POST
/
dataset-from-filter-params
curl --request POST \
  --url https://api.promptlayer.com/dataset-from-filter-params \
  --header 'Content-Type: application/json' \
  --header 'X-API-KEY: <x-api-key>' \
  --data '{
  "name": "<string>",
  "workspace_id": 123,
  "q": "<string>",
  "start_time": "<string>",
  "end_time": "<string>",
  "tags": [
    "<string>"
  ],
  "metadata": [
    {
      "key": "<string>",
      "value": "<string>"
    }
  ],
  "scores": [
    {
      "name": "<string>",
      "operator": "<string>",
      "value": 123
    }
  ],
  "starred": true,
  "prompt_template": {
    "name": "<string>",
    "version_numbers": [
      123
    ]
  },
  "limit": 123
}'
{
  "success": true,
  "message": "<string>",
  "dataset_id": 123
}

This endpoint allows you to create a dataset based on a historical search query. Search filters can include tags, metadata, and other criteria such as time range and scores. This dataset is then stored in a given workspace.

Example Code

import requests

response = requests.post(
    "https://api.promptlayer.com/dataset-from-filter-params",
    headers=headers,
    json={
        "name": "Dataset Name",
        "workspace_id": 1,
        "q": "javascript",
        "start_time": "2023-11-17 20:14:31.874642",
        "end_time": "2024-11-18 20:14:31.874642",
        "tags": ["prod", "dev"],
        "metadata": [
            {"key": "user_id", "value": "abc123"},
            {"key": "success", "value": "true"}
        ],
        "scores": [
            {"name": "default", "operator": ">", "value": 90}
        ],
        "starred": True,
        "prompt_template": {
            "name": "recipe_template",
            "version_numbers": [50, 51]
        },
        "limit": 500,
    }
)

Headers

X-API-KEY
string
required

API key to authorize the operation.

Body

application/json
name
string
required

The name of the dataset to be created.

workspace_id
integer
required

The ID of the workspace under which the dataset will be stored.

q
string

The search query for filtering the data.

start_time
string

The start time for the dataset's time range filter.

end_time
string

The end time for the dataset's time range filter.

tags
string[]

A list of tags to filter by.

metadata
object[]

A list of metadata key-value pairs to filter by.

scores
object[]

Score thresholds and conditions for filtering request logs.

starred
boolean

Only include favorited requests.

prompt_template
object

Filters requests by the specified prompt template, defaulting to its latest version if no versions are specified.

limit
integer

The maximum number of rows that will be included in the dataset.

Response

200 - application/json
success
boolean
required
message
string
required
dataset_id
integer
required

The ID of the created dataset.