GET
/
v2
/
threads
curl --request GET \
  --url https://api.langtail.com/v2/threads \
  --header 'X-API-Key: <x-api-key>'
{
  "object": "list",
  "data": [
    {
      "id": "<string>",
      "createdAt": 123,
      "projectId": "<string>",
      "createLog": {
        "id": "<string>",
        "url": "<string>",
        "stream": true,
        "metadata": "<string>",
        "promptId": "<string>",
        "threadId": "<string>",
        "assistant": true,
        "projectId": "<string>",
        "requestIP": "<string>",
        "startedAt": "2023-11-07T05:31:56Z",
        "variables": "<string>",
        "parameters": "<string>",
        "promptSlug": "<string>",
        "doNotRecord": true,
        "environment": "<string>",
        "openAIKeyId": "<string>",
        "projectSlug": "<string>",
        "requestData": "<string>",
        "deploymentId": "<string>",
        "organizationId": "<string>",
        "projectAPIKeyId": "<string>",
        "organizationSlug": "<string>",
        "deploymentVersion": "<string>",
        "promptHistoryHash": "<string>",
        "openAIOrganization": "<string>"
      },
      "metadata": {
        "user_id": "user_123",
        "conversation_topic": "product_inquiry",
        "priority": "high"
      }
    }
  ],
  "first_id": "<string>",
  "last_id": "<string>",
  "has_more": true
}

Before using the Threads API, make sure you have set up the REST API integration.

Threads are a fundamental component of the Langtail API, designed to manage and maintain the state of conversations with AI assistants. Here’s how the Threads API works:

  1. Creation: A thread can be created either as a new conversation or by referencing an existing thread ID.

  2. Message Storage: Threads store all messages exchanged during a conversation, including both user inputs and assistant responses.

  3. Conversation Continuity: By using thread IDs, you can maintain context across multiple interactions, allowing for coherent, ongoing dialogues.

​
Pagination

This endpoint supports pagination in the same way as the OpenAI API. Specifically, it follows the pagination mechanism described in the OpenAI API documentation for listing Assistants.

Here’s how it works:

  1. The limit parameter allows you to specify the maximum number of threads to return in a single request. The default and maximum value is 100.

  2. The after parameter is used as a cursor for pagination. It should be set to any thread ID from which you want to retrieve the next set of results.

  3. To fetch the next page of results, make a new request with the after parameter set to the ID of the last thread in the current response.

  4. The response includes a has_more parameter, which indicates whether there are more results available.

This pagination approach allows you to efficiently retrieve and process large numbers of threads in manageable chunks.

Headers

​
X-API-Key
string
required

Your Langtail API Key

Example:

"<LANGTAIL_API_KEY>"

Query Parameters

​
limit
number | null

The maximum number of threads to return. Default is 100.

​
after
string | null

A cursor for use in pagination. 'after' is a thread ID that defines your place in the list. For instance, if you make a list request and receive 100 threads, ending with thread 'xyz', your subsequent call can include after='xyz' in order to fetch the next page of the list. Pagination works the same as in the OpenAI API https://platform.openai.com/docs/api-reference/assistants/listAssistants.

Response

200
application/json

Successful response

The response is of type object.