API ReferenceConversationsTurn data

List Retrieval Log

Beta
Per-conversation retrieval log, newest first — one row per `search_knowledge` invocation made during the call. Each entry records the query, ranked chunks (denormalised so deletions don't render history unreadable), `limit`, and hit count. Powers the Retrieval panel on the conversation detail view. Cursor-paginated: omit `cursor` to fetch the first page. Default page size is 50 and max is 200. Walk pages while `has_more` is true.

Authentication

AuthorizationBearer

Enter your API key with the Bearer prefix, e.g. ‘Bearer sk_…’.

Path parameters

conversation_idstringRequired

Conversation id (prefixed external id, conv_...).

Headers

Speechify-VersionstringOptional

Query parameters

cursorstringOptional
Opaque pagination cursor from a previous response.
limitintegerOptional1-200Defaults to 50

Max items per page (default 50, max 200).

Response headers

X-Request-IDstring
Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends an `X-Request-ID` request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests - it is the stable handle that ties your observation to Speechify's server-side logs, and it matches the `request_id` field in the error envelope.

Response

The retrieval log entries for the conversation.
next_cursorstring or null

Opaque keyset cursor for the next page. Pass back as the cursor request parameter. null when the caller has reached the end of the list (has_more is also false in that case).

has_moreboolean
True when more rows exist beyond this page.
entrieslist of objects

Errors

400
Bad Request Error
401
Unauthorized Error
404
Not Found Error