Text search

GET

/v1/convai/conversations/messages/text-search

GET

/v1/convai/conversations/messages/text-search

$ curl -G https://api.elevenlabs.io/v1/convai/conversations/messages/text-search \
>      -d agent_id=agent_id \
>      -d branch_id=branch_id \
>      -d call_duration_max_secs=1 \
>      -d call_duration_min_secs=1 \
>      -d call_start_after_unix=1 \
>      -d call_start_before_unix=1 \
>      -d call_successful=success \
>      -d conversation_initiation_source=unknown \
>      -d conversation_product_type=agents \
>      -d cursor=cursor \
>      -d data_collection_params=data_collection_params \
>      -d dynamic_variable_params=dynamic_variable_params \
>      -d evaluation_params=evaluation_params \
>      -d exclude_statuses=initiated \
>      -d has_feedback_comment=true \
>      -d include_invalid_tool_calls=true \
>      -d main_languages=main_languages \
>      -d page_size=1 \
>      -d rating_max=1 \
>      -d rating_min=1 \
>      -d sort_by=search_score \
>      -d summary_mode=exclude \
>      -d termination_reasons=termination_reasons \
>      -d text_only=true \
>      --data-urlencode "text_query=refund policy" \
>      -d tool_names=tool_names \
>      -d tool_names_errored=tool_names_errored \
>      -d tool_names_successful=tool_names_successful \
>      -d topic_ids=topic_ids \
>      -d triggered_procedure_ids=triggered_procedure_ids \
>      -d user_id=user_id \
>      -d version_id=version_id \
>      -d visited_agent_branch_ids=visited_agent_branch_ids \
>      -d visited_agent_ids=visited_agent_ids

1 {
2   "results": [
3     {
4       "conversation_id": "conversation_id",
5       "agent_id": "agent_id",
6       "transcript_index": 1,
7       "chunk_text": "chunk_text",
8       "score": 1.1,
9       "conversation_start_time_unix_secs": 1,
10       "agent_name": "agent_name",
11       "chunk_highlights": [
12         {
13           "value": "value",
14           "is_hit": true
15         }
16       ]
17     }
18   ],
19   "has_more": true,
20   "meta": {
21     "total": 1,
22     "page": 1,
23     "page_size": 1
24   },
25   "next_cursor": "next_cursor"
26 }

Search through conversation transcript messages by full-text and fuzzy search

Query parameters

text_querystringRequired

The search query text for full-text and fuzzy matching

agent_idstringOptional

Agent id (agent_…) or speech engine external id (seng_), resolved to the same underlying resource.

visited_agent_idsstringOptional

Filter conversations where any of these agents participated. Can not exceed 50 values.

visited_agent_branch_idsstringOptional

Filter conversations where any of these agent branches participated. Can not exceed 50 values.

triggered_procedure_idsstringOptional

Filter conversations where any of these procedures were triggered. Can not exceed 50 values.

call_successfulenumOptional

The result of the success evaluation

Allowed values:

call_start_before_unixintegerOptional

Unix timestamp (in seconds) to filter conversations up to this start date.

call_start_after_unixintegerOptional

Unix timestamp (in seconds) to filter conversations after to this start date.

call_duration_min_secsintegerOptional

Minimum call duration in seconds.

call_duration_max_secsintegerOptional

Maximum call duration in seconds.

rating_maxintegerOptional1-5

Maximum overall rating (1-5).

rating_minintegerOptional1-5

Minimum overall rating (1-5).

has_feedback_commentbooleanOptional

Filter conversations with user feedback comments.

user_idstringOptional

Filter conversations by the user ID who initiated them.

evaluation_paramsstringOptional

Evaluation filters. Repeat param. Format: criteria_id:result. Example: eval=value_framing:success

data_collection_paramsstringOptional

Data collection filters. Repeat param. Format: id:op:value where op is one of eq|neq|gt|gte|lt|lte|in|exists|missing. For in, pipe-delimit values.

dynamic_variable_paramsstringOptional

Dynamic variable filters. Repeat param. Format: name:op:value where op is one of eq|gt|gte|lt|lte. Comparison operators require a numeric value. Names containing ’:’ cannot be expressed.

tool_namesstringOptional

Filter conversations by tool names used during the call.

tool_names_successfulstringOptional

Filter conversations by tool names that had successful calls.

tool_names_erroredstringOptional

Filter conversations by tool names that had errored calls.

include_invalid_tool_callsbooleanOptionalDefaults to false

Also match tool calls that never ran.

main_languagesstringOptional

Filter conversations by detected main language (language code).

exclude_statusesenumOptional

Exclude conversations with the given statuses. Useful for hiding in-progress / processing conversations from list views.

Allowed values:

termination_reasonsstringOptional

Filter conversations by their stored termination_reason (metadata.termination_reason). Repeat param to match any of several.

page_sizeintegerOptional1-50Defaults to 20

Number of results per page. Max 50.

summary_modeenumOptionalDefaults to exclude

Whether to include transcript summaries in the response.

Allowed values:

conversation_initiation_sourceenumOptionalDefaults to unknown

Enum representing the possible sources for conversation initiation.

text_onlybooleanOptional

conversation_product_typeenumOptional

Restrict results to a single conversation product surface.

Allowed values:

branch_idstringOptional

Filter conversations by branch ID.

version_idstringOptional

Filter conversations by version ID.

topic_idsstringOptional

Filter conversations by topic IDs assigned during topic discovery.

sort_byenumOptional

Sort order for search results. ‘search_score’ sorts by search score, ‘created_at’ sorts by conversation start time.

Allowed values:

cursorstringOptional

Used for fetching next page. Cursor is returned in the response.

Response

Successful Response

resultslist of objects

has_moreboolean

Whether there are more results available

metaobjectOptional

next_cursorstringOptional

Cursor for the next page of results

Errors

422

Messages Text Search Request Unprocessable Entity Error

Headers

Query parameters

Response

Errors