Skip to content

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

docs: translate VLM providers section in README to English (#487)

曹謀仁77fcc73b3aae
diff --git a/README.md b/README.md
index 6df20a46c..a7426f9d2 100644
--- a/README.md
+++ b/README.md
@@ -97,13 +97,13 @@ OpenViking supports three VLM providers:
| Provider | Description | Get API Key |
|----------|-------------|-------------|
-| `volcengine` | 火山引擎豆包模型 | [Volcengine Console](https://console.volcengine.com/ark) |
-| `openai` | OpenAI 官方 API | [OpenAI Platform](https://platform.openai.com) |
-| `litellm` | 统一调用多种第三方模型 (Anthropic, DeepSeek, Gemini, vLLM, Ollama, etc.) | See [LiteLLM Providers](https://docs.litellm.ai/docs/providers) |
+| `volcengine` | Volcengine Doubao Models | [Volcengine Console](https://console.volcengine.com/ark) |
+| `openai` | OpenAI Official API | [OpenAI Platform](https://platform.openai.com) |
+| `litellm` | Unified access to various third-party models (Anthropic, DeepSeek, Gemini, vLLM, Ollama, etc.) | See [LiteLLM Providers](https://docs.litellm.ai/docs/providers) |
-> 💡 **Tip**:
-> - `litellm` 支持通过统一接口调用多种模型,model 字段需遵循 [LiteLLM 格式规范](https://docs.litellm.ai/docs/providers)
-> - 系统自动检测常见模型(如 `claude-*`, `deepseek-*`, `gemini-*`, `hosted_vllm/*`, `ollama/*` 等),其他模型需按 LiteLLM 格式填写完整前缀
+> 💡 **Tip**:
+> - `litellm` supports unified access to various models. The `model` field must follow the [LiteLLM format specification](https://docs.litellm.ai/docs/providers)
+> - The system auto-detects common models (e.g., `claude-*`, `deepseek-*`, `gemini-*`, `hosted_vllm/*`, `ollama/*`, etc.). For other models, use the full prefix according to LiteLLM format
#### Provider-Specific Notes
diff --git a/README_CN.md b/README_CN.md
index c6923e9b7..c036a3009 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -41,7 +41,7 @@
**OpenViking** 是专为 AI 智能体设计的开源**上下文数据库**。
-我们的目标是为智能体定义一个极简的上下文交互范式,让开发者完全告别上下文管理的烦恼。OpenViking 抛弃了传统 RAG 的碎片化向量存储模型,创新性地采用**"文件系统范式"**来统一组织智能体所需的记忆、资源和技能。
+我们的目标是为智能体定义一个极简的上下文交互范式,让开发者完全告别上下文管理的烦恼。OpenViking 抛弃了传统 RAG 的碎片化向量存储模型,创新性地采用 **"文件系统范式"** 来统一组织智能体所需的记忆、资源和技能。
使用 OpenViking,开发者可以像管理本地文件一样构建智能体的大脑: