Get Interactions

curl --request POST \
  --url https://backend.nebuly.com/api/external/get-interactions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "time_range": {
    "start": "<string>",
    "end": "<string>"
  },
  "filters": [
    {
      "kind": "<string>",
      "tag": "<string>",
      "values": [
        "<string>"
      ]
    }
  ],
  "limit": 123,
  "offset": 123
}
'

{
  "total": 123,
  "offset": 123,
  "limit": 123,
  "data": [
    {
      "id": "<string>",
      "input_text": "<string>",
      "output_text": "<string>",
      "user_query": "<string>",
      "end_user": "<string>",
      "conversation_id": "<string>",
      "timestamp": "<string>",
      "end_timestamp": "<string>",
      "warning_message_v2": "<string>",
      "negative_intent_message_v2": "<string>",
      "cost": 123,
      "latency": 123,
      "text_language": "<string>",
      "verbosity": 123,
      "pii_removed": true,
      "feedback_action_text": "<string>",
      "feedback_action_rating": 123,
      "feedback_actions": [
        "<string>"
      ],
      "sentiment": "<string>",
      "emotions": [
        "<string>"
      ],
      "tags": {},
      "custom_columns": {},
      "custom_aggregates": {},
      "rag_details": {}
    }
  ]
}

POST

https://backend.nebuly.com

api

external

get-interactions

Get Interactions

curl --request POST \
  --url https://backend.nebuly.com/api/external/get-interactions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "time_range": {
    "start": "<string>",
    "end": "<string>"
  },
  "filters": [
    {
      "kind": "<string>",
      "tag": "<string>",
      "values": [
        "<string>"
      ]
    }
  ],
  "limit": 123,
  "offset": 123
}
'

{
  "total": 123,
  "offset": 123,
  "limit": 123,
  "data": [
    {
      "id": "<string>",
      "input_text": "<string>",
      "output_text": "<string>",
      "user_query": "<string>",
      "end_user": "<string>",
      "conversation_id": "<string>",
      "timestamp": "<string>",
      "end_timestamp": "<string>",
      "warning_message_v2": "<string>",
      "negative_intent_message_v2": "<string>",
      "cost": 123,
      "latency": 123,
      "text_language": "<string>",
      "verbosity": 123,
      "pii_removed": true,
      "feedback_action_text": "<string>",
      "feedback_action_rating": 123,
      "feedback_actions": [
        "<string>"
      ],
      "sentiment": "<string>",
      "emotions": [
        "<string>"
      ],
      "tags": {},
      "custom_columns": {},
      "custom_aggregates": {},
      "rag_details": {}
    }
  ]
}

You need an API key to authenticate. See here for more information about the API keys.

time_range

object

required

The time range to consider when computing the metrics and analytics to show.

Show properties

start

string

default:"2024-05-30T09:27:52.420Z"

required

The start date for the time-range.

end

string

default:"2024-05-30T09:27:52.420Z"

required

The end date for the time-range.

filters

object[]

required

Filters you can use to get data based only on the interactions you are interested in.

Show properties

kind

string

required

The filter kind. It can be one of the following values:

user_intent
negative_user_intent
keyword
user_feedback
tag
type_of_problem
topic
user
user_query

tag

string

Optional field to be used only when the kind is tag. It should specify the tag name, which is the same as the key you used in the tags dictionary during the interaction submission.

values

string[]

required

The values of the selected filter you want to filter on. Note that all the values passed in the list are considered to be in “or” the one with the other. This means that if the kind is “topic” and the passed values are “value A”, “value B”, this is equal to topic="value A" or topic="value B".

limit

integer

required

Parameter needed for pagination. It indicates the number of rows per page.

offset

integer

required

Parameter needed for pagination. It indicates the offset to be applied to the first rows returned.

Response

total

integer

Needed for pagination. The total number of rows available.

offset

integer

Needed for pagination. It indicates the offset to be applied to the first rows returned.

limit

integer

Needed for pagination. It indicates the number of rows per page.

data

object[]

The data per interaction.

Show properties

string

The interaction id. It uniquely identifies the interaction and can be used to retrieve further information.

input_text

string

The input text written by the user.

output_text

string

The response generated by the assistant.

user_query

string

A detailed version of the user intent in a single sentence.

end_user

string

The end user interacting with the LLM.

conversation_id

string

The conversation id. It uniquely identifies the conversation the interaction belongs to. This information can be sent via API in order to group interactions, otherwise it will be generated automatically by Nebuly.

timestamp

string

The date when the user input was received by the LLM.

end_timestamp

string

The date when the assistant response was sent back to the user.

warning_message_v2

string

Description of any warnings or issues detected with the LLM response.

negative_intent_message_v2

string

If present, it indicates that the user is having a negative experience withing the conversation.

cost

float

Cost of the interaction, in microdollars.

latency

float

Time elapsed between the user input and the assistant response, in seconds.

text_language

string

Language detected in the user input.

verbosity

integer

Number of characters in the output.

pii_removed

boolean

Indicates whether PII was removed from the interaction.

feedback_action_text

string

Text content accompanying feedback actions, if any.

feedback_action_rating

number

Numerical rating provided as feedback (e.g., 1–5).

feedback_actions

string[]

Actions taken or suggested via user feedback (e.g., “thumbs_up”, “thumbs_down”).

sentiment

string

Sentiment classification of the interaction, if available (e.g., positive, neutral, negative).

emotions

string[]

List of detected emotions from the user input.

Examples

​Response

Response