Get interaction details V2
Insights API
Get interaction details V2
GET
Get interaction details V2
Retrieve the detailed information about a single interaction using the v2 schema. This version includes expanded metadata such as sentiment, emotions, latency, PII info, and feedback details. You can list interactions using the Get interactions endpoint.
For authentication you need the to use the API key associated to the project you want to retrieve the interactions from.
UUID
required
ID of the interaction you want to retrieve.
Response
string
Unique identifier of the interaction.
string
The project identifier to which the interaction belongs.
string
Sentiment classification of the interaction, if available (e.g., positive, neutral, negative).
string[]
List of detected emotions from the user input.
number
The cost incurred for the interaction
string
Automatically or manually assigned topic of the interaction.
string
The detected intent associated with the interaction.
string
The user input as received by the system.
string
The LLM-generated output corresponding to the input.
number
Time taken to generate the response.
boolean
Flag indicating whether PII (Personally Identifiable Information) was removed from the input.
string
Language detected in the user input.
string
The timestamp when the interaction began (user input was received).
string
The timestamp when the assistant’s response was generated.
string
User identifier associated with the interaction.
string
Number of characters in the output.
string[]
List of action labels inferred or triggered from the interaction
string
Additional context or metadata about the actions taken.
string[]
Actions taken or suggested via user feedback (e.g., “thumbs_up”, “thumbs_down”).
string
Text content accompanying feedback actions, if any.
number
Numerical rating provided as feedback (e.g., 1–5).
string
A normalized or cleaned-up version of the original user query, if processed.
object
Key-value pairs showing custom tags associated with the interaction.
string
Type of feedback provided (e.g., “negative_implicit”, “positive_implicit”).
string
A flag or description for any risky or concerning user behavior detected.
string[]
Identifiers or summaries of RAG sources used, if provided.
object
Detailed metadata about each RAG item (e.g., source, query, result).
string
Description of any warnings or issues detected with the LLM response.
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.
object[]
List of conversation turns surrounding the interaction.