Get a Chatbot trace details - Fluid Topics - Latest

Fluid Topics API Reference Guide
Category
Reference Guides
Audience
public
Version
Latest

This web service allows users with the ADMIN or BEHAVIOR_DATA_USER role to get more information about a Chatbot trace.

It is necessary to provide an Ft-Calling-App value when using Fluid Topics web services. See Fluid Topics calling app.

Method Endpoint
GET 
/api/admin/ai/rag/chat/conversations/{conversationId}
Path parameter Type Description
{conversationId} String The conversation's ID. Call the Search chatbot traces web service, and use the conversationId value.

Response body

{
    "timestamp": "2025-11-27T10:48:29.315000+00:00",
    "sessionId": "d1baa50e-bcf8-4593-85da-88063ee15d23",
    "userId": "xxx-xxx-xxx-xxx-xxx",
    "profileId": "chatbot",
    "conversationId": "xxx-xxx-xxx-xxx-xxx",
    "llmModel": "openai:///gpt-4.1",
    "history": [
        {
            "role": "USER",
            "timestamp": "2025-11-27T10:48:29.315000+00:00",
            "content": "i got the md-0001 error what can i do"
        },
        {
            "role": "ASSISTANT",
            "timestamp": "2025-11-27T10:48:34.741000+00:00",
            "content": "The MD-0001 error is not listed in the available documentation. Please provide the full error message or additional context so I can assist you further. If possible, check your publishing report for more details about the error.",
            "chatbotInstructions": "Your name is Fluidy. You are a Fluid Topics Chatbot. You are in charge of helping users with their questions about Fluid Topics. You are polite, kind, and informative. You must refuse to answer questions unrelated to Fluid Topics.\n\nWhenever possible, break down your answers into numbered steps.",
            "semsearch": {
                "query": "i got the md-0001 error what can i do",
                "results": [
                    {
                        "excerpt": "| `MD-0021`      | `\"{toc_path}\" is not valid: {error}`                                                                                                                                                     | Review the [table of contents](75a0b2cf8843a8af91ed219abeb872285cc884d9f893ea5bfa71275dae280421-toc_org) of the document, and [publish again](2702891eed14d7ad9a8445e1ce06b7b2803182375898e48404bce079ddbefadf-publish). |\n| `MD-0022`      | `Invalid metadata in \"toc.yml\": {error}`                                                                                                                                                 | Review the [table of contents](75a0b2cf8843a8af91ed219abeb872285cc884d9f893ea5bfa71275dae280421-toc_org) of the document, and [publish again](2702891eed14d7ad9a8445e1ce06b7b2803182375898e48404bce079ddbefadf-publish). |\n| `MD-0023`      | `In \"{toc_path}\": \"{filepath}\" is not a markdown file.`                                                                                                                                  | Remove `{filepath}` from `{toc_path}`, and [publish again](2702891eed14d7ad9a8445e1ce06b7b2803182375898e48404bce079ddbefadf-publish).                                                                                    |",
                        "relevance": -0.050511837,
                        "metadata": {}
                    }
                ]
            }
        }
    ]
}
Field Type Description
timestamp String The UTC date and time for the first message of the user to the Chatbot, in ISO-8601 format (YYYY-MM-DD HH:MM:SS with microseconds).
sessionId String The session ID. A user can have multiple traces in the same session.
userId String The user's ID.
profileId String An AI profile ID.
conversationId String The conversation ID.
llmModel String The Large Language Model (LLM) used by the Chatbot, and configured in the AI profile.
history Array The messages between the user and the Chatbot, from the oldest to the most recent.
role String Can be USER for the user, or ASSISTANT for the Chatbot.
timestamp String The UTC date and time for the message, in ISO-8601 format (YYYY-MM-DD HH:MM:SS with microseconds).
content String Either the user's message, or the Chatbot's answer.
chatbotInstructions String The system prompt for the Chatbot.
semsearch Object The Chatbot bases its answers on the content of the portal. To that end, the Chatbot uses semantic search. An object containing information about the semantic search performed by the Chatbot.
query String The query used by the Chatbot for the semantic search. The Chatbot can rephrase the user's message to improve the semantic search's efficacy.
results Array The semantic search results for the user's query.
excerpt String A part of a topic that appears in the semantic search results.
relevance Number A relevance score from -1 to 1. -1 is the lowest possible score, while 1 is the highest possible score.
metadata Object The metadata for the topic containing the excerpt.