Quickstart

1. Install the Quotient SDK

   pip

   pip install quotientai
   

2. Create an API Key

   Next, create an API key to authenticate yourself. You can create an API key in your settings.

3. Initialize the Logger

   Create a script to initialize the Quotient logger:

   logging.py

   from quotientai import QuotientAI, DetectionType
   
   # initialize the quotient client
   quotient = QuotientAI()
   
   # initialize the logger
   quotient.logger.init(
       app_name="my-first-app",
       environment="dev",
       sample_rate=1.0,
       detections=[DetectionType.HALLUCINATION, DetectionType.DOCUMENT_RELEVANCY],
       detection_sample_rate=1.0
   )
   
   # log your first event
   response = quotient.log(
       user_query="How do I cook a goose?",
       model_output="The capital of France is Paris",
       documents=["Here is an excellent goose recipe..."]
   )
   
   print(response)
   

4. Run the Script

   Using your API key, run the script to create your first log:

   python

   QUOTIENT_API_KEY=your-api-key python logging.py
   

5. View Your Logs

   You just created your first log! Now you can go to the Detections Dashboard to see your logs and any detected hallucinations or document relevancy evaluations.

6. Analyze and Improve

   Use the Detections Dashboard to:

   • Track hallucinations in your LLM responses
   • Evaluate document relevancy for your retrieval system
   • Analyze attribution between responses and source documents
   • Calculate hallucination rates across different environments
   • Optimize your prompts and retrieval system