Humanloop Documentation and API Reference

Update a logged datapoint by its reference ID.

The reference_id query parameter must be provided, and refers to the reference_id of a previously-logged datapoint.

Query parameters

reference_idstringRequired

A unique string to reference the datapoint. Identifies the logged datapoint created with the same reference_id.

Request

This endpoint expects an object.

outputstringOptional

Generated output from your model for the provided inputs.

errorstringOptional

Error message if the log is an error.

durationdoubleOptional

Duration of the logged event in seconds.

Response

This endpoint returns an object

idstring

String ID of logged datapoint. Starts with data_.

configobject

evaluation_resultslist of objects

observability_statusenum

Allowed values: pendingrunningcompletedfailed

Status of a Log for observability.

Observability is implemented by running monitoring Evaluators on Logs.

updated_atdatetime

projectstringOptional

The name of the project associated with this log

project_idstringOptional

The unique ID of the project associated with this log.

session_idstringOptional

ID of the session to associate the datapoint.

session_reference_idstringOptional

A unique string identifying the session to associate the datapoint to. Allows you to log multiple datapoints to a session (using an ID kept by your internal systems) by passing the same session_reference_id in subsequent log requests. Specify at most one of this or session_id.

parent_idstringOptional

ID associated to the parent datapoint in a session.

parent_reference_idstringOptional

A unique string identifying the previously-logged parent datapoint in a session. Allows you to log nested datapoints with your internal system IDs by passing the same reference ID as parent_id in a prior log request. Specify at most one of this or parent_id. Note that this cannot refer to a datapoint being logged in the same request.

inputsmap from strings to anyOptional

The inputs passed to the prompt template.

sourcestringOptional

Identifies where the model was called from.

metadatamap from strings to anyOptional

Any additional metadata to record.

savebooleanOptional

Whether the request/response payloads will be stored on Humanloop.

source_datapoint_idstringOptional

ID of the source datapoint if this is a log derived from a datapoint in a dataset.

reference_idstringOptional

Unique user-provided string identifying the datapoint.

messageslist of objectsOptional

The messages passed to the to provider chat endpoint.

outputstringOptional

Generated output from your model for the provided inputs. Can be None if logging an error, or if logging a parent datapoint with the intention to populate it later

judgmentboolean or double or list of strings or stringOptional

config_idstringOptional

Unique ID of a config to associate to the log.

environmentstringOptional

The environment name used to create the log.

feedbacklist of objectsOptional

created_atdatetimeOptional

User defined timestamp for when the log was created.

errorstringOptional

Error message if the log is an error.

stdoutstringOptional

Captured log and debug statements.

durationdoubleOptional

Duration of the logged event in seconds.

output_messageobjectOptional

The message returned by the provider.

prompt_tokensintegerOptional

Number of tokens in the prompt used to generate the output.

output_tokensintegerOptional

Number of tokens in the output generated by the model.

prompt_costdoubleOptional

Cost in dollars associated to the tokens in the prompt.

output_costdoubleOptional

Cost in dollars associated to the tokens in the output.

provider_requestmap from strings to anyOptional

Raw request sent to provider.

provider_responsemap from strings to anyOptional

Raw response received the provider.

userstringOptional

User email address provided when creating the datapoint.

provider_latencydoubleOptional

Latency of provider response.

tokensintegerOptional

Total number of tokens in the prompt and output.

raw_outputstringOptional

Raw output from the provider.

finish_reasonstringOptional

Reason the generation finished.

toolslist of objectsOptional

A result from a tool used to populate the prompt template

tool_choice"none" or "auto" or "required" or objectOptional

Controls how the model uses tools. The following options are supported: 'none' forces the model to not call a tool; the default when no tools are provided as part of the model config. 'auto' the model can decide to call one of the provided tools; the default when tools are provided as part of the model config. Providing {'type': 'function', 'function': {name': <TOOL_NAME>}} forces the model to use the named function.

batch_idslist of stringsOptional

List of batch IDs the log belongs to.

1	curl -X PATCH "https://api.humanloop.com/v4/logs?reference_id=reference_id" \
2	-H "X-API-KEY: <apiKey>" \
3	-H "Content-Type: application/json" \
4	-d '{}'

1	{
2	"project": "project",
3	"project_id": "project_id",
4	"session_id": "session_id",
5	"session_reference_id": "session_reference_id",
6	"parent_id": "parent_id",
7	"parent_reference_id": "parent_reference_id",
8	"inputs": {
9	"key": "value"
10	},
11	"source": "source",
12	"metadata": {
13	"key": "value"
14	},
15	"save": true,
16	"source_datapoint_id": "source_datapoint_id",
17	"id": "id",
18	"reference_id": "reference_id",
19	"messages": [
20	{
21	"content": "content",
22	"name": "name",
23	"tool_call_id": "tool_call_id",
24	"role": "user",
25	"tool_calls": [
26	{
27	"id": "id",
28	"type": "function",
29	"function": {
30	"name": "name"
31	}
32	}
33	],
34	"tool_call": {
35	"name": "name"
36	}
37	}
38	],
39	"output": "output",
40	"judgment": true,
41	"config_id": "config_id",
42	"config": {
43	"type": "generic",
44	"id": "config",
45	"other": {
46	"key": "value"
47	},
48	"created_by": {
49	"id": "id",
50	"email_address": "email_address",
51	"full_name": "full_name",
52	"verified": true
53	},
54	"status": "config",
55	"name": "config",
56	"description": "config"
57	},
58	"environment": "environment",
59	"feedback": [
60	{
61	"type": "rating",
62	"value": true,
63	"data_id": "data_id",
64	"user": "user",
65	"created_at": "2024-01-15T09:30:00Z",
66	"id": "id"
67	}
68	],
69	"created_at": "2024-01-15T09:30:00Z",
70	"error": "error",
71	"stdout": "stdout",
72	"duration": 1.1,
73	"output_message": {
74	"content": "content",
75	"name": "name",
76	"tool_call_id": "tool_call_id",
77	"role": "user",
78	"tool_calls": [
79	{
80	"id": "id",
81	"type": "function",
82	"function": {
83	"name": "name"
84	}
85	}
86	],
87	"tool_call": {
88	"name": "name",
89	"arguments": "arguments"
90	}
91	},
92	"prompt_tokens": 1,
93	"output_tokens": 1,
94	"prompt_cost": 1.1,
95	"output_cost": 1.1,
96	"provider_request": {
97	"key": "value"
98	},
99	"provider_response": {
100	"key": "value"
101	},
102	"user": "user",
103	"provider_latency": 1.1,
104	"tokens": 1,
105	"raw_output": "raw_output",
106	"finish_reason": "finish_reason",
107	"tools": [
108	{
109	"id": "id",
110	"name": "name",
111	"signature": "signature",
112	"result": "result"
113	}
114	],
115	"tool_choice": "none",
116	"evaluation_results": [
117	{
118	"id": "id",
119	"evaluator_id": "evaluator_id",
120	"evaluator_version_id": "evaluator_version_id",
121	"evaluation_id": "evaluation_id",
122	"log_id": "log_id",
123	"version_id": "version_id",
124	"version": {
125	"key": "value"
126	},
127	"value": true,
128	"error": "error",
129	"updated_at": "2024-01-15T09:30:00Z",
130	"created_at": "2024-01-15T09:30:00Z"
131	}
132	],
133	"observability_status": "pending",
134	"updated_at": "2024-01-15T09:30:00Z",
135	"batch_ids": [
136	"batch_ids"
137	]
138	}

Update By Reference

Query parameters

Request

Response

Errors