Datasets

Set up Respan

Sign up — Create an account at platform.respan.ai
Create an API key — Generate one on the API keys page
Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page

Use AI

Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.

{
  "mcpServers": {
    "respan-docs": {
      "url": "https://docs.respan.ai/mcp"
    }
  }
}

A dataset is a curated collection of logs (inputs/outputs + metadata) that you can evaluate, annotate, and use to power experiments.

Create from existing logs

Sample production logs into a dataset by applying filters, time ranges, and sampling percentages.

Via UI
Via API

Go to Datasets and click Create

Navigate to Datasets and click Create dataset. Choose From logs (sampling).

Set filters, time range, and sampling percentage

Configure filters (e.g. status_code = 200, specific model, metadata), time range, and sampling percentage.

Create and verify

Click Create. Once ingestion finishes, open the dataset and confirm logs appear.

Create with specific log IDs:

import requests

API_KEY = "YOUR_API_KEY"
url = "https://api.respan.ai/api/datasets/"

payload = {
  "name": "Dataset from existing logs",
  "type": "sampling",
  "sampling": 100,
  "start_time": "2025-07-30T00:00:00Z",
  "end_time": "2025-08-01T00:00:00Z",
  "initial_log_filters": {
    "id": {"operator": "in", "value": ["log_id_1", "log_id_2"]}
  }
}

res = requests.post(url, headers={"Authorization": f"Bearer {API_KEY}"}, json=payload)
print(res.json())

Or bulk add by filters:

import requests

API_KEY = "YOUR_API_KEY"
dataset_id = "YOUR_DATASET_ID"

url = f"https://api.respan.ai/api/datasets/{dataset_id}/logs/bulk/"
payload = {
  "start_time": "2025-07-01T00:00:00Z",
  "end_time": "2025-07-31T23:59:59Z",
  "filters": {"status_code": {"operator": "eq", "value": 200}},
  "sampling_percentage": 40
}

res = requests.post(url, headers={"Authorization": f"Bearer {API_KEY}"}, json=payload)
print(res.json())

See the Datasets API reference for all endpoints.

Create manually

Create an empty dataset and add logs by hand — via JSON, CSV, or API.

Via UI
Via API

Create an empty dataset

Navigate to Datasets, click Create dataset, and choose Create empty.

Add logs

Click Insert new log and provide JSON with input and output, or click Import from CSV to upload a batch.

CSV template (Google Drive)

Create an empty dataset

import requests

API_KEY = "YOUR_API_KEY"

url = "https://api.respan.ai/api/datasets/"
payload = {
  "name": "Demo Dataset (via API)",
  "description": "Created from docs tutorial",
  "is_empty": True
}

res = requests.post(url, headers={"Authorization": f"Bearer {API_KEY}"}, json=payload)
dataset = res.json()
print("dataset_id:", dataset["id"])

Add a dataset log

import requests

API_KEY = "YOUR_API_KEY"
dataset_id = "YOUR_DATASET_ID"

url = f"https://api.respan.ai/api/datasets/{dataset_id}/logs/"
payload = {
  "input": {
    "question": "What is 2+2?",
    "context": {"source": "docs_tutorial"}
  },
  "output": {
    "answer": "4",
    "explanation": "2 + 2 = 4."
  },
  "metadata": {
    "custom_identifier": "dataset-tutorial-log",
    "model": "gpt-4o-mini"
  }
}

res = requests.post(url, headers={"Authorization": f"Bearer {API_KEY}"}, json=payload)
print(res.json())

Run an eval on the dataset

import requests

API_KEY = "YOUR_API_KEY"
dataset_id = "YOUR_DATASET_ID"

url = f"https://api.respan.ai/api/datasets/{dataset_id}/eval-reports/create"
payload = {"evaluator_slugs": ["char_count_eval"]}

res = requests.post(url, headers={"Authorization": f"Bearer {API_KEY}"}, json=payload)
print(res.json())

See the Datasets API reference for all endpoints.

Get started

Features

Admin

Security

Resources

Help & Community

Create from existing logs

Create manually

Get started

Features

Admin

Security

Resources

Help & Community

​Create from existing logs

​Create manually

Create from existing logs

Create manually