Retrieve a Monitor's Details

Retrieve a monitor

from deeprails import DeepRails

DEEPRAILS_API_KEY = "YOUR_API_KEY"

client = DeepRails(
    api_key=DEEPRAILS_API_KEY,
)

monitor_response = client.monitor.retrieve(
    monitor_id="mon_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)
print(monitor_response.data.name)
print(monitor_response.data.status)

{
  "monitor_id": "mon_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  "name": "Test Monitor",
  "status": "active",
  "created_at": "2025-01-15T10:30:00Z",
  "updated_at": "2025-01-15T10:30:00Z",
  "stats": {
    "total_evaluations": 1,
    "completed_evaluations": 0,
    "failed_evaluations": 0,
    "queued_evaluations": 0,
    "in_progress_evaluations": 1
  },
  "evaluations": [
    {
      "evaluation_status": "in_progress",
      "run_mode": "smart",
      "model_input": {
        "user_prompt": "Hello, how are you?",
        "system_prompt": "You are a helpful assistant.",
        "ground_truth": "The user prefers that you refer to them as 'the user' instead of 'you'.",
        "context": [
          "User: 'Can you help me update my code from 5 years ago to use modern C++ practices?'"
        ]
      },
      "model_output": "I am good, thank you!",
      "guardrail_metrics": [
        "correctness"
      ],
      "nametag": "Test Evaluation",
      "progress": 50,
      "error_message": null,
      "evaluation_result": null,
      "evaluation_total_cost": null,
      "created_at": "2025-01-15T10:30:00Z"
    }
  ],
  "capabilities": [
    {
      "capability": "web_search"
    }
  ],
  "files": [
    {
      "file_name": "example.pdf",
      "file_id": "file_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
      "file_size": 1024
    }
  ],
  "description": "A monitor used to test the DeepRails SDK"
}

GET

monitor

{monitor_id}

Retrieve a monitor

from deeprails import DeepRails

DEEPRAILS_API_KEY = "YOUR_API_KEY"

client = DeepRails(
    api_key=DEEPRAILS_API_KEY,
)

monitor_response = client.monitor.retrieve(
    monitor_id="mon_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)
print(monitor_response.data.name)
print(monitor_response.data.status)

{
  "monitor_id": "mon_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  "name": "Test Monitor",
  "status": "active",
  "created_at": "2025-01-15T10:30:00Z",
  "updated_at": "2025-01-15T10:30:00Z",
  "stats": {
    "total_evaluations": 1,
    "completed_evaluations": 0,
    "failed_evaluations": 0,
    "queued_evaluations": 0,
    "in_progress_evaluations": 1
  },
  "evaluations": [
    {
      "evaluation_status": "in_progress",
      "run_mode": "smart",
      "model_input": {
        "user_prompt": "Hello, how are you?",
        "system_prompt": "You are a helpful assistant.",
        "ground_truth": "The user prefers that you refer to them as 'the user' instead of 'you'.",
        "context": [
          "User: 'Can you help me update my code from 5 years ago to use modern C++ practices?'"
        ]
      },
      "model_output": "I am good, thank you!",
      "guardrail_metrics": [
        "correctness"
      ],
      "nametag": "Test Evaluation",
      "progress": 50,
      "error_message": null,
      "evaluation_result": null,
      "evaluation_total_cost": null,
      "created_at": "2025-01-15T10:30:00Z"
    }
  ],
  "capabilities": [
    {
      "capability": "web_search"
    }
  ],
  "files": [
    {
      "file_name": "example.pdf",
      "file_id": "file_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
      "file_size": 1024
    }
  ],
  "description": "A monitor used to test the DeepRails SDK"
}

Monitors track all the data from each of the events submitted to them. This endpoint returns comprehensive information for the monitor including recent event history and observability stats, plus configuration details like name, description, and its status.

The stats object in the response has counts of the evaluations in each status and an evaluations array containing all evaluation records.

Use the optional limit query parameter to control the number of returned evaluations (defaults to 10).

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

monitor_id

string

required

The ID of the monitor to retrieve.

Query Parameters

limit

integer

default:10

Limit the number of returned evaluations associated with this monitor. Defaults to 10.

Response

Monitor retrieved successfully

monitor_id

string

required

A unique monitor ID.

Example:

"mon_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

name

string

required

Name of this monitor.

