PAIG Client Library¶
The paig_client
library allows you to seamlessly integrate Privacera AI Governance into your Langchain projects.
This README provides a step-by-step guide on how to set up and use the library.
Installation¶
You can install the paig_client
library using pip
:
Bash | |
---|---|
Initialization¶
Start your PAIG-Server. Create your AI application and generate API key. Set the PAIG_APP_API_KEY
as environment variable.
Python | |
---|---|
Usage¶
Once you have completed the setup of paig_client, you can set the user in the context for PAIG Shield to use.
Using context manager¶
Code Example¶
You can refer to the Sample Code.
Additional ways of passing the PAIG_APP_API_KEY to set up Privacera Shield¶
Alternative Method: Pass API Key in Code
If you prefer not to use environment variables, you can directly pass the API key when initializing the library:
Python | |
---|---|
setup()
method in the provided sample code section below. Precedence Rule
If the PAIG_APP_API_KEY is set both as an environment variable and in the code, the key specified in the code will take priority.
You can create multiple applications¶
If your application has multiple AI models to be governed, you can create multiple applications as follows:
Python | |
---|---|
- Pass the api key as
application_config_api_key="<API_KEY>"
parameter to the setup function
And then you can pass the application object to the context manager as follows:
Python | |
---|---|
Note that you still need to invoke the privacera.client.setup() method before calling the privacera.client.setup_app(...) method.