Get Prompt

GET

https://host.com/apis/models/v2/workspaces/:workspace/prompts/:name

GET

/apis/models/v2/workspaces/:workspace/prompts/:name

$ curl https://host.com/apis/models/v2/workspaces/workspace/prompts/name \
>      -H "Content-Type: application/json"

1 {
2   "name": "llama-3.1-8b",
3   "workspace": "research_team_alpha",
4   "created_at": "2024-01-15T09:30:00Z",
5   "updated_at": "2024-04-10T14:45:00Z",
6   "id": "a3f47c2e-9b1d-4f3a-8c2e-1d2b3f4a5c6d",
7   "project": "urn:project:ai-models/llama",
8   "description": "Prompt for llama 3.1 8b model to generate conversational responses.",
9   "messages": [
10     {
11       "role": "system",
12       "content": "You are a helpful assistant specialized in AI research."
13     }
14   ],
15   "input_variables": [
16     "user_input"
17   ],
18   "tools": [
19     {
20       "type": "function",
21       "function": {
22         "name": "get_current_weather",
23         "description": "Fetches the current weather for a given location.",
24         "parameters": {
25           "type": "object",
26           "properties": {
27             "location": {
28               "type": "string",
29               "description": "The city and state, e.g. San Francisco, CA"
30             },
31             "unit": {
32               "type": "string",
33               "enum": [
34                 "celsius",
35                 "fahrenheit"
36               ]
37             }
38           },
39           "required": [
40             "location"
41           ]
42         },
43         "strict": true
44       }
45     }
46   ],
47   "tool_choice": "auto",
48   "response_format": {
49     "type": "json_schema",
50     "schema": {
51       "type": "object",
52       "properties": {
53         "response": {
54           "type": "string"
55         }
56       },
57       "required": [
58         "response"
59       ]
60     }
61   },
62   "inference_params": {
63     "model": "llama-3.1-8b",
64     "temperature": 0.7,
65     "max_tokens": 256,
66     "max_completion_tokens": 256,
67     "top_p": 0.9,
68     "stop": [
69       "\n"
70     ]
71   },
72   "tags": [
73     "llama",
74     "chat",
75     "research"
76   ]
77 }

Get a prompt by workspace and name.

Path parameters

workspacestringRequired

namestringRequired

Response

Return prompt details

namestringformat: "^[\w\-.]+$"<=255 characters

Name of the entity. Name/workspace combo must be unique across all entities. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

workspacestringformat: "^[\w\-.]+$"<=255 characters

The workspace of the entity. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

created_atdatetime

The timestamp of model entity creation

updated_atdatetime

The timestamp of the last model entity update

idstring

Unique identifier for the prompt.

projectstringformat: "^[\w\-./]+$"<=255 characters

The URN of the project associated with this entity.

descriptionstring<=1000 characters

Optional description of the prompt.

messageslist of objects

Ordered list of chat messages that make up the prompt.

input_variableslist of strings

Names of the Jinja2 template variables the prompt expects.

toolslist of objects

Optional OpenAI-compatible tool definitions to send with the prompt.

tool_choicestring or map from strings to any

Controls which (if any) tool is called: ‘none’, ‘auto’, ‘required’, or a named-tool object.

response_formatmap from strings to any

Optional OpenAI-compatible response_format, e.g. a json_schema structured-output spec.

inference_paramsobject

Optional default model and sampling parameters (temperature, top_p, max_tokens, …).

tagslist of strings

Optional free-form tags for organizing prompts.

Errors

422

Unprocessable Entity Error