HTTP Integration

The HTTP integration allows you to send events to the LLMonitor API endpoint. This is useful if you want to integrate LLMonitor with a custom language where our SDKs are not available.

The endpoint accepts POST requests with a JSON body containing an array of Event objects.

Endpoint

https://app.llmonitor.com/api/v1/report

Authentication

There is no authentication required to send events to the API endpoint. However, you will need to provide valid app IDs in the Event object or the request will be rejected.

Example

Here is an example with cURL to send a POST request to the API endpoint:

curl -X POST 'https://app.llmonitor.com/api/v1/report' \
 -H 'Content-Type: application/json' \
 -d '{
  "events": [
    {
      "type": "llm",
      "app": "YOUR APP ID",
      "event": "start",
      "runId": "some-unique-id",
      "name": "gpt-3.5-turbo",
      "timestamp": "2022-01-01T00:00:00Z",
      "input": [{"role": "user", "text": "Hello world!"}],
      "tags": ["tag1"]
    }
  ]
}'

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.

Input / output format

You can use any valid JSON for the input & output fields.

However, for LLM calls you can use the chat message format:

Example:

[{
  "role": "system",
  "text": "You are an assistant"
}, {
  "role": "user",
  "text": "Hello world!"
}, {
  "role": "ai",
  "text": "Hello. How are you?"
}]

Event definition

The Event object has the following properties:

Property	Type	Required	Description
type	string	Yes	The type of the event. Can be one of "llm", "agent", "tool", "chain", "chat", "convo".
app	string	Yes	The app ID of the application.
event	string	No	The name of the event. Can be one of "start", "end, "error", "feedback",
runId	string	Yes	The ID of the run (UUID recommended)
parentRunId	string	No	The ID of the parent run, if any.
timestamp	string	Yes	Timestamp in ISO 8601 format.
input	any	No	Input data (with start events)
tags	string[]	No	Array of tags.
name	string	No	The name of the current model, agent, tool, etc.
output	any	No	Output data (with end events)
extra	any	No	Extra data associated with the run.
feedback	any	No	Feedback data associated with the run (only when type = 'feedback')
tokensUsage	object	No	An object containing the number of prompt and completion tokens used (only for llm run)
error	object	No	An object containing the error message and stack trace if an error occurred.

The tokensUsage object has the following properties:

Property	Type	Required	Description
prompt	number	No	The number of prompt tokens used.
completion	number	No	The number of completion tokens used.

If tokensUsage is not provided, the number of tokens used will be calculated from the input and output fields. This works with models from OpenAI, Anthropic and Google at the moment.

The error object has the following properties:

Property	Type	Required	Description
message	string	Yes	The error message.
stack	string	No	The stack trace of the error.

For the feedback field, refer to the Feedback page for more information.