Example:

"Test Monitor"

status

enum<string>

required

Status of the monitor. Can be active or inactive. Inactive monitors no longer record and evaluate events.

Available options:

active,

inactive

Example:

"active"

created_at

string<date-time>

required

The time the monitor was created in UTC.

Example:

"2025-01-15T10:30:00Z"

updated_at

string<date-time>

required

The most recent time the monitor was modified in UTC.

Example:

"2025-01-15T10:30:00Z"

stats

object

required

Contains five fields used for stats of this monitor: total evaluations, completed evaluations, failed evaluations, queued evaluations, and in progress evaluations.

Show child attributes

stats.total_evaluations

integer

Total number of evaluations performed by this monitor.

Example:

1

stats.completed_evaluations

integer

Number of evaluations that completed successfully.

Example:

0

stats.failed_evaluations

integer

Number of evaluations that failed.

Example:

0

stats.queued_evaluations

integer

Number of evaluations currently queued.

Example:

0

stats.in_progress_evaluations

integer

Number of evaluations currently in progress.

Example:

1

evaluations

object[]

required

An array of all evaluations performed by this monitor. Each one corresponds to a separate monitor event.

Show child attributes

evaluations.evaluation_status

enum<string>

required

Status of the evaluation.

Available options:

in_progress,

completed,

canceled,

queued,

failed

evaluations.run_mode

enum<string>

required

Run mode for the evaluation. The run mode allows the user to optimize for speed, accuracy, and cost by determining which models are used to evaluate the event.

Available options:

precision_plus,

precision,

smart,

economy

Example:

"smart"

evaluations.model_input

object

required

A dictionary of inputs sent to the LLM to generate output. The dictionary must contain at least a user_prompt field or a system_prompt field. For ground_truth_adherence guardrail metric, ground_truth should be provided.

Option 1
Option 2

Show child attributes

evaluations.model_input.user_prompt

string

required

The user prompt used to generate the output.

Example:

"Hello, how are you?"

evaluations.model_input.system_prompt

string

The system prompt used to generate the output.

Example:

"You are a helpful assistant."

evaluations.model_input.ground_truth

string

The ground truth for evaluating Ground Truth Adherence guardrail.

Example:

"The user prefers that you refer to them as 'the user' instead of 'you'."

evaluations.model_input.context

string[]

Any structured information that directly relates to the model’s input and expected output—e.g., the recent turn-by-turn history between an AI tutor and a student, facts or state passed through an agentic workflow, or other domain-specific signals your system already knows and wants the model to condition on.

evaluations.model_output

string

required

Output generated by the LLM to be evaluated.

Example:

"I am good, thank you!"

evaluations.guardrail_metrics

enum<string>[]

An array of guardrail metrics that the input and output pair will be evaluated on.

Available options:

correctness,

completeness,

instruction_adherence,

context_adherence,

ground_truth_adherence,

comprehensive_safety

evaluations.nametag

string

An optional, user-defined tag for the evaluation.

Example:

"Test Evaluation"

evaluations.progress

integer

Evaluation progress. Values range between 0 and 100; 100 corresponds to a completed evaluation_status.

Required range: 0 <= x <= 100

Example:

50

evaluations.error_message

string

Error message if the evaluation failed.

Example:

null

evaluations.evaluation_result

object

Evaluation result consisting of average scores and rationales for each of the evaluated guardrail metrics.

Example:

null

evaluations.evaluation_total_cost

number<float>

Total cost of the evaluation.

Example:

null

evaluations.created_at

string<date-time>

The time the evaluation was created in UTC.

Example:

"2025-01-15T10:30:00Z"

capabilities

object[]

required

An array of extended AI capabilities associated with this monitor. Can be web_search, file_search, and/or context_awareness.

Show child attributes

capabilities.capability

string

The type of capability.

Example:

"web_search"

files

object[]

required

An array of files associated with this monitor.

Show child attributes

files.file_name

string

The name of the file.

Example:

"example.pdf"

files.file_id

string

The ID of the file.

Example:

"file_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

files.file_size

integer

The size of the file in bytes.

Example:

1024

description

string

Description of this monitor.

Example:

"A monitor used to test the DeepRails SDK"

Create a Monitor Update a Monitor

⌘I

API Documentation

Authorizations

Path Parameters

Query Parameters

Response