Update Monitoring

Activate and deactivate Evaluators for monitoring the Flow. An activated Evaluator will automatically be run on all new "completed" Logs within the Flow for monitoring purposes.

Path parameters

idstringRequired

Request

This endpoint expects an object.

activatelist of objectsOptional

Evaluators to activate for Monitoring. These will be automatically run on new Logs.

deactivatelist of objectsOptional

Evaluators to deactivate. These will not be run on new Logs.

Response

Successful Response

pathstring

Path of the Flow, including the name, which is used as a unique identifier.

idstring

Unique identifier for the Flow.

attributesmap from strings to any

A key-value object identifying the Flow Version.

namestring

Name of the Flow.

version_idstring

Unique identifier for the specific Flow Version. If no query params provided, the default deployed Flow Version is returned.

created_atdatetime

updated_atdatetime

last_used_atdatetime

version_logs_countinteger

The number of logs that have been generated for this Flow Version

directory_idstring or null

ID of the directory that the file is in on Humanloop.

version_namestring or null

Unique name for the Flow version. Version names must be unique for a given Flow.

version_descriptionstring or null

Description of the Version.

descriptionstring or null

Description of the Flow.

schemamap from strings to any or null

The JSON schema for the File.

readmestring or null

Long description of the file.

tagslist of strings or null

List of tags associated with the file.

type"flow" or nullDefaults to flow

environmentslist of objects or null

The list of environments the Flow Version is deployed to.

created_byany or null

The user who created the Flow.

evaluator_aggregateslist of objects or null

Aggregation of Evaluator results for the Flow Version.

evaluatorslist of objects or null

The list of Monitoring Evaluators associated with the Flow Version.

1	{
2	"path": "Personal Projects/MedQA",
3	"id": "fl_6o701g4jmcanPVHxdqD0O",
4	"attributes": {
5	"prompt": {
6	"template": "You are a helpful assistant helping with medical anamnesis",
7	"model": "gpt-4o",
8	"temperature": 0.8
9	},
10	"tool": {
11	"name": "retrieval_tool_v3",
12	"description": "Retrieval tool for MedQA.",
13	"source_code": "def retrieval_tool(question: str) -> str:\n pass\n"
14	}
15	},
16	"name": "MedQA Flow",
17	"version_id": "flv_7ZNQREaScH0JkhUwtXrLN",
18	"created_at": "2024-07-08T22:40:35.656915",
19	"updated_at": "2024-07-08T22:40:35.656915",
20	"last_used_at": "2024-07-08T22:40:35.656915",
21	"version_logs_count": 0,
22	"version_name": "medqa-flow-v1",
23	"version_description": "Initial version",
24	"type": "flow",
25	"environments": [
26	{
27	"id": "env_ffSVxEBzJcBZ1H5jcNMVj",
28	"created_at": "2023-06-27T23:16:07.992339",
29	"name": "development",
30	"tag": "default"
31	}
32	],
33	"created_by": {
34	"id": "usr_01RJO1k2spBVqNUt1ASef",
35	"email_address": "raza@humanloop.com",
36	"full_name": "Raza Habib"
37	},
38	"evaluator_aggregates": null
39	}

Path parameters

Headers

Request

Response

Errors

1	from humanloop import Humanloop
2	client = Humanloop(api_key="YOUR_API_KEY", )
3	client.flows.update_monitoring(id='fl_6o701g4jmcanPVHxdqD0O', activate=[{'evaluator_version_id': 'evv_1abc4308abd'}], )