Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
chore: downgrade golang version limit, update vlm version to seed 2.0 (#425)
MaojiaShengc4209da6cc69
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex b742c4d89..aab836b3c 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -14,7 +14,7 @@ Thank you for your interest in OpenViking! We welcome contributions of all kinds### Prerequisites- **Python**: 3.10+-- **Go**: 1.25.1+ (Required for building AGFS components from source)+- **Go**: 1.19.1+ (Required for building AGFS components from source)- **C++ Compiler**: GCC 9+ or Clang 11+ (Required for building core extensions, must support C++17)- **CMake**: 3.12+@@ -77,7 +77,7 @@ Create a configuration file `~/.openviking/ov.conf`:},"vlm": {"api_key": "your-api-key",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3"}}diff --git a/CONTRIBUTING_CN.md b/CONTRIBUTING_CN.mdindex 9c0974f5f..244f79c96 100644--- a/CONTRIBUTING_CN.md+++ b/CONTRIBUTING_CN.md@@ -14,7 +14,7 @@### 前置要求- **Python**: 3.10+-- **Go**: 1.25.1+ (从源码构建 AGFS 组件需要)+- **Go**: 1.19+ (从源码构建 AGFS 组件需要)- **C++ 编译器**: GCC 9+ 或 Clang 11+ (构建核心扩展需要,必须支持 C++17)- **CMake**: 3.12+@@ -77,7 +77,7 @@ uv pip install -e . --force-reinstall},"vlm": {"api_key": "your-api-key",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3"}}diff --git a/README.md b/README.mdindex 0a78d3190..a479fe18c 100644--- a/README.md+++ b/README.md@@ -114,7 +114,7 @@ Volcengine supports both model names and endpoint IDs. Using model names is reco{"vlm": {"provider": "volcengine",- "model": "doubao-seed-1-6-240615",+ "model": "doubao-seed-2-0-pro-260215","api_key": "your-api-key","api_base": "https://ark.cn-beijing.volces.com/api/v3"}@@ -265,7 +265,7 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"api_base" : "<api-endpoint>", // API endpoint address"api_key" : "<your-api-key>", // Model service API Key"provider" : "<provider-type>", // Provider type (volcengine, openai, deepseek, anthropic, etc.)- "model" : "<model-name>", // VLM model name (e.g., doubao-seed-1-8-251228 or gpt-4-vision-preview)+ "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)}}@@ -303,7 +303,7 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"api_base" : "https://ark.cn-beijing.volces.com/api/v3","api_key" : "your-volcengine-api-key","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228",+ "model" : "doubao-seed-2-0-pro-260215","max_concurrent": 100}}diff --git a/README_CN.md b/README_CN.mdindex a602faf92..e51849473 100644--- a/README_CN.md+++ b/README_CN.md@@ -113,7 +113,7 @@ Volcengine 支持模型名称和端点 ID。为简单起见,建议使用模型{"vlm": {"provider": "volcengine",- "model": "doubao-seed-1-6-240615",+ "model": "doubao-seed-2-0-pro-260215","api_key": "your-api-key","api_base": "https://ark.cn-beijing.volces.com/api/v3"}@@ -264,7 +264,7 @@ ollama serve"api_base" : "<api-endpoint>", // API 端点地址"api_key" : "<your-api-key>", // 模型服务 API Key"provider" : "<provider-type>", // 提供商类型 (volcengine, openai, deepseek, anthropic 等)- "model" : "<model-name>", // VLM 模型名称(如 doubao-seed-1-8-251228 或 gpt-4-vision-preview)+ "model" : "<model-name>", // VLM 模型名称(如 doubao-seed-2-0-pro-260215 或 gpt-4-vision-preview)"max_concurrent": 100 // 语义处理的最大并发 LLM 调用(默认:100)}}@@ -302,7 +302,7 @@ ollama serve"api_base" : "https://ark.cn-beijing.volces.com/api/v3","api_key" : "your-volcengine-api-key","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228",+ "model" : "doubao-seed-2-0-pro-260215","max_concurrent": 100}}diff --git a/docs/en/faq/faq.md b/docs/en/faq/faq.mdindex e03bd4af0..32b0fe70a 100644--- a/docs/en/faq/faq.md+++ b/docs/en/faq/faq.md@@ -86,7 +86,7 @@ Create an `~/.openviking/ov.conf` configuration file in your project directory:"vlm": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3"},"rerank": {diff --git a/docs/en/getting-started/03-quickstart-server.md b/docs/en/getting-started/03-quickstart-server.mdindex b6e8ce610..035090f3f 100644--- a/docs/en/getting-started/03-quickstart-server.md+++ b/docs/en/getting-started/03-quickstart-server.md@@ -247,7 +247,7 @@ vim ~/.openviking/ov.conf"api_key" : "<your-api-key>","provider" : "<provider-type>","max_retries": 2,- "model" : "<model-name>" // e.g., doubao-seed-1-8-251228 or gpt-4-vision-preview+ "model" : "<model-name>" // e.g., doubao-seed-2-0-pro-260215 or gpt-4-vision-preview}}diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.mdindex 764d70471..568e39309 100644--- a/docs/en/guides/01-configuration.md+++ b/docs/en/guides/01-configuration.md@@ -19,7 +19,7 @@ Create `~/.openviking/ov.conf` in your project directory:"vlm": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-seed-1-8-251228"+ "model": "doubao-seed-2-0-pro-260215"},"rerank": {"provider": "volcengine",@@ -55,7 +55,7 @@ Create `~/.openviking/ov.conf` in your project directory:"api_base" : "https://ark.cn-beijing.volces.com/api/v3","api_key" : "your-volcengine-api-key","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228"+ "model" : "doubao-seed-2-0-pro-260215"}}```@@ -252,7 +252,7 @@ Vision Language Model for semantic extraction (L0/L1 generation).