Conversations

Create items

Add message items to a conversation.

POST

/conversations/{conversation_id}/items

Python

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  base_url="https://dashscope-intl.aliyuncs.com/api/v2/apps/protocols/compatible-mode/v1",
)

items = client.conversations.items.create(
  "conv_xxx",
  items=[
    {
      "type": "message",
      "role": "user",
      "content": [{"type": "input_text", "text": "Alice's major is teacher education"}],
    }
  ],
)
print(items.data)

{
  "data": [
    {
      "content": [
        {
          "text": "Alice's major is teacher education",
          "type": "input_text"
        }
      ],
      "id": "msg_xxx",
      "role": "user",
      "status": "completed",
      "type": "message"
    }
  ],
  "first_id": "msg_xxx",
  "has_more": false,
  "last_id": "msg_xxx"
}

Authorizations

string

header

required

Qwen Cloud API Key. Create one in the console.

Path Parameters

string

required

The conversation ID.

Example:conv_xxx

Body

application/json

object[]

required

Message items to add (up to 20 per request).

Required range:items <= 20

Show child attributes

enum<string>

required

Only message is supported.

Available options:message

enum<string>

required

Message role. system and developer roles have higher priority than user. assistant indicates model-generated messages from previous interactions.

Available options:user,assistant,system,developer

string

required

Message content as a plain text string or a structured content list (such as ResponseInputText object array).

Response

200-application/json

object[]

Created message items.

Show child attributes

string

The message item ID.

Example:msg_xxx

string

Message content. A plain text string or a structured content list (such as ResponseInputText object array).

enum<string>

Message role: user, assistant, system, or developer.

Available options:user,assistant,system,developer

enum<string>

Processing status: in_progress, completed, or incomplete.

Available options:in_progress,completed,incomplete

enum<string>

Always message.

Available options:message

string

ID of the first message item.

boolean

Whether more data is available.

string

ID of the last message item.

Python

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  base_url="https://dashscope-intl.aliyuncs.com/api/v2/apps/protocols/compatible-mode/v1",
)

items = client.conversations.items.create(
  "conv_xxx",
  items=[
    {
      "type": "message",
      "role": "user",
      "content": [{"type": "input_text", "text": "Alice's major is teacher education"}],
    }
  ],
)
print(items.data)

{
  "data": [
    {
      "content": [
        {
          "text": "Alice's major is teacher education",
          "type": "input_text"
        }
      ],
      "id": "msg_xxx",
      "role": "user",
      "status": "completed",
      "type": "message"
    }
  ],
  "first_id": "msg_xxx",
  "has_more": false,
  "last_id": "msg_xxx"
}