> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# Pesquisar mensagens da conversa por texto

GET https://api.elevenlabs.io/v1/convai/conversations/messages/text-search

Pesquise mensagens de transcrições de conversas por texto completo e pesquisa aproximada

Reference: https://elevenlabs.io/docs/eleven-agents/api-reference/conversations/messages/text-search

## Servers

- `https://api.elevenlabs.io` (Production, default)
- `https://api.us.elevenlabs.io` (Production US)
- `https://api.eu.residency.elevenlabs.io` (Production EU)
- `https://api.in.residency.elevenlabs.io` (Production India)
- `https://api.sg.residency.elevenlabs.io` (Production Singapore)

## Request

### Query parameters

- `text_query` (string, required) — O texto da consulta de pesquisa para correspondência de texto completo e aproximada
- `agent_id` (string, optional) — ID do agente (agent_…) ou ID externo do mecanismo de fala (seng_), resolvidos para o mesmo recurso subjacente.
- `visited_agent_ids` (string, optional) — Filtre conversas das quais qualquer um desses agentes participou. Não pode exceder 50 valores.
- `visited_agent_branch_ids` (string, optional) — Filtre conversas das quais qualquer uma dessas ramificações de agente participou. Não pode exceder 50 valores.
- `triggered_procedure_ids` (string, optional) — Filtre conversas nas quais qualquer um desses procedimentos foi acionado. Não pode exceder 50 valores.
- `call_successful` (enum, optional) — O resultado da avaliação de sucesso
  - Allowed values: `success`, `failure`, `unknown`, `error`
- `call_start_before_unix` (integer, optional) — Timestamp Unix (em segundos) para filtrar conversas até esta data inicial.
- `call_start_after_unix` (integer, optional) — Timestamp Unix (em segundos) para filtrar conversas posteriores a esta data inicial.
- `call_duration_min_secs` (integer, optional) — Duração mínima da chamada em segundos.
- `call_duration_max_secs` (integer, optional) — Duração máxima da chamada em segundos.
- `rating_max` (integer, optional) — Avaliação geral máxima (1 a 5).
- `rating_min` (integer, optional) — Avaliação geral mínima (1 a 5).
- `has_feedback_comment` (boolean, optional) — Filtre conversas com comentários de feedback dos usuários.
- `user_id` (string, optional) — Filtre conversas pelo ID do usuário que as iniciou.
- `evaluation_params` (string, optional) — Filtros de avaliação. Repita o parâmetro. Formato: criteria_id:result, em que result é success|failure|unknown. Exemplo: eval=value_framing:success
- `data_collection_params` (string, optional) — Filtros de coleta de dados. Parâmetro repetível. Formato: id:op:value, em que op é um de eq|neq|gt|gte|lt|lte|in. Para in, separe os valores por barra vertical. Um valor vazio corresponde a conversas em que o campo não foi coletado (id:eq:), e neq com um valor vazio corresponde àquelas em que foi (id:neq:). eq representa igualdade exata. gt|gte|lt|lte exigem um valor numérico.
- `dynamic_variable_params` (string, optional) — Filtros de variáveis dinâmicas. Parâmetro repetível. Formato: name:op:value, em que op é um de eq|neq|gt|gte|lt|lte|in. Para in, separe os valores com barra vertical. Um valor vazio corresponde a conversas em que a variável não foi definida (name:eq:), e neq com um valor vazio corresponde àquelas em que ela foi definida (name:neq:). eq representa igualdade exata. gt|gte|lt|lte exigem um valor numérico. Nomes que contêm ':' não podem ser expressos.
- `tool_names` (string, optional) — Filtre conversas pelos nomes das ferramentas usadas durante a chamada.
- `tool_names_successful` (string, optional) — Filtre conversas pelos nomes das ferramentas que tiveram chamadas bem-sucedidas.
- `tool_names_errored` (string, optional) — Filtre conversas pelos nomes das ferramentas que tiveram chamadas com erro.
- `include_invalid_tool_calls` (boolean, optional, default: false) — Também corresponda a chamadas de ferramentas que nunca foram executadas.
- `main_languages` (string, optional) — Filtre conversas pelo idioma principal detectado (código do idioma).
- `exclude_statuses` (enum, optional) — Exclua conversas com os status especificados. Útil para ocultar conversas em andamento ou em processamento nas visualizações de lista.
  - Allowed values: `initiated`, `in-progress`, `processing`, `done`, `failed`
- `termination_reasons` (string, optional) — Filtre conversas pelo termination_reason armazenado (metadata.termination_reason). Repita o parâmetro para corresponder a qualquer um entre vários valores.
- `page_size` (integer, optional, default: 20) — Número de resultados por página. Máximo de 50.
- `summary_mode` (enum, optional, default: exclude) — Indica se deve incluir resumos das transcrições na resposta.
  - Allowed values: `exclude`, `include`
- `conversation_initiation_source` (enum, optional, default: unknown) — Enumeração que representa as possíveis origens para o início de uma conversa.
  - Allowed values: `unknown`, `android_sdk`, `node_js_sdk`, `react_native_sdk`, `react_sdk`, `js_sdk`, `python_sdk`, `widget`, `sip_trunk`, `twilio`, `exotel`, `genesys`, `avaya`, `audiocodes`, `swift_sdk`, `whatsapp`, `twilio_sms`, `flutter_sdk`, `zendesk_integration`, `slack_integration`, `telegram_integration`, `intercom_integration`, `freshdesk_integration`, `salesforce_integration`, `template_preview`, `genesys_bot_connector`, `subagent_tool`
- `text_only` (boolean, optional)
- `conversation_product_type` (enum, optional) — Restrinja os resultados a uma única interface de produto de conversas.
  - Allowed values: `agents`, `speech_engine`
- `branch_id` (string, optional) — Filtre conversas por ID da ramificação.
- `version_id` (string, optional) — Filtre conversas por ID da versão.
- `topic_ids` (string, optional) — Filtre conversas pelos IDs de tópicos atribuídos durante a descoberta de tópicos.
- `sort_by` (enum, optional) — Ordem de classificação dos resultados de pesquisa. 'search_score' ordena pela pontuação da pesquisa, e 'created_at' ordena pelo horário de início da conversa.
  - Allowed values: `search_score`, `created_at`
- `cursor` (string, optional) — Usado para buscar a próxima página. O cursor é retornado na resposta.