{"vlm": {"api_key": "your-api-key",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3"}}@@ -272,7 +272,7 @@ Vision Language Model for semantic extraction (L0/L1 generation).| Model | Notes ||-------|-------|-| `doubao-seed-1-8-251228` | Recommended for semantic extraction |+| `doubao-seed-2-0-pro-260215` | Recommended for semantic extraction || `doubao-pro-32k` | For longer context |When resources are added, VLM generates:diff --git a/docs/en/guides/02-volcengine-purchase-guide.md b/docs/en/guides/02-volcengine-purchase-guide.mdindex 04ac4a26a..27539b19c 100644--- a/docs/en/guides/02-volcengine-purchase-guide.md+++ b/docs/en/guides/02-volcengine-purchase-guide.md@@ -8,7 +8,7 @@ OpenViking requires the following model services:| Model Type | Purpose | Recommended Model ||------------|---------|-------------------|-| VLM (Vision Language Model) | Content understanding, semantic generation | `doubao-seed-1-8-251228` |+| VLM (Vision Language Model) | Content understanding, semantic generation | `doubao-seed-2-0-pro-260215` || Embedding | Vectorization, semantic retrieval | `doubao-embedding-vision-250615` |## Prerequisites@@ -66,7 +66,7 @@ Visit: [Model Management Page](https://console.volcengine.com/ark/region:ark+cn-<img src="../../images/activate_vlm_model.gif" width="80%"></div>-After activation, you can use the model ID directly: `doubao-seed-1-8-251228`+After activation, you can use the model ID directly: `doubao-seed-2-0-pro-260215`### 5. Activate Embedding Model@@ -121,7 +121,7 @@ Create an `~/.openviking/ov.conf` file using the following template:|-------|------|----------|-------------|| `provider` | string | Yes | Model service provider, fill in `"volcengine"` for Volcengine || `api_key` | string | Yes | Volcano Ark API Key |-| `model` | string | Yes | Model ID, e.g., `doubao-seed-1-8-251228` |+| `model` | string | Yes | Model ID, e.g., `doubao-seed-2-0-pro-260215` || `api_base` | string | No | API endpoint address, defaults to Beijing region endpoint, see Appendix - Regional Endpoints for details || `temperature` | float | No | Generation temperature, controls output randomness, range 0-1, recommended 0.1 || `max_retries` | int | No | Number of retries when request fails, recommended 3 |@@ -146,7 +146,7 @@ Save the following content as `~/.openviking/ov.conf`:"vlm": {"provider": "volcengine","api_key": "sk-1234567890abcdef1234567890abcdef",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.1,"max_retries": 3@@ -277,7 +277,7 @@ Error: Connection timeout| Model Name | Current Version | Release Date ||------------|-----------------|--------------|-| Doubao-Seed-1.8 | `doubao-seed-1-8-251228` | 2025-12-28 |+| Doubao-Seed-1.8 | `doubao-seed-2-0-pro-260215` | 2025-12-28 || Doubao-Embedding-Vision | `doubao-embedding-vision-250615` | 2025-06-15 |> Note: Model versions may be updated, please refer to the Volcano Ark Console for the latest information.diff --git a/docs/en/guides/03-deployment.md b/docs/en/guides/03-deployment.mdindex 4d1f1cd5c..c49406ed1 100644--- a/docs/en/guides/03-deployment.md+++ b/docs/en/guides/03-deployment.md@@ -111,18 +111,14 @@ After=network.target[Service]Type=simple-# Replace with the user running OpenViking-User=your-username-# Replace with the user group-Group=your-group# Replace with your working directory-WorkingDirectory=/home/your-username/openviking_workspace+WorkingDirectory=/var/lib/openviking# Choose one of the following start methods-ExecStart=/path/to/your/python/bin/openviking-server+ExecStart=/usr/bin/openviking-serverRestart=alwaysRestartSec=5# Path to config file-Environment="OPENVIKING_CONFIG_FILE=/home/your-username/.openviking/ov.conf"+Environment="OPENVIKING_CONFIG_FILE=/etc/openviking/ov.conf"[Install]WantedBy=multi-user.targetdiff --git a/docs/zh/faq/faq.md b/docs/zh/faq/faq.mdindex 1c702ceec..8e72b7705 100644--- a/docs/zh/faq/faq.md+++ b/docs/zh/faq/faq.md@@ -85,7 +85,7 @@ pip install openviking --upgrade --force-reinstall"vlm": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3"},"rerank": {diff --git