialMind stack, add the URL and API key for the remote service to the .env file. For example, if the connector ID is llm_connector and the API key is your-api-key, add the following lines:

   llm_connector_URL=https://api.example.com/api/hrevxyjgdfwxkaguhpab/
   llm_connector_APIKEY=your-api-key
   

   Note: The URL and API key can be created and obtained from the ConfidentialMind portal: navigate to the service you want to connect to, click on the "API Keys" tab, and create a new API key. The URL and API key will be displayed there. You can also click the "Copy .env" button to copy the required environment variables to your clipboard. However, you must still replace the placeholder connector ID with the correct ID in the .env file.
5. The environment variables will be automatically loaded when you run the application.

The ConfigManager will use these environment variables to configure the application for local development.

Local Development with Array Connectors

For local development with array connectors, you can set environment variables in your .env file using this pattern:

# For a regular connector:
CONNECTOR_ID_URL=http://localhost:8000
CONNECTOR_ID_APIKEY=your.jwt.token

# For an array connector with multiple services:
ARRAY_CONNECTOR_ID_0_URL=http://localhost:8001
ARRAY_CONNECTOR_ID_0_APIKEY=first.jwt.token
ARRAY_CONNECTOR_ID_1_URL=http://localhost:8002
ARRAY_CONNECTOR_ID_1_APIKEY=second.jwt.token
ARRAY_CONNECTOR_ID_2_URL=http://localhost:8003
ARRAY_CONNECTOR_ID_2_APIKEY=third.jwt.token

Usage example

Here's an example of how to use this for array connectors:

# For a single connector
url, headers = get_api_parameters("CONNECTOR_ID")
response = requests.get(url, headers=headers)

# For an array connector
connector_params = get_array_api_parameters("ARRAY_CONNECTOR_ID")
for url, headers in connector_params:
    response = requests.get(url, headers=headers)
    # Process each response

Note

This package is designed to work within the ConfidentialMind ecosystem. Ensure you have the necessary permissions and access to the ConfidentialMind stack before using this package in a production environment.

For more detailed information on the ConfidentialMind SDK and its capabilities, please refer to the main SDK documentation.