Update By 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

Successful Response

idstring

String ID of logged datapoint. Starts with data_.

configobject

evaluation_resultslist of objects

observability_statusenum

Status of a Log for observability. Observability is implemented by running monitoring Evaluators on Logs.

Allowed values:

updated_atdatetime

projectstring or null

The name of the project associated with this log

project_idstring or null

The unique ID of the project associated with this log.

session_idstring or null

ID of the session to associate the datapoint.

session_reference_idstring or null

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_idstring or null

ID associated to the parent datapoint in a session.

parent_reference_idstring or null

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 any or null

The inputs passed to the prompt template.

sourcestring or null

Identifies where the model was called from.

metadatamap from strings to any or null

Any additional metadata to record.

saveboolean or nullDefaults to true

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

source_datapoint_idstring or null

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

reference_idstring or null

Unique user-provided string identifying the datapoint.

messageslist of objects or null

The messages passed to the to provider chat endpoint.

outputstring or null

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 string or null

config_idstring or null

Unique ID of a config to associate to the log.

environmentstring or null

The environment name used to create the log.

feedbacklist of objects or null

created_atdatetime or null

User defined timestamp for when the log was created.

errorstring or null

Error message if the log is an error.

stdoutstring or null

Captured log and debug statements.

durationdouble or null

Duration of the logged event in seconds.

output_messageobject or null

The message returned by the provider.

prompt_tokensinteger or null

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

output_tokensinteger or null

Number of tokens in the output generated by the model.

prompt_costdouble or null

Cost in dollars associated to the tokens in the prompt.

output_costdouble or null

Cost in dollars associated to the tokens in the output.

provider_requestmap from strings to any or null

Raw request sent to provider.

provider_responsemap from strings to any or null

Raw response received the provider.

userstring or null

User email address provided when creating the datapoint.

provider_latencydouble or null

Latency of provider response.

tokensinteger or null

Total number of tokens in the prompt and output.

raw_outputstring or null

Raw output from the provider.

finish_reasonstring or null

Reason the generation finished.

toolslist of objects or null

tool_choice"none" or "auto" or "required" or object or null

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 strings or null

List of batch IDs the log belongs to.

1	import requests
2
3	url = "https://api.humanloop.com/v4/logs"
4
5	querystring = {"reference_id":"reference_id"}
6
7	payload = {}
8	headers = {
9	"X-API-KEY": "<apiKey>",
10	"Content-Type": "application/json"
11	}
12
13	response = requests.patch(url, json=payload, headers=headers, params=querystring)
14
15	print(response.json())

1	{
2	"id": "id",
3	"config": {
4	"type": "model",
5	"id": "id",
6	"model": "model",
7	"chat_template": [
8	{
9	"role": "user"
10	}
11	],
12	"description": "description",
13	"endpoint": "complete",
14	"frequency_penalty": 1.1,
15	"max_tokens": 1,
16	"name": "name",
17	"other": {
18	"key": "value"
19	},
20	"presence_penalty": 1.1,
21	"prompt_template": "prompt_template",
22	"provider": "anthropic",
23	"reasoning_effort": "high",
24	"response_format": {
25	"type": "json_object",
26	"json_schema": {
27	"key": "value"
28	}
29	},
30	"seed": 1,
31	"stop": "stop",
32	"temperature": 1.1,
33	"template_language": "default",
34	"tools": [
35	{
36	"id": "id",
37	"name": "name"
38	}
39	],
40	"top_p": 1.1,
41	"tool_configs": [
42	{
43	"id": "id",
44	"status": "status",
45	"name": "name"
46	}
47	]
48	},
49	"evaluation_results": [
50	{
51	"id": "id",
52	"evaluator_id": "evaluator_id",
53	"evaluator_version_id": "evaluator_version_id",
54	"log_id": "log_id",
55	"updated_at": "2024-01-15T09:30:00Z",
56	"created_at": "2024-01-15T09:30:00Z",
57	"evaluation_id": "evaluation_id",
58	"version_id": "version_id",
59	"version": {
60	"key": "value"
61	},
62	"value": true,
63	"error": "error"
64	}
65	],
66	"observability_status": "pending",
67	"updated_at": "2024-01-15T09:30:00Z",
68	"project": "project",
69	"project_id": "project_id",
70	"session_id": "session_id",
71	"session_reference_id": "session_reference_id",
72	"parent_id": "parent_id",
73	"parent_reference_id": "parent_reference_id",
74	"inputs": {
75	"key": "value"
76	},
77	"source": "source",
78	"metadata": {
79	"key": "value"
80	},
81	"save": true,
82	"source_datapoint_id": "source_datapoint_id",
83	"reference_id": "reference_id",
84	"messages": [
85	{
86	"role": "user",
87	"content": "content",
88	"name": "name",
89	"tool_call_id": "tool_call_id",
90	"tool_calls": [
91	{
92	"id": "id",
93	"type": "function",
94	"function": {
95	"name": "name"
96	}
97	}
98	],
99	"thinking": [
100	{
101	"type": "thinking",
102	"signature": "signature",
103	"thinking": "thinking"
104	}
105	],
106	"tool_call": {
107	"name": "name"
108	}
109	}
110	],
111	"output": "output",
112	"judgment": true,
113	"config_id": "config_id",
114	"environment": "environment",
115	"feedback": [
116	{
117	"type": "rating",
118	"id": "id",
119	"value": true,
120	"data_id": "data_id",
121	"user": "user",
122	"created_at": "2024-01-15T09:30:00Z"
123	}
124	],
125	"created_at": "2024-01-15T09:30:00Z",
126	"error": "error",
127	"stdout": "stdout",
128	"duration": 1.1,
129	"output_message": {
130	"role": "user",
131	"content": "content",
132	"name": "name",
133	"tool_call_id": "tool_call_id",
134	"tool_calls": [
135	{
136	"id": "id",
137	"type": "function",
138	"function": {
139	"name": "name"
140	}
141	}
142	],
143	"thinking": [
144	{
145	"type": "thinking",
146	"signature": "signature",
147	"thinking": "thinking"
148	}
149	],
150	"tool_call": {
151	"name": "name",
152	"arguments": "arguments"
153	}
154	},
155	"prompt_tokens": 1,
156	"output_tokens": 1,
157	"prompt_cost": 1.1,
158	"output_cost": 1.1,
159	"provider_request": {
160	"key": "value"
161	},
162	"provider_response": {
163	"key": "value"
164	},
165	"user": "user",
166	"provider_latency": 1.1,
167	"tokens": 1,
168	"raw_output": "raw_output",
169	"finish_reason": "finish_reason",
170	"tools": [
171	{
172	"id": "id",
173	"name": "name",
174	"signature": "signature",
175	"result": "result"
176	}
177	],
178	"tool_choice": "none",
179	"batch_ids": [
180	"batch_ids"
181	]
182	}

Headers

Query parameters

Request

Response

Errors