a/docs/zh/getting-started/03-quickstart-server.md b/docs/zh/getting-started/03-quickstart-server.mdindex 3272c8d81..f06687df5 100644--- a/docs/zh/getting-started/03-quickstart-server.md+++ b/docs/zh/getting-started/03-quickstart-server.md@@ -244,7 +244,7 @@ vim ~/.openviking/ov.conf"api_key" : "<your-api-key>", // Model service API Key"provider" : "<provider-type>", // Provider type (volcengine or openai)"max_retries": 2,- "model" : "<model-name>" // VLM model name (e.g., doubao-seed-1-8-251228 or gpt-4-vision-preview)+ "model" : "<model-name>" // VLM model name (e.g., doubao-seed-2-0-pro-260215 or gpt-4-vision-preview)}}```diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.mdindex 457738cc9..01dc6d41a 100644--- a/docs/zh/guides/01-configuration.md+++ b/docs/zh/guides/01-configuration.md@@ -60,7 +60,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支"api_base" : "https://ark.cn-beijing.volces.com/api/v3","api_key" : "your-volcengine-api-key","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228"+ "model" : "doubao-seed-2-0-pro-260215"}}```@@ -259,7 +259,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支"vlm": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3"}}@@ -279,7 +279,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支| 模型 | 说明 ||------|------|-| `doubao-seed-1-8-251228` | 推荐用于语义提取 |+| `doubao-seed-2-0-pro-260215` | 推荐用于语义提取 || `doubao-pro-32k` | 用于更长上下文 |添加资源时,VLM 生成:diff --git a/docs/zh/guides/02-volcengine-purchase-guide.md b/docs/zh/guides/02-volcengine-purchase-guide.mdindex f8a69264c..b91e89dbb 100644--- a/docs/zh/guides/02-volcengine-purchase-guide.md+++ b/docs/zh/guides/02-volcengine-purchase-guide.md@@ -8,7 +8,7 @@ OpenViking 需要以下模型服务:| 模型类型 | 用途 | 推荐模型 ||---------|------|---------|-| VLM(视觉语言模型) | 内容理解、语义生成 | `doubao-seed-1-8-251228` |+| VLM(视觉语言模型) | 内容理解、语义生成 | `doubao-seed-2-0-pro-260215` || Embedding | 向量化、语义检索 | `doubao-embedding-vision-250615` |## 前置条件@@ -68,7 +68,7 @@ OpenViking 需要以下模型服务:<img src="../../images/activate_vlm_model.gif" width="80%"></div>-开通后可直接使用模型 ID:`doubao-seed-1-8-251228`+开通后可直接使用模型 ID:`doubao-seed-2-0-pro-260215`### 5. 开通 Embedding 模型@@ -123,7 +123,7 @@ OpenViking 需要以下模型服务:|------|------|------|------|| `provider` | string | 是 | 模型服务提供商,火山引擎填 `"volcengine"` || `api_key` | string | 是 | 火山方舟 API Key |-| `model` | string | 是 | 模型 ID,如 `doubao-seed-1-8-251228` |+| `model` | string | 是 | 模型 ID,如 `doubao-seed-2-0-pro-260215` || `api_base` | string | 否 | API 端点地址,默认为北京区域端点,具体可见附录-区域端点 || `temperature` | float | 否 | 生成温度,控制输出随机性,范围 0-1,推荐 0.1 || `max_retries` | int | 否 | 请求失败时的重试次数,推荐 3 |@@ -148,7 +148,7 @@ OpenViking 需要以下模型服务:"vlm": {"provider": "volcengine","api_key": "sk-1234567890abcdef1234567890abcdef",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.1,"max_retries": 3@@ -279,7 +279,7 @@ Error: Connection timeout| 模型名称 | 当前版本 | 发布日期 ||---------|---------|---------|-| Doubao-Seed-1.8 | `doubao-seed-1-8-251228` | 2025-12-28 |+| Doubao-Seed-1.8 | `doubao-seed-2-0-pro-260215` | 2025-12-28 || Doubao-Embedding-Vision | `doubao-embedding-vision-250615` | 2025-06-15 |> 注:模型版本可能更新,请以火山方舟控制台显示为准。diff --git a/docs/zh/guides/03-deployment.md b/docs/zh/guides/03-deployment.mdindex d6f615fde..278c3e863 100644--- a/docs/zh/guides/03-deployment.md+++ b/docs/zh/guides/03-deployment.md@@ -116,13 +116,13 @@ User=your-username# 替换为用户组Group=your-group# 替换为工作目录-WorkingDirectory=/home/your-username/openviking_workspace+WorkingDirectory=/var/lib/openviking# 以下两种启动方式二选一ExecStart=/path/to/your/python/bin/openviking-serverRestart=alwaysRestartSec=5# 配置文件路径-Environment="OPENVIKING_CONFIG_FILE=/home/your-username/.openviking/ov.conf"+Environment="OPENVIKING_CONFIG_FILE=/etc/openviking/ov.conf"[Install]WantedBy=multi-user.targetdiff --git a/examples/cloud/GUIDE.md b/examples/cloud/GUIDE.mdindex 68269bcc6..60a9993a5 100644--- a/examples/cloud/GUIDE.md+++ b/examples/cloud/GUIDE.md@@ -81,7 +81,7 @@ AK/SK 同时用于 TOS 和 VikingDB 的鉴权。3. 记录生成的 API Key4. 确认以下模型已开通(在 **模型广场** 中申请):- `doubao-embedding-vision-250615`(多模态 Embedding)- - `doubao-seed-1-8-251228`(VLM 推理)+ - `doubao-seed-2-0-pro-260215`(VLM 推理)5. 