Follow this guide to learn how to create a dataset, add data sources to the dataset, create a session associated with the dataset, and then run jobs to start anayzing the uploaded data.

​
Step 1. Get your project API key

If you’re the admin of your team, get API key of the target project on the admin console.

If you’re a system user or virtual user in a team, simply ask your admin to provide you with one.

​
Step 2. Create a dataset and upload a data source to it

This step is optional but highly recommended, as it allows you to receive insights tailored to your own data.

Data sources are the data you upload to Powerdrill for embedding, indexing, knowledge extraction, and vectorized storage and retrieval, while datasets are collections of data sources that help organize and categorize them.

You can create datasets and data sources in two ways:

  • Method 1: Create a dataset first, then add data sources to it.

  • Method 2: Create a data source directly without specifying a dataset, and Powerdrill will automatically create a dataset for it.

  1. Make a request to POST /v2/team/datasets endpoint to create a dataset.

    Replace $PD_API_KEY with the API key you’ve obtained in Step 1 and $UID with your user ID in the target project.

    Example request:

    curl --request POST \
  --url https://ai.data.cloud/api/v2/team/datasets \
  --header 'Content-Type: application/json' \
  --header 'x-pd-api-key: $PD_API_KEY' \
  --data '{
  "name": "My dataset",
  "description": "my default dataset",
  "user_id": "$UID"
}'

    Example response:

    {
    "code": 0,
    "data": {
        "id": "dset-cmc1nh2e2lqf507retfodc0dn"
    }
}

    Obtain the id value (dataset ID) from the response and save it for later use.

  2. Make a request to the POST /v2/team/datasets/{id}/datasources endpoint. Replace the id value with the ID of the dataset you’ve created in the previous sub-step.

    Replace $PD_API_KEY with the API key you’ve obtained in Step 1 and $UID with your user ID in the target project.

    When making the request, specify either url or file_key, but not both. Use url to upload a file through a publicly accessible URL. For privately accessible files, use file_key.

    Example request:

    curl --request POST \
  --url https://ai.data.cloud/api/v2/team/datasets/dset-cmc1nh2e2lqf507retfodc0dn/datasources \
  --header 'Content-Type: application/json' \
  --header 'x-pd-api-key: $PD_API_KEY' \
  --data '{
  "name": "test.pdf",
  "type": "FILE",
  "user_id": "$UID",
  "url": "https://arxiv.org/pdf/2406.12660v1"
}'

    Example response:

    {
    "code": 0,
    "data": {
        "id": "ds-cmc1ntbw105ug07j49zei4kcb",
        "name": "test.pdf",
        "type": "FILE",
        "status": "synching",
        "dataset_id":"dset-cmc1nh2e2lqf507retfodc0dn"
    }
}

    Repeat this sub-step to create multiple data sources in the same dataset, if needed.

​
Step 3. Create a session

To create a session, make a request to the POST /v2/team/sessions endpoint. Sessions are essential for running jobs on Powerdrill, as each job must be linked to a session using its session ID.

Replace $PD_API_KEY with the API key you’ve obtained in Step 1 and $UID with your user ID in the target project.

Example request:

curl --request POST \
  --url https://ai.data.cloud/api/v2/team/sessions \
  --header 'Content-Type: application/json' \
  --header 'x-pd-api-key: $PD_API_KEY' \
  --data '{
  "name": "My session",
  "output_language": "EN",
  "job_mode": "AUTO",
  "max_contextual_job_history": 10,
  "user_id": "$UID"
}'

Example response:

{
    "code": 0,
    "data": {
        "id": "bc9a8127-4214-42b2-bbbe-a022f23d9795"
    }
}

Obtain the id value (session ID) from the response and save it for use in the following step.

​
Step 4. Create a job

Now, after you’ve prepared a session and probably a dataset stuffed with data sources, you can create a job to start conversing with Powerdrill.

For the definition of job, see What Is Job?.

Make a request to the POST /v2/team/jobs endpoint.

Powerdrill provides the ability to stream responses, controlled by the stream parameter. For more details about how to understand the streaming mode, see Streaming.

  • If stream is set to true, streaming is enabled.

  • If stream is set to false, streaming is disabled.

When making the request:

  • Replace $PD_API_KEY with the API key you’ve obtained in Step 1 and $UID with your user ID in the target project.

  • Replace the session_id value with the ID of the session you’ve created in Step 3.

  • To enable Powerdrill to retrieve information from your own data and provide responses specific to it, set the dataset_id to the ID of the dataset obtained in Step 2.

  • If you want to use specific data sources in the specified dataset, list the data source IDs in the datasource_ids field.

Example request:

curl --request POST \
  --url https://ai.data.cloud/api/v2/team/jobs \
  --header 'Content-Type: application/json' \
  --header 'x-pd-api-key: $PD_API_KEY' \
  --data '{
  "session_id": "bc9a8127-4214-42b2-bbbe-a022f23d9795",
  "user_id": "$UID",
  "stream": true,
  "question": "introducing the dataset",
  "dataset_id": "dset-cmc1nh2e2lqf507retfodc0dn",
  "datasource_ids": [
    "ds-cmc1ntbw105ug07j49zei4kcb"
  ],
  "output_language": "EN",
  "job_mode": "AUTO"
}'

​
Need more help?

Post to our help community

Get answers from our members

Contact us

Tell us more and we’ll help you out