For LLM calls, you would first track a start event with the input data. Once your LLM call succeeds, you would need to send an end event to the API endpoint with the output data from the LLM call.

For a full step-by-step guide on sending LLM data to the Lunary API, see the Custom Integration guide.

POST

/v1/runs/ingest

curl --request POST \
  --url https://api.lunary.ai/v1/runs/ingest \
  --header 'Authorization: Bearer <api_key>' \
  --header 'Content-Type: application/json' \
  --data '{"events":[{"type":"llm","event":"start","runId":"some-unique-id","name":"gpt-4","timestamp":"2022-01-01T00:00:00Z","input":[{"role":"user","content":"Hello world!"}],"tags":["tag1"],"extra":{"temperature":0.5,"max_tokens":100}}]}'

Accepted Keys:

events

Example response:

{
  "results": [
    {
      "id": "some-unique-id",
      "success": true
    }
  ]
}

Request Body

Property	Type	Description
events	Object

Responses

200

Successful ingestion

Property	Type	Description
results	array

401

Project does not exist

402

Incorrect project id format

Questions? We're here to help.

Email

Ingest run events

Request Body

Responses

200

401

402

Questions? We're here to help.

On this page