将 API Key 填入配置文件的 `embedding.dense.api_key` 和 `vlm.api_key`---@@ -343,7 +343,7 @@ openviking:provider: volcengineinput: multimodalvlm:- model: "doubao-seed-1-8-251228"+ model: "doubao-seed-2-0-pro-260215"api_key: "your-ark-api-key"api_base: "https://ark.cn-beijing.volces.com/api/v3"temperature: 0.0diff --git a/examples/cloud/ov.conf.example b/examples/cloud/ov.conf.exampleindex a8440c1bd..a7cef4178 100644--- a/examples/cloud/ov.conf.example+++ b/examples/cloud/ov.conf.example@@ -46,7 +46,7 @@}},"vlm": {- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_key": "<your-ark-api-key>","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.0,diff --git a/examples/k8s-helm/README.md b/examples/k8s-helm/README.mdindex 86479be91..69033cd84 100644--- a/examples/k8s-helm/README.md+++ b/examples/k8s-helm/README.md@@ -102,7 +102,7 @@ openviking:vlm:api_key: "your-api-key-here"api_base: "https://ark.cn-beijing.volces.com/api/v3"- model: "doubao-seed-1-8-251228"+ model: "doubao-seed-2-0-pro-260215"```## Storagediff --git a/examples/k8s-helm/values.yaml b/examples/k8s-helm/values.yamlindex 722fa9907..792d992eb 100644--- a/examples/k8s-helm/values.yaml+++ b/examples/k8s-helm/values.yaml@@ -31,7 +31,7 @@ openviking:dimension: "1024"backend: "volcengine"vlm:- model: "doubao-seed-1-8-251228"+ model: "doubao-seed-2-0-pro-260215"api_key: nullapi_base: "https://ark.cn-beijing.volces.com/api/v3"backend: "volcengine"diff --git a/examples/mcp-query/ov.conf.example b/examples/mcp-query/ov.conf.exampleindex fc40ea925..3ab97f7ab 100644--- a/examples/mcp-query/ov.conf.example+++ b/examples/mcp-query/ov.conf.example@@ -12,7 +12,7 @@"api_base" : "https://ark-cn-beijing.bytedance.net/api/v3","api_key" : "<your-api-key>","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228",+ "model" : "doubao-seed-2-0-pro-260215","thinking": false}}diff --git a/examples/multi_tenant/ov.conf.example b/examples/multi_tenant/ov.conf.exampleindex ebb60058d..4f2a3e009 100644--- a/examples/multi_tenant/ov.conf.example+++ b/examples/multi_tenant/ov.conf.example@@ -29,7 +29,7 @@}},"vlm": {- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_key": "{your-api-key}","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.0,diff --git a/examples/openclaw-memory-plugin/INSTALL-ZH.md b/examples/openclaw-memory-plugin/INSTALL-ZH.mdindex 08322a3d5..3fcdd3b7b 100644--- a/examples/openclaw-memory-plugin/INSTALL-ZH.md+++ b/examples/openclaw-memory-plugin/INSTALL-ZH.md@@ -58,12 +58,12 @@ copy examples\openclaw-memory-plugin\skills\install-openviking-memory\SKILL.md ^| **Node.js** | >= 22 | OpenClaw 运行时 + 安装助手 | 是 || **cmake** | — | 编译 C++ 扩展(OpenViking + OpenClaw 的 node-llama-cpp) | 是 || **g++ (gcc-c++)** | — | C++ 编译器 | 是 |-| **Go** | >= 1.25 | 编译 AGFS 服务端(仅 Linux 源码安装) | 源码安装必需 |+| **Go** | >= 1.19 | 编译 AGFS 服务端(仅 Linux 源码安装) | 源码安装必需 || **火山引擎 Ark API Key** | — | Embedding + VLM 模型调用 | 是 |> **PyPI 安装 vs 源码安装:**> - `pip install openviking --upgrade --force-reinstall`(PyPI 预编译包):只需 Python、cmake、g++,**不需要 Go**-> - `pip install -e . --force-reinstall`(源码安装):需要 Python、cmake、g++ **以及 Go >= 1.25**(Linux 上编译 AGFS)+> - `pip install -e . --force-reinstall`(源码安装):需要 Python、cmake、g++ **以及 Go >= 1.19**(Linux 上编译 AGFS)> - **Windows** 用户可直接使用预编译 wheel 包,无需 Go### 快速检查@@ -329,7 +329,7 @@ npx ./examples/openclaw-memory-plugin/setup-helper3. **交互配置** — 提示输入以下信息:- 数据存储路径(默认为绝对路径,如 `/home/yourname/.openviking/data`)- 火山引擎 Ark API Key- - VLM 模型名称(默认 `doubao-seed-1-8-251228`)+ - VLM 模型名称(默认 `doubao-seed-2-0-pro-260215`)- Embedding 模型名称(默认 `doubao-embedding-vision-250615`)- 服务端口(默认 1933 / 1833)4. **生成配置** — 创建 `~/.openviking/ov.conf`@@ -433,7 +433,7 @@ call "%USERPROFILE%\.openclaw\openviking.env.bat" && openclaw gateway"vlm": {"backend": "volcengine","api_key": "<your-api-key>",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.1,"max_retries": 3@@ -520,7 +520,7 @@ sudo apt install -y python3-dev # 或 python3.11-devLinux 源码安装**必须**安装 Go >= 1.25,参见 [3.4 安装 Go](#34-安装-go--125仅源码安装需要)。```bash-go version # 确认 >= 1.25+go version # 确认 >= 1.19python3 -m pip install -e .```@@ -587,7 +587,7 @@ call "%USERPROFILE%\.openclaw\openviking.env.bat" && openclaw gateway- `embedding.dense.api_key` 为有效的火山引擎 Ark API Key- `vlm.api_key` 已设置(通常与 embedding 相同)-- `vlm.model` 为模型名称(如 `doubao-seed-1-8-251228`),**不是** API Key+- `vlm.model` 为模型名称(如 `doubao-seed-2-0-pro-260215`),**不是** API Key### Python 版本问题diff --git a/examples/openclaw-memory-plugin/INSTALL.md b/examples/openclaw-memory-plugin/INSTALL.mdindex 88ead88b5..818b908e4 100644--- a/examples/openclaw-memory-plugin/INSTALL.md+++ b/examples/openclaw-memory-plugin/INSTALL.md@@ -58,12 +58,12 @@ For manual installation, continue reading.