Files
mintlify__docs/api/analytics/assistant-conversations.mdx
mintlify[bot] 47447c8617 Update from code changes: document responseType in assistant analytics export (#6970)
* docs: document responseType and per-row semantics in assistant analytics export

* docs: mirror assistant analytics export updates in Chinese translation

---------

Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
2026-08-13 11:29:43 -07:00

35 lines
2.0 KiB
Plaintext

---
title: "Get assistant conversations"
openapi: /analytics.openapi.json GET /v1/analytics/{projectId}/assistant
keywords: ["analytics", "assistant", "conversations", "export", "AI"]
---
## Usage
Use this endpoint to export AI assistant conversation history from your documentation. Each conversation includes the user query, assistant response, sources cited, resolution status, and query category.
Paginate through results using the `cursor` parameter returned in the response. Continue fetching while `hasMore` is `true`.
## Filtering
Filter conversations by date range using `dateFrom` and `dateTo` parameters.
## Conversation data
Each row represents one user turn in a conversation. A conversation with multiple back-and-forth messages produces multiple rows that share a `conversationId`.
Each row includes:
- **query**: The user's question.
- **response**: The assistant's answer. For clarifying-question turns, this is the follow-up question the assistant asked the user.
- **responseType**: Either `answer` or `clarifying_question`. `clarifying_question` means the assistant asked the user a follow-up question instead of answering. Defaults to `answer` when not present.
- **sources**: Pages referenced in the response, with title and URL.
- **resolutionStatus**: Whether the assistant successfully answered this turn. Either `answered` or `unanswered`. Computed per row, so a single conversation can contain both statuses. Use this field to track and analyze documentation gaps surfaced by user questions the assistant could not resolve.
- **timestamp**: When the user sent the message that started this turn. Rows in the same conversation have different timestamps.
- **queryCategory**: Classification of the query type, if available.
- **pageUrl**: Full URL of the documentation page where the conversation started, or `null` if no page path is available. Use this field to attribute conversations to a specific page.
## Rate limits
This endpoint allows 100 requests per organization per hour. All analytics endpoints share this limit.