Skip to content

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

docs(config): correct documented vlm.max_concurrent default 100 -> 64 (#2376)

Evo851848509d11
diff --git a/README.md b/README.md
index 137cd8480..5f6f381de 100644
--- a/README.md
+++ b/README.md
@@ -332,7 +332,7 @@ If you prefer manual configuration, create `~/.openviking/ov.conf`, remove the c
"api_key" : "<your-api-key>", // Model service API Key (optional for openai-codex)
"provider" : "<provider-type>", // Provider type (volcengine, openai, openai-codex, kimi, glm, etc.)
"model" : "<model-name>", // VLM model name (e.g., doubao-seed-2-0-pro-260215 or gpt-4-vision-preview)
- "max_concurrent": 100 // Max concurrent LLM calls for semantic processing (default: 100)
+ "max_concurrent": 64 // Max concurrent LLM calls for semantic processing (default: 64)
}
}
```
@@ -370,7 +370,7 @@ If you prefer manual configuration, create `~/.openviking/ov.conf`, remove the c
"api_key" : "your-volcengine-api-key",
"provider" : "volcengine",
"model" : "doubao-seed-2-0-pro-260215",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
@@ -404,7 +404,7 @@ If you prefer manual configuration, create `~/.openviking/ov.conf`, remove the c
"api_key" : "your-openai-api-key",
"provider" : "openai",
"model" : "gpt-4-vision-preview",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
@@ -439,7 +439,7 @@ pip install "google-genai>=1.0.0"
"api_key" : "your-openai-api-key",
"provider" : "openai",
"model" : "gpt-4o",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
@@ -471,7 +471,7 @@ Use `openviking-server init` and choose `OpenAI Codex`, then run `openviking-ser
"api_base" : "https://chatgpt.com/backend-api/codex",
"provider" : "openai-codex",
"model" : "gpt-5.3-codex",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
diff --git a/README_CN.md b/README_CN.md
index b16d3334a..ff837d210 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -288,7 +288,7 @@ openviking-server doctor
"provider" : "<provider-type>", // 提供商类型 (volcengine, openai, azure, openai-codex 等)
"api_version": "2025-01-01-preview", // (仅 azure)API 版本,可选,默认 "2025-01-01-preview"
"model" : "<model-name>", // VLM 模型名称或 Azure 部署名
- "max_concurrent": 100 // 语义处理的最大并发 LLM 调用(默认:100)
+ "max_concurrent": 64 // 语义处理的最大并发 LLM 调用(默认:64)
}
}
```
@@ -326,7 +326,7 @@ openviking-server doctor
"api_key" : "your-volcengine-api-key",
"provider" : "volcengine",
"model" : "doubao-seed-2-0-pro-260215",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
@@ -360,7 +360,7 @@ openviking-server doctor
"api_key" : "your-openai-api-key",
"provider" : "openai",
"model" : "gpt-4-vision-preview",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
@@ -396,7 +396,7 @@ openviking-server doctor
"provider" : "azure",
"api_version": "2025-01-01-preview",
"model" : "gpt-4o",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
diff --git a/README_JA.md b/README_JA.md
index 9a1cc974e..86aa1731f 100644
--- a/README_JA.md
+++ b/README_JA.md
@@ -198,7 +198,7 @@ OpenAIの公式APIを使用:
"api_key" : "<your-api-key>", // モデルサービスAPIキー
"provider" : "<provider-type>", // プロバイダータイプ(volcengine、openai、deepseek、anthropicなど)
"model" : "<model-name>", // VLMモデル名(例:doubao-seed-2-0-pro-260215 または gpt-4-vision-preview)
- "max_concurrent": 100 // セマンティック処理の最大同時LLM呼び出し数(デフォルト: 100)
+ "max_concurrent": 64 // セマンティック処理の最大同時LLM呼び出し数(デフォルト: 64)
}
}
```
@@ -236,7 +236,7 @@ OpenAIの公式APIを使用:
"api_key" : "your-volcengine-api-key",
"provider" : "volcengine",
"model" : "doubao-seed-2-0-pro-260215",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
@@ -270,7 +270,7 @@ OpenAIの公式APIを使用:
"api_key" : "your-openai-api-key",
"provider" : "openai",
"model" : "gpt-4-vision-preview",
- "max_concurrent": 100
+ "max_concurrent": 64
}
}
```
diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.md
index bb7a28fb1..4043e1cad 100644
--- a/docs/en/guides/01-configuration.md
+++ b/docs/en/guides/01-configuration.md
@@ -585,7 +585,7 @@ Vision Language Model for semantic extraction (L0/L1 generation).
| `model` | str | Model name |
| `api_base` | str | API endpoint (optional) |
| `thinking` | bool | Enable thinking mode for VolcEngine models (default: `false`) |
-| `max_concurrent` | int | Maximum concurrent semantic LLM calls (default: `100`) |
+| `max_concurrent` | int | Maximum concurrent semantic LLM calls (default: `64`) |
| `max_retries` | int | Maximum retry attempts for transient VLM provider errors (default: `3`; `0` disables retry) |
| `backup` | object | Optional backup VLM configuration (same shape as `vlm`) for automatic failover when the primary fails with retryable errors such as rate limits, `5xx` responses, or connection/timeout failures. Only one level of failover is supported &mdash; the backup itself cannot define a nested `backup` |
| `timeout` | float | Per-request HTTP timeout in seconds passed to the underlying OpenAI/LiteLLM client. Increase for slow endpoints (e.g., DashScope, local inference). Must be `> 0` (default: `60.0`) |
@@ -1421,7 +1421,7 @@ For detailed encryption explanations, see [Data Encryption](../concepts/10-encry
"model": "string",
"api_base": "string",
"thinking": false,
- "max_concurrent": 100,
+ "max_concurrent": 64,
"max_retries": 3,
"extra_headers": {},
"extra_request_body": {},
diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.md
index 19bdadabf..393fe4264 100644
--- a/docs/zh/guides/01-configuration.md
+++ b/docs/zh/guides/01-configuration.md
@@ -556,7 +556,7 @@ openviking-server doctor
| `model` | str | 模型名称 |
| `api_base` | str | API 端点(可选) |
| `thinking` | bool | 启用思考模式(仅对部分火山模型生效,默认:`false`) |
-| `max_concurrent` | int | 语义处理阶段 LLM 最大并发调用数(默认:`100`) |
+| `max_concurrent` | int | 语义处理阶段 LLM 最大并发调用数(默认:`64`) |
| `max_retries` | int | VLM provider 瞬时错误的最大重试次数(默认:`3`;`0` 表示禁用重试) |
| `backup` | object | 可选的备用 VLM 配置(结构与 `vlm` 相同),当主 VLM 遇到限流、`5xx`、超时或连接失败等可重试错误时自动切换。仅支持 1 层备用 &mdash; 备用 VLM 本身不能再嵌套 `backup` |
| `timeout` | float | 单次 VLM API 请求的 HTTP 超时时间(秒),传递给底层 OpenAI/LiteLLM 客户端。慢端点(如 DashScope、本地推理)可调大。必须 `> 0`(默认:`60.0`) |
@@ -1393,7 +1393,7 @@ openviking add-resource ./docs --exclude "*.tmp"
"model": "string",
"api_base": "string",
"thinking": false,
- "max_concurrent": 100,
+ "max_concurrent": 64,
"max_retries": 3,
"extra_headers": {},
"extra_request_body": {},