Clarify Base URL settings in READMEs

This commit is contained in:
Nakano Kenji
2025-12-10 01:50:16 +08:00
parent a7caa4344f
commit b768b77c74
2 changed files with 12 additions and 6 deletions
+6 -3
View File
@@ -38,9 +38,12 @@ Everything starts with the **API Config** node.
* *Claude*: `sk-ant-...`
* *Gemini*: Your Google AI Studio key.
4. **Base URL (Optional)**:
* Leave empty for official APIs.
* Enter a custom URL if you use a proxy, a local LLM (like LM Studio/Ollama), or a third-party service.
* *Example*: `https://api.deepseek.com/v1` or `http://localhost:1234/v1`.
* **Strongly recommended to leave empty** unless you are using a proxy or local model.
* The plugin has built-in default official API addresses:
* OpenAI: `https://api.openai.com/v1`
* Claude: `https://api.anthropic.com/v1`
* Gemini: `https://generativelanguage.googleapis.com/v1beta`
* If you use a proxy service (like DeepSeek, OneAPI, etc.), you usually need to fill in the full path including `/v1`, e.g., `https://api.deepseek.com/v1`.
5. **Select Model**:
* **Click the "Refresh Models" button**.
* The node will connect to the API and fetch the *real-time list* of models you can use.
+6 -3
View File
@@ -38,9 +38,12 @@ git clone https://github.com/Moeblack/ComfyUI-SimpleChat.git
* *Claude*: `sk-ant-...`
* *Gemini*: 您的 Google AI Studio key。
4. **Base URL (可选)**:
* 使用官方 API 时请留空。
* 如果您使用代理、中转或本地 LLM,请在此输入 URL。
* *例如*: `https://api.deepseek.com/v1` 或 `http://localhost:1234/v1`。
* **强烈建议留空**,除非您使用代理或本地模型。
* 插件内置了默认的官方 API 地址:
* OpenAI: `https://api.openai.com/v1`
* Claude: `https://api.anthropic.com/v1`
* Gemini: `https://generativelanguage.googleapis.com/v1beta`
* 如果您使用中转服务(如 DeepSeek, OneAPI 等),通常需要填写包含 `/v1` 的完整路径,例如 `https://api.deepseek.com/v1`。
5. **选择模型 (Select Model)**:
* **点击 "Refresh Models" 按钮**。
* 节点会连接 API 并获取您当前可用的**实时模型列表**。