## Response

### 200

Resposta bem-sucedida

- `results` (list of MessagesSearchResult, required)
- `has_more` (boolean, required) — Indica se há mais resultados disponíveis
- `meta` (ListResponseMeta, optional)
- `next_cursor` (string, optional) — Cursor para a próxima página de resultados

## Errors

### 422 Messages Text Search Request Unprocessable Entity Error

Erro de validação

- `detail` (list of ValidationError, optional)

## Types

### MessagesSearchResult

transcript_index: índice da mensagem na transcrição da conversa chunk_text: texto da transcrição; mensagens da transcrição muito longas podem ter vários trechos. chunk_highlights: chunk_text dividido em segmentos correspondentes/não correspondentes para destaque. Preenchido apenas para pesquisa por palavra-chave/texto, não para pesquisa semântica. score: pontuação de similaridade da mensagem com a consulta de pesquisa

- `conversation_id` (string, required)
- `agent_id` (string, required)
- `transcript_index` (integer, required)
- `chunk_text` (string, required)
- `score` (double, required)
- `conversation_start_time_unix_secs` (integer, required)
- `agent_name` (string, optional)
- `chunk_highlights` (list of SearchHighlightSegment, optional)

### ListResponseMeta

- `total` (integer, optional)
- `page` (integer, optional)
- `page_size` (integer, optional)

