Humanloop Documentation and API Reference

Deploy Prompt to an Environment.

Set the deployed version for the specified Environment. This Prompt will be used for calls made to the Prompt in this Environment.

Path parameters

idstringRequired

Unique identifier for Prompt.

environment_idstringRequired

Unique identifier for the Environment to deploy the Version to.

Query parameters

version_idstringRequired

Unique identifier for the specific version of the Prompt.

Response

Successful Response

pathstring

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

idstring

Unique identifier for the Prompt.

modelstring

The model instance used, e.g. gpt-4. See supported models

namestring

Name of the Prompt.

version_idstring

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

created_atdatetime

updated_atdatetime

statusenum

Allowed values: uncommittedcommitteddeleted

The status of the Prompt Version.

last_used_atdatetime

version_logs_countinteger

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

total_logs_countinteger

The number of logs that have been generated across all Prompt Versions

inputslist of objects

Inputs associated to the Prompt. Inputs correspond to any of the variables used within the Prompt template.

directory_idstringOptional

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

endpointenumOptional

Allowed values: completechatedit

The provider model endpoint used.

templatestring or list of objectsOptional

The template contains the main structure and instructions for the model, including input variables for dynamic values.

For chat models, provide the template as a ChatTemplate (a list of messages), e.g. a system message, followed by a user message with an input variable. For completion models, provide a prompt template as a string.

Input variables should be specified with double curly bracket syntax: {{input_name}}.

providerenumOptional

The company providing the underlying model service.

max_tokensintegerOptionalDefaults to -1

The maximum number of tokens to generate. Provide max_tokens=-1 to dynamically calculate the maximum number of tokens to generate given the length of the prompt

temperaturedoubleOptionalDefaults to 1

What sampling temperature to use when making a generation. Higher values means the model will be more creative.

top_pdoubleOptionalDefaults to 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

stopstring or list of stringsOptional

The string (or list of strings) after which the model will stop generating. The returned text will not contain the stop sequence.

presence_penaltydoubleOptionalDefaults to 0

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the generation so far.

frequency_penaltydoubleOptionalDefaults to 0

Number between -2.0 and 2.0. Positive values penalize new tokens based on how frequently they appear in the generation so far.

othermap from strings to anyOptional

Other parameter values to be passed to the provider call.

seedintegerOptional

If specified, model will make a best effort to sample deterministically, but it is not guaranteed.

response_formatobjectOptional

The format of the response. Only {"type": "json_object"} is currently supported for chat.

toolslist of objectsOptional

The tool specification that the model can choose to call if Tool calling is supported.

linked_toolslist of objectsOptional

The tools linked to your prompt that the model can call.

attributesmap from strings to anyOptional

Additional fields to describe the Prompt. Helpful to separate Prompt versions from each other with details on how they were created or used.

commit_messagestringOptional

Message describing the changes made.

type"prompt"OptionalDefaults to prompt

environmentslist of objectsOptional

The list of environments the Prompt Version is deployed to.

created_byanyOptional

The user who created the Prompt.

committed_byanyOptional

The user who committed the Prompt Version.

committed_atdatetimeOptional

The date and time the Prompt Version was committed.

evaluatorslist of objectsOptional

Evaluators that have been attached to this Prompt that are used for monitoring logs.

evaluator_aggregateslist of objectsOptional

Aggregation of Evaluator results for the Prompt Version.

1	{
2	"path": "path",
3	"id": "id",
4	"model": "model",
5	"name": "name",
6	"version_id": "version_id",
7	"created_at": "2024-01-15T09:30:00Z",
8	"updated_at": "2024-01-15T09:30:00Z",
9	"status": "uncommitted",
10	"last_used_at": "2024-01-15T09:30:00Z",
11	"version_logs_count": 1,
12	"total_logs_count": 1,
13	"inputs": [
14	{
15	"name": "name"
16	}
17	],
18	"directory_id": "directory_id",
19	"endpoint": "complete",
20	"template": "template",
21	"provider": "openai",
22	"max_tokens": 1,
23	"temperature": 1.1,
24	"top_p": 1.1,
25	"stop": "stop",
26	"presence_penalty": 1.1,
27	"frequency_penalty": 1.1,
28	"other": {
29	"key": "value"
30	},
31	"seed": 1,
32	"response_format": {
33	"type": "json_object",
34	"json_schema": {
35	"key": "value"
36	}
37	},
38	"tools": [
39	{
40	"name": "name",
41	"description": "description",
42	"strict": true,
43	"parameters": {
44	"key": "value"
45	}
46	}
47	],
48	"linked_tools": [
49	{
50	"name": "name",
51	"description": "description",
52	"id": "id",
53	"version_id": "version_id",
54	"strict": true,
55	"parameters": {
56	"key": "value"
57	}
58	}
59	],
60	"attributes": {
61	"key": "value"
62	},
63	"commit_message": "commit_message",
64	"type": "prompt",
65	"environments": [
66	{
67	"id": "id",
68	"created_at": "2024-01-15T09:30:00Z",
69	"name": "name",
70	"tag": "default"
71	}
72	],
73	"created_by": {
74	"id": "id",
75	"email_address": "email_address",
76	"full_name": "full_name"
77	},
78	"committed_by": {
79	"id": "id",
80	"email_address": "email_address",
81	"full_name": "full_name"
82	},
83	"committed_at": "2024-01-15T09:30:00Z",
84	"evaluator_aggregates": [
85	{
86	"value": 1.1,
87	"evaluator_id": "evaluator_id",
88	"evaluator_version_id": "evaluator_version_id",
89	"created_at": "2024-01-15T09:30:00Z",
90	"updated_at": "2024-01-15T09:30:00Z"
91	}
92	]
93	}

1	curl -X POST "https://api.humanloop.com/v5/prompts/id/environments/environment_id?version_id=version_id" \
2	-H "X-API-KEY: <apiKey>"

Path parameters

Query parameters

Response

Errors