> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# 角色

> 发现公开的 Venice 角色，并通过与 OpenAI 兼容的聊天补全 API，将其人格应用到文本模型中。

角色是一些公开的人格设定，你可以将其应用到聊天补全中。每个角色都有一个 `slug` 以及关联的文本模型。

<Warning>
  Characters API 处于预览阶段，可能会发生变更。
</Warning>

## 发现角色

使用 [列出角色端点](/api-reference/endpoint/characters/list) 来搜索并过滤公开的角色目录：

```bash cURL theme={"system"}
curl "https://api.venice.ai/api/v1/characters?search=philosophy&limit=5" \
  -H "Authorization: Bearer $VENICE_API_KEY"
```

响应中包含用于聊天补全所需的字段：

```json theme={"system"}
{
  "data": [
    {
      "name": "Alan Watts",
      "slug": "alan-watts",
      "modelId": "venice-uncensored-1-2",
      "description": "A philosophical entertainer...",
      "webEnabled": true
    }
  ],
  "object": "list"
}
```

你也可以通过 [获取角色端点](/api-reference/endpoint/characters/get) 按 slug 检索单个角色：

```bash cURL theme={"system"}
curl "https://api.venice.ai/api/v1/characters/alan-watts" \
  -H "Authorization: Bearer $VENICE_API_KEY"
```

将返回的 `slug` 作为 `venice_parameters.character_slug` 使用。将其 `modelId` 作为聊天补全的模型，或者从 [文本模型页面](/models/text) 中选择一个兼容的模型。

## 与角色对话

在调用与 OpenAI 兼容的 Chat Completions API 时，将 `character_slug` 传入 `venice_parameters`：

<CodeGroup>
  ```python Python theme={"system"}
  import os
  import requests
  from openai import OpenAI

  headers = {"Authorization": f"Bearer {os.environ['VENICE_API_KEY']}"}
  character = requests.get(
      "https://api.venice.ai/api/v1/characters/alan-watts",
      headers=headers,
      timeout=30,
  ).json()["data"]

  client = OpenAI(
      api_key=os.environ["VENICE_API_KEY"],
      base_url="https://api.venice.ai/api/v1",
  )

  response = client.chat.completions.create(
      model=character["modelId"],
      messages=[
          {"role": "user", "content": "How can I worry less about the future?"}
      ],
      extra_body={
          "venice_parameters": {
              "character_slug": character["slug"],
          }
      },
  )

  print(response.choices[0].message.content)
  ```

  ```javascript Node.js theme={"system"}
  import OpenAI from "openai";

  const characterResponse = await fetch(
    "https://api.venice.ai/api/v1/characters/alan-watts",
    {
      headers: {
        Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
      },
    },
  );
  const { data: character } = await characterResponse.json();

  const client = new OpenAI({
    apiKey: process.env.VENICE_API_KEY,
    baseURL: "https://api.venice.ai/api/v1",
  });

  const response = await client.chat.completions.create({
    model: character.modelId,
    messages: [
      { role: "user", content: "How can I worry less about the future?" },
    ],
    venice_parameters: {
      character_slug: character.slug,
    },
  });

  console.log(response.choices[0].message.content);
  ```

  ```bash cURL theme={"system"}
  curl "https://api.venice.ai/api/v1/chat/completions" \
    -H "Authorization: Bearer $VENICE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "venice-uncensored",
      "messages": [
        {
          "role": "user",
          "content": "How can I worry less about the future?"
        }
      ],
      "venice_parameters": {
        "character_slug": "alan-watts"
      }
    }'
  ```
</CodeGroup>

<Note>
  角色 slug 仅适用于公开的 Venice 角色。缺失或无效的 slug 会导致 API 返回错误。
</Note>

## 相关资源

* [文本模型](/models/text)
* [列出角色 API](/api-reference/endpoint/characters/list)
* [获取角色 API](/api-reference/endpoint/characters/get)
* [角色评价 API](/api-reference/endpoint/characters/reviews)
* [Chat Completions API](/api-reference/endpoint/chat/completions)