| **Node.js** | >= 22 | OpenClaw runtime + setup helper | Yes || **cmake** | — | Compile C++ extensions (OpenViking + OpenClaw's node-llama-cpp) | Yes || **g++ (gcc-c++)** | — | C++ compiler | Yes |-| **Go** | >= 1.25 | Compile AGFS server (Linux source install only) | Source install only |+| **Go** | >= 1.19 | Compile AGFS server (Linux source install only) | Source install only || **Volcengine Ark API Key** | — | Embedding + VLM model calls | Yes |> **PyPI vs Source install:**> - `pip install openviking --upgrade --force-reinstall` (pre-built package): needs Python, cmake, g++ — **no Go required**-> - `pip install -e . --force-reinstall` (source install): needs Python, cmake, g++ **and Go >= 1.25** (to compile AGFS on Linux)+> - `pip install -e . --force-reinstall` (source install): needs Python, cmake, g++ **and Go >= 1.19** (to compile AGFS on Linux)> - **Windows** users can use pre-built wheel packages without Go### Quick Check@@ -208,7 +208,7 @@ node -v # >= v22npm -v```-### 3.4 Install Go >= 1.25 (source install only)+### 3.4 Install Go >= 1.19 (source install only)> Already installed? Run `go version` — if it shows >= go1.25, skip this step.> Also skippable if using `pip install openviking --upgrade --force-reinstall` (pre-built package).@@ -303,7 +303,7 @@ python3 -m pip install -e .python -m pip install -e .```-> **Note:** Go >= 1.25 is **required** on Linux for source install (to compile AGFS). To force-skip (advanced users only):+> **Note:** Go >= 1.19 is **required** on Linux for source install (to compile AGFS). To force-skip (advanced users only):> ```bash> OPENVIKING_SKIP_AGFS_BUILD=1 python3 -m pip install -e .> ```@@ -329,7 +329,7 @@ The helper will walk you through:3. **Interactive configuration** — prompts for:- Data storage path (defaults to absolute path, e.g. `/home/yourname/.openviking/data`)- Volcengine Ark API Key- - VLM model name (default: `doubao-seed-1-8-251228`)+ - VLM model name (default: `doubao-seed-2-0-pro-260215`)- Embedding model name (default: `doubao-embedding-vision-250615`)- Server ports (default: 1933 / 1833)4. **Generate config** — creates `~/.openviking/ov.conf`@@ -433,7 +433,7 @@ The plugin automatically starts and stops the OpenViking server."vlm": {"backend": "volcengine","api_key": "<your-api-key>",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.1,"max_retries": 3@@ -517,10 +517,10 @@ sudo apt install -y python3-dev # or python3.11-dev#### `Go compiler not found` / AGFS build failure-Go >= 1.25 is **required** on Linux for source install. See [3.4 Install Go](#34-install-go--125-source-install-only).+Go >= 1.19 is **required** on Linux for source install. See [3.4 Install Go](#34-install-go--119-source-install-only).```bash-go version # Confirm >= 1.25+go version # Confirm >= 1.19python3 -m pip install -e .```@@ -587,7 +587,7 @@ Model configuration in `ov.conf` is incorrect. Check:- `embedding.dense.api_key` is a valid Volcengine Ark API key- `vlm.api_key` is set (usually the same key)-- `vlm.model` is a model name (e.g. `doubao-seed-1-8-251228`), **not** the API key+- `vlm.model` is a model name (e.g. `doubao-seed-2-0-pro-260215`), **not** the API key### Python Version Issuesdiff --git a/examples/openclaw-memory-plugin/README.md b/examples/openclaw-memory-plugin/README.mdindex e0eea2fda..2a8f58bc7 100644--- a/examples/openclaw-memory-plugin/README.md+++ b/examples/openclaw-memory-plugin/README.md@@ -58,7 +58,7 @@ Env vars:"vlm": {"backend": "volcengine","api_key": "<your-api-key>",- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.1,"max_retries": 3diff --git a/examples/openclaw-memory-plugin/install.ps1 b/examples/openclaw-memory-plugin/install.ps1index eb83fd1b4..63159ce7f 100644--- a/examples/openclaw-memory-plugin/install.ps1+++ b/examples/openclaw-memory-plugin/install.ps1@@ -39,7 +39,7 @@ $PluginDest = Join-Path $OpenClawDir "extensions\memory-openviking"$DefaultServerPort = 1933$DefaultAgfsPort = 1833-$DefaultVlmModel = "doubao-seed-1-8-251228"+$DefaultVlmModel = "doubao-seed-2-0-pro-260215"$DefaultEmbeddingModel = "doubao-embedding-vision-250615"function Get-PythonCommand {diff --git a/examples/openclaw-memory-plugin/install.sh b/examples/openclaw-memory-plugin/install.shindex 83ee10519..ab7c9eb47 100644--- a/examples/openclaw-memory-plugin/install.sh+++ b/examples/openclaw-memory-plugin/install.sh@@ -31,7 +31,7 @@ OPENVIKING_DIR="${HOME_DIR}/.openviking"PLUGIN_DEST="${OPENCLAW_DIR}/extensions/memory-openviking"DEFAULT_SERVER_PORT=1933DEFAULT_AGFS_PORT=1833-DEFAULT_VLM_MODEL="doubao-seed-1-8-251228"+DEFAULT_VLM_MODEL="doubao-seed-2-0-pro-260215"DEFAULT_EMBED_MODEL="doubao-embedding-vision-250615"SELECTED_SERVER_PORT="${DEFAULT_SERVER_PORT}"LANG_UI="en"diff --git a/examples/openclaw-memory-plugin/setup-helper/cli.js b/examples/openclaw-memory-plugin/setup-helper/cli.jsindex c912d3fbd..ccc79cd3e 100755--- a/examples/openclaw-memory-plugin/setup-helper/cli.js+++ b/examples/openclaw-memory-plugin/setup-helper/cli.js@@ -150,8 +150,8 @@ async function checkGo() {const m = out.match(/go([0-9]+)\.