### ValidationError

- `loc` (list of ValidationErrorLocItem, required)
- `msg` (string, required)
- `type` (string, required)

### SearchHighlightSegment

- `value` (string, required)
- `is_hit` (boolean, required)

### ValidationErrorLocItem

## Examples

**Response**

```json
{
  "results": [
    {
      "conversation_id": "conversation_id",
      "agent_id": "agent_id",
      "transcript_index": 1,
      "chunk_text": "chunk_text",
      "score": 1.1,
      "conversation_start_time_unix_secs": 1,
      "agent_name": "agent_name",
      "chunk_highlights": [
        {
          "value": "value",
          "is_hit": true
        }
      ]
    }
  ],
  "has_more": true,
  "meta": {
    "total": 1,
    "page": 1,
    "page_size": 1
  },
  "next_cursor": "next_cursor"
}
```

**SDK Code**

```python
import requests

url = "https://api.elevenlabs.io/v1/convai/conversations/messages/text-search"

querystring = {"agent_id":"agent_id","branch_id":"branch_id","call_duration_max_secs":"1","call_duration_min_secs":"1","call_start_after_unix":"1","call_start_before_unix":"1","call_successful":"success","conversation_initiation_source":"unknown","conversation_product_type":"agents","cursor":"cursor","data_collection_params":"[\"data_collection_params\"]","dynamic_variable_params":"[\"dynamic_variable_params\"]","evaluation_params":"[\"evaluation_params\"]","exclude_statuses":"[\"initiated\"]","has_feedback_comment":"true","include_invalid_tool_calls":"true","main_languages":"[\"main_languages\"]","page_size":"1","rating_max":"1","rating_min":"1","sort_by":"search_score","summary_mode":"exclude","termination_reasons":"[\"termination_reasons\"]","text_only":"true","text_query":"refund policy","tool_names":"[\"tool_names\"]","tool_names_errored":"[\"tool_names_errored\"]","tool_names_successful":"[\"tool_names_successful\"]","topic_ids":"[\"topic_ids\"]","triggered_procedure_ids":"[\"triggered_procedure_ids\"]","user_id":"user_id","version_id":"version_id","visited_agent_branch_ids":"[\"visited_agent_branch_ids\"]","visited_agent_ids":"[\"visited_agent_ids\"]"}

response = requests.get(url, params=querystring)

print(response.json())
```

```javascript
const url = 'https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D';
const options = {method: 'GET'};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D');

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let request = NSMutableURLRequest(url: NSURL(string: "https://api.elevenlabs.io/v1/convai/conversations/messages/text-search?agent_id=agent_id&branch_id=branch_id&call_duration_max_secs=1&call_duration_min_secs=1&call_start_after_unix=1&call_start_before_unix=1&call_successful=success&conversation_initiation_source=unknown&conversation_product_type=agents&cursor=cursor&data_collection_params=%5B%22data_collection_params%22%5D&dynamic_variable_params=%5B%22dynamic_variable_params%22%5D&evaluation_params=%5B%22evaluation_params%22%5D&exclude_statuses=%5B%22initiated%22%5D&has_feedback_comment=true&include_invalid_tool_calls=true&main_languages=%5B%22main_languages%22%5D&page_size=1&rating_max=1&rating_min=1&sort_by=search_score&summary_mode=exclude&termination_reasons=%5B%22termination_reasons%22%5D&text_only=true&text_query=refund+policy&tool_names=%5B%22tool_names%22%5D&tool_names_errored=%5B%22tool_names_errored%22%5D&tool_names_successful=%5B%22tool_names_successful%22%5D&topic_ids=%5B%22topic_ids%22%5D&triggered_procedure_ids=%5B%22triggered_procedure_ids%22%5D&user_id=user_id&version_id=version_id&visited_agent_branch_ids=%5B%22visited_agent_branch_ids%22%5D&visited_agent_ids=%5B%22visited_agent_ids%22%5D")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```