You can use Quotient’s SDK to log inputs and outputs from your retrieval or search-augmented AI applications.

​
Initialize the Logger

Initialize the Quotient logger with configuration settings for your application:

from quotientai import QuotientAI

quotient = QuotientAI(api_key="your-quotient-api-key")

logger = quotient.logger.init(
    app_path="my-first-app",
    environment="dev",
)

​
Parameters:

​
app_name
string
required

Name of your application. Core parameter used to identify the source of logs in the Quotient dashboard.

​
environment
string
required

Environment where your application is running (e.g., “dev”, “staging”, “prod”). Core parameter used to help segregate logs by deployment environment.

​
tags
object

Key-value pairs for categorizing and filtering logs. Useful for slicing analytics by dimensions like customer, feature, model version, etc.

Example: {"model": "gpt-4", "feature": "customer-support"}

​
sample_rate
float
default:"1.0"

Value that determines what percent of logs to persist. Valid range of 0.0 to 1.0.

​
hallucination_detection
boolean
default:"false"

Enable automatic detection of potential hallucinations in model outputs.

​
hallucination_detection_sample_rate
float
default:"0.0"

Value that determines what percent of logs to run hallucination detection on. Valid range of 0.0 to 1.0.

​
Returns:

​
QuotientLogger
object

A QuotientLogger object.

​
Send Logs

Log model interactions with context and metadata for analysis.

log_id = logger.log(
    user_query="How do I cook a goose?",
    model_output="The capital of France is Paris",
    documents=["Here is an excellent goose recipe..."]
)

​
Parameters:

​
user_query
string
required

The input query or prompt sent to the model.

​
model_output
string
required

The response generated by the model.

​
documents
array
required

List of document contents used as context for the model. Can be strings or dictionaries with page_content and optional metadata.

Used in hallucination detection and attribution analysis.

If a dictionary is passed, it must have the key page_content, containing the document text, and optionally metadata , containing any document metadata you want to capture about the document.

Example:

[
    "Sample Document 1 without metadata",
    {"page_content": "Sample Document 2 with metadata", "metadata": {"source": "google.com"},
    {"page_content": "Sample Document 3 without metadata"}
]

NOTE: One of documents, message_history, or instructions is required.

​
message_history
array

Previous messages in the conversation, following the OpenAI message format with role and content keys.

Used in hallucination detection and attribution analysis.

Example:

[
    {"role": "system", "content": "You are an expert on geography."},
    {"role": "user", "content": "What is the capital of France?"},
    {"role": "assistant", "content": "The capital of France is Paris"}
]

NOTE: One of documents, message_history, or instructions is required.

​
instructions
array

List of instructions provided to the model.

Used in hallucination detection and attribution analysis.

Example:

[
    "You are a helpful assistant that answers questions about the world.",
    "Answer the question in a concise manner. If you are not sure, say 'I don't know'."
]

NOTE: One of documents, message_history, or instructions is required.

​
tags
object
required

Additional tags to associate with each log entry.

Example: {"model": "gpt-4", "feature": "customer-support"}

​
Returns:

​
log_id
string

A UUID representing the unique identifier for the logged event.

​
Retrieve Logs

Retrieve logs sent to Quotient using the client.

logs = quotient.logs.list()

​
Returns:

​
logs
array
required

An array of Log objects containing the following fields:

​
Asynchronous Python client

You can also use the asynchronous Python client to log data and retrieve logs.

from quotientai import AsyncQuotientAI

quotient = AsyncQuotientAI(api_key="your-quotient-api-key")

logger = quotient.logger.init(
    app_path="my-first-app",
    environment="dev",
    sample_rate=1.0,
    hallucination_detection=True,
    hallucination_detection_sample_rate=1.0,
)

log_id = await logger.log(
    user_query="How do I cook a goose?",
    model_output="The capital of France is Paris",
    documents=["Here is an excellent goose recipe..."]
)

logs = await quotient.logs.list()
print(logs)