([0-9]+)/);if (!m) return { ok: false, version: null, msg: "Cannot parse Go version" };const [, major, minor] = m.map(Number);- if (major < 1 || (major === 1 && minor < 25))- return { ok: false, version: `${major}.${minor}`, msg: `Go ${major}.${minor} too old, need >= 1.25` };+ if (major < 1 || (major === 1 && minor < 19))+ return { ok: false, version: `${major}.${minor}`, msg: `Go ${major}.${minor} too old, need >= 1.19` };return { ok: true, version: `${major}.${minor}`, msg: `${major}.${minor}` };}@@ -185,7 +185,7 @@ async function checkOvvConf() {const DEFAULT_SERVER_PORT = 1933;const DEFAULT_AGFS_PORT = 1833;-const DEFAULT_VLM_MODEL = "doubao-seed-1-8-251228";+const DEFAULT_VLM_MODEL = "doubao-seed-2-0-pro-260215";const DEFAULT_EMBEDDING_MODEL = "doubao-embedding-vision-250615";const DEFAULT_WORKSPACE = join(HOME, ".openviking", "data");@@ -606,7 +606,7 @@ Env vars:log(`Go: ${goResult.msg}`, "ok");} else if (IS_LINUX) {log(`Go: ${goResult.msg}`, "err");- missing.push({ name: "Go >= 1.25", detail: goResult.msg });+ missing.push({ name: "Go >= 1.19", detail: goResult.msg });} else {log(`Go: not found (not required on ${process.platform})`, "warn");}@@ -632,7 +632,7 @@ Env vars:console.log(" # See INSTALL-ZH.md 'Linux Environment Setup' section");}if (needGo) {- console.log(" # Install Go >= 1.25:");+ console.log(" # Install Go >= 1.19:");console.log(" wget https://go.dev/dl/go1.25.6.linux-amd64.tar.gz");console.log(" sudo rm -rf /usr/local/go");console.log(" sudo tar -C /usr/local -xzf go1.25.6.linux-amd64.tar.gz");@@ -653,7 +653,7 @@ Env vars:console.log(" sudo apt install -y python3.11 python3.11-dev python3.11-venv");}if (needGo) {- console.log(" # Install Go >= 1.25:");+ console.log(" # Install Go >= 1.19:");console.log(" wget https://go.dev/dl/go1.25.6.linux-amd64.tar.gz");console.log(" sudo rm -rf /usr/local/go");console.log(" sudo tar -C /usr/local -xzf go1.25.6.linux-amd64.tar.gz");@@ -663,7 +663,7 @@ Env vars:console.log(" go env -w GOPROXY=https://goproxy.cn,direct");}} else {- console.log(" Please install: cmake, g++, Python >= 3.10, Go >= 1.25");+ console.log(" Please install: cmake, g++, Python >= 3.10, Go >= 1.19");console.log(" See INSTALL-ZH.md for detailed instructions.");}diff --git a/examples/openclaw-memory-plugin/skills/install-openviking-memory/SKILL.md b/examples/openclaw-memory-plugin/skills/install-openviking-memory/SKILL.mdindex ce0fc362b..a5b306ec2 100644--- a/examples/openclaw-memory-plugin/skills/install-openviking-memory/SKILL.md+++ b/examples/openclaw-memory-plugin/skills/install-openviking-memory/SKILL.md@@ -64,7 +64,7 @@ openclaw --version- **Pass:** Shows version output.- **Fail:** Tell the user: "OpenClaw is required. Install with: `npm install -g openclaw` (if downloads are slow: `npm install -g openclaw --registry=https://registry.npmmirror.com`). After installing, run `openclaw onboard` to configure your LLM."-### 1.5 Check Go (>= 1.25) — only for source install on Linux+### 1.5 Check Go (>= 1.19) — only for source install on Linux> Skip this check if the user will install via `pip install openviking --upgrade --force-reinstall` (PyPI pre-built package).@@ -72,8 +72,8 @@ openclaw --versiongo version```-- **Pass:** Output shows `go1.25.x` or higher.-- **Fail:** Tell the user: "Go >= 1.25 is required for source installation on Linux (to compile AGFS). Download from https://go.dev/dl/ — see INSTALL.md for detailed steps."+- **Pass:** Output shows `go1.19.x` or higher.+- **Fail:** Tell the user: "Go >= 1.19 is required for source installation on Linux (to compile AGFS). Download from https://go.dev/dl/ — see INSTALL.md for detailed steps."---@@ -100,7 +100,7 @@ python3 -m pip install openviking --upgrade --force-reinstall#### Option B: Install from Source (developer mode)-Requires Go >= 1.25 on Linux (check passed in Step 1.5).+Requires Go >= 1.19 on Linux (check passed in Step 1.5).**Linux / macOS:**@@ -150,7 +150,7 @@ The helper will interactively prompt for:1. **Workspace path** — data storage location (default: absolute path of `~/.openviking/data`, auto-detected)2. **Volcengine Ark API Key** — **[ASK USER]** Direct them to https://console.volcengine.com/ark if they don't have one-3. **VLM model** — default `doubao-seed-1-8-251228`, press Enter to accept+3. **VLM model** — default `doubao-seed-2-0-pro-260215`, press Enter to accept4. **Embedding model** — default `doubao-embedding-vision-250615`, press Enter to accept5. **Server ports** — default 1933 (HTTP) and 1833 (AGFS), press Enter to accept@@ -211,7 +211,7 @@ The **Memory** line should show: `enabled (plugin memory-openviking)`|---------|-------|-----|| `cmake not found` during npm install | Missing build tools | `sudo dnf install -y gcc gcc-c++ cmake make` || `Python.h: No such file or directory` | Missing Python dev headers | `sudo dnf install -y python3-devel` (or `python3.11-devel`) |-| `Go compiler not found` | Go not installed | Install Go >= 1.25 from https://go.dev/dl/ |+| `Go compiler not found` | Go not installed | Install Go >= 1.19 from https://go.dev/dl/ || `dial tcp: i/o timeout` (Go modules) | Network issue | `go env -w GOPROXY=https://goproxy.cn,direct` || `ERR_INVALID_URL` (npm) | Proxy missing `http://` prefix | `export https_proxy=http://host:port` || `extracted 0 memories` | Wrong API key or model name | Check `api_key` and `model` in `~/.openviking/ov.conf` |diff --git a/examples/ov.conf.example b/examples/ov.conf.exampleindex 5ca4f5e86..5be88191c 100644--- a/examples/ov.conf.example+++ b/examples/ov.conf.example@@ -45,7 +45,7 @@}},"vlm": {- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_key": "{your-api-key}","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.0,diff --git a/examples/server_client/ov.conf.example b/examples/server_client/ov.conf.exampleindex 247e90536..adaa2b414 100644--- a/examples/server_client/ov.conf.example+++ b/examples/server_client/ov.conf.example@@ -28,7 +28,7 @@}},"vlm": {- "model": "doubao-seed-1-8-251228",+ "model": "doubao-seed-2-0-pro-260215","api_key": "{your-api-key}","api_base": "https://ark.cn-beijing.volces.com/api/v3","temperature": 0.0,diff --git a/openviking/eval/datasets/local_doc_example_glm5.jsonl b/openviking/eval/datasets/local_doc_example_glm5.jsonlindex 31ffc5544..0c4516cde 100644--- a/openviking/eval/datasets/local_doc_example_glm5.jsonl+++ b/openviking/eval/datasets/local_doc_example_glm5.jsonl@@ -11,7 +11,7 @@{"question": "VikingFS 与 AGFS 的关系是什么?为什么需要两层文件系统抽象?", "files": ["OpenViking/docs/en/concepts/05-storage.md"], "answer": "VikingFS 是 AGFS 之上的 URI 抽象层,两者构成双层存储架构。\n\n**关系说明**:\n\n```\n┌─────────────────────────────────────────┐\n│ VikingFS (URI Abstraction) │\n│ URI Mapping · Hierarchical Access │\n│ · Relation Management │\n└────────────────┬────────────────────────┘\n ┌────────┴────────┐\n │ │\n┌───────▼────────┐ ┌─────▼───────────┐\n│ Vector Index │ │ AGFS │\n│ (Semantic │ │ (Content │\n│ Search) │ │ Storage) │\n└────────────────┘ └─────────────────┘\n```\n\n**职责划分**:\n\n| 层级 | 职责 | 内容 |\n|------|------|------|\n| **VikingFS** | URI 抽象层 | URI 映射、层级访问、关系管理 |\n| **AGFS** | 内容存储层 | L0/L1/L2 全部内容、多媒体文件 |\n| **Vector Index** | 索引存储层 | URI、向量、元数据 |\n\n**为什么需要两层抽象**:\n\n1. **职责分离**:\n - VikingFS 处理 URI 到物理路径的映射\n - AGFS 处理实际的文件读写操作\n\n2. **后端灵活性**:\n - AGFS 支持多种后端:localfs、s3fs、memory\n - VikingFS 屏蔽底层存储差异\n\n3. **URI 映射示例**:\n```\nviking://resources/docs/auth → /local/resources/docs/auth\nviking://user/memories → /local/user/memories\n```\n\n4. **设计优势**:\n - 清晰职责:向量索引负责检索,AGFS 负责存储\n - 内存优化:向量索引不存储文件内容\n - 独立扩展:向量索引和 AGFS 可独立扩展"}{"question": "`client.add_resource` 支持哪些输入格式?如何处理本地目录的递归添加和子目录过滤?", "files": ["OpenViking/docs/en/api/02-resources.md", "OpenViking/openviking/parse/directory_scan.py:1-80"], "answer": "`add_resource` 支持多种输入格式,目录处理通过 directory_scan 模块实现。\n\n**支持的输入格式**:\n\n| 格式 | 扩展名 | 处理方式 |\n|------|--------|----------|\n| PDF | `.pdf` | 文本和图片提取 |\n| Markdown | `.md` | 原生支持 |\n| HTML | `.html`, `.htm` | 清理文本提取 |\n| 纯文本 | `.txt` | 直接导入 |\n| JSON/YAML | `.json`, `.yaml` | 结构化解析 |\n| 代码 | `.py`, `.js`, `.go` 等 | 语法感知解析 |\n| 图片 | `.png`, `.jpg` 等 | VLM 描述 |\n| 视频/音频 | `.mp4`, `.mp3` 等 | 转录 |\n\n**目录递归添加流程**:\n\n1. **DirectoryScan 预扫描**:\n - 遍历目录树\n - 分类文件为 processable / unsupported\n - 跳过:点文件、符号链接、空文件\n\n2. **目录过滤机制**:\n```python\ndef _should_skip_directory(dir_path, root, ignore_dirs):\n # 跳过:点目录、符号链接、IGNORE_DIRS\n```\n\n3. **内置忽略目录**:\n - `.git`、`node_modules`、`__pycache__` 等\n - 通过 `IGNORE_DIRS` 常量定义\n\n4. **API 参数**:\n```python\nclient.add_resource(\n \"./documents\", # 本地目录路径\n target=\"viking://resources/docs\", # 目标 URI\n reason=\"文档说明\", # 添加原因\n wait=True, # 等待处理完成\n timeout=300 # 超时时间\n)\n```\n\n**处理流水线**:\nInput → Parser → TreeBuilder → AGFS → SemanticQueue → Vector Index"}{"question": "向量索引是如何构建和维护的?增量更新时如何避免全量重建?", "files": ["OpenViking/openviking/storage/viking_vector_index_backend.py", "OpenViking/docs/en/concepts/05-storage.md"], "answer": "向量索引通过 VikingVectorIndexBackend 实现,支持增量更新。\n\n**索引构建流程**:\n\n1. **初始化配置**:\n```python\nconfig = VectorDBBackendConfig(\n backend=\"local\", # local/http/volcengine\n path=\"./data/vectordb\",\n dimension=1024,\n distance_metric=\"cosine\"\n)\nbackend = VikingVectorIndexBackend(config=config)\n```\n\n2. **支持的后端模式**:\n - **local**:本地持久化存储\n - **http**:远程 HTTP 服务\n - **volcengine**:火山引擎 VikingDB\n\n3. **索引特性**:\n - 使用 BruteForce 索引进行向量相似度搜索\n - 支持标量过滤和多操作符\n - 每个集合自动管理索引\n\n**增量更新机制**:\n\n1. **URI 级别操作**:\n - VikingFS 的 `rm()`、`mv()` 操作同步更新向量索引\n - 新增内容自动触发向量化并写入索引\n\n2. **避免全量重建**:\n - 通过 URI 唯一标识每个向量条目\n - 更新时只删除旧向量、插入新向量\n - 不影响其他条目的索引\n\n3. **双层存储优势**:\n - 向量索引只存储 URI 引用和元数据\n - 内容变更不影响索引结构\n - 独立扩展存储和索引层\n\n**核心 API**:\n- `upsert()`:插入或更新向量\n- `delete()`:删除向量\n- `search()`:向量相似度搜索"}-{"question": "配置文件 `ov.conf` 的必填项有哪些?如何配置不同的 VLM 后端(OpenAI、Volcengine 等)?", "files": ["OpenViking/docs/en/guides/01-configuration.md:1-150"], "answer": "配置文件 `ov.conf` 包含 embedding、vlm、rerank、storage 等配置项。\n\n**必填配置项**:\n\n```json\n{\n \"embedding\": {\n \"dense\": {\n \"provider\": \"volcengine\", // 必填:volcengine/openai/vikingdb\n \"api_key\": \"your-api-key\", // 必填\n \"model\": \"doubao-embedding-vision-250615\",\n \"dimension\": 1024\n }\n },\n \"vlm\": {\n \"provider\": \"volcengine\", // 必填\n \"api_key\": \"your-api-key\", // 必填\n \"model\": \"doubao-seed-1-8-251228\"\n }\n}\n```\n\n**VLM 后端配置**:\n\n1. **Volcengine(豆包模型)**:\n```json\n{\n \"vlm\": {\n \"api_base\": \"https://ark.cn-beijing.volces.com/api/v3\",\n \"api_key\": \"your-volcengine-api-key\",\n \"provider\": \"volcengine\",\n \"model\": \"doubao-seed-1-8-251228\"\n }\n}\n```\n\n2. **OpenAI**:\n```json\n{\n \"vlm\": {\n \"api_base\": \"https://api.openai.com/v1\",\n \"api_key\": \"your-openai-api-key\",\n \"provider\": \"openai\",\n \"model\": \"gpt-4-vision-preview\"\n }\n}\n```\n\n**Embedding 配置**:\n\n| 参数 | 说明 |\n|------|------|\n| `provider` | volcengine/openai/vikingdb |\n| `api_key` | API 密钥 |\n| `model` | 模型名称 |\n| `dimension` | 向量维度 |\n| `input` | 输入类型:text/multimodal |\n\n**可选配置**:\n- `rerank`:重排序模型配置\n- `storage`:存储后端配置"}+{"question": "配置文件 `ov.conf` 的必填项有哪些?如何配置不同的 VLM 后端(OpenAI、Volcengine 等)?", "files": ["OpenViking/docs/en/guides/01-configuration.md:1-150"], "answer": "配置文件 `ov.conf` 包含 embedding、vlm、rerank、storage 等配置项。\n\n**必填配置项**:\n\n```json\n{\n \"embedding\": {\n \"dense\": {\n \"provider\": \"volcengine\", // 必填:volcengine/openai/vikingdb\n \"api_key\": \"your-api-key\", // 必填\n \"model\": \"doubao-embedding-vision-250615\",\n \"dimension\": 1024\n }\n },\n \"vlm\": {\n \"provider\": \"volcengine\", // 必填\n \"api_key\": \"your-api-key\", // 必填\n \"model\": \"doubao-seed-2-0-pro-260215\"\n }\n}\n```\n\n**VLM 后端配置**:\n\n1. **Volcengine(豆包模型)**:\n```json\n{\n \"vlm\": {\n \"api_base\": \"https://ark.cn-beijing.volces.com/api/v3\",\n \"api_key\": \"your-volcengine-api-key\",\n \"provider\": \"volcengine\",\n \"model\": \"doubao-seed-2-0-pro-260215\"\n }\n}\n```\n\n2. **OpenAI**:\n```json\n{\n \"vlm\": {\n \"api_base\": \"https://api.openai.com/v1\",\n \"api_key\": \"your-openai-api-key\",\n \"provider\": \"openai\",\n \"model\": \"gpt-4-vision-preview\"\n }\n}\n```\n\n**Embedding 配置**:\n\n| 参数 | 说明 |\n|------|------|\n| `provider` | volcengine/openai/vikingdb |\n| `api_key` | API 密钥 |\n| `model` | 模型名称 |\n| `dimension` | 向量维度 |\n| `input` | 输入类型:text/multimodal |\n\n**可选配置**:\n- `rerank`:重排序模型配置\n- `storage`:存储后端配置"}{"question": "`HierarchicalRetriever` 的检索流程是怎样的?如何实现从 L0 到 L2 的层级穿透检索?", "files": ["OpenViking/openviking/retrieve/hierarchical_retriever.py"], "answer": "HierarchicalRetriever 实现目录递归检索和层级穿透。\n\n**检索流程**:\n\n1. **初始化**:\n```python\nclass HierarchicalRetriever:\n MAX_CONVERGENCE_ROUNDS = 3 # 收敛轮次\n MAX_RELATIONS = 5 # 最大关联数\n SCORE_PROPAGATION_ALPHA = 0.5 # 分数传播系数\n DIRECTORY_DOMINANCE_RATIO = 1.2 # 目录分数阈值\n GLOBAL_SEARCH_TOPK = 3 # 全局检索数量\n```\n\n2. **检索模式**:\n - **THINKING**:深度思考模式\n - **QUICK**:快速检索模式\n\n3. **核心方法**:\n```python\nasync def retrieve(\n self,\n query: TypedQuery,\n limit: int = 5,\n mode: RetrieverMode = RetrieverMode.THINKING,\n score_threshold: Optional[float] = None,\n metadata_filter: Optional[Dict[str, Any]] = None,\n) -> QueryResult:\n```\n\n**层级穿透机制**:\n\n1. **L0 检索**:\n - 向量相似度搜索 `.abstract.md` 内容\n - 快速过滤不相关内容\n\n2. **L1 确认**:\n - 读取 `.overview.md` 进行重排序\n - 确认内容相关性\n\n3. **L2 加载**:\n - 按需读取完整内容\n - 仅在确认需要时加载\n\n**关键特性**:\n- 分数传播:目录分数向子节点传播\n- 目录优势:目录分数需超过最大子节点分数\n- 关联检索:自动检索关联上下文"}{"question": "语义处理队列的工作机制是什么?如何监控和调试异步处理状态?", "files": ["OpenViking/docs/en/concepts/01-architecture.md", "OpenViking/openviking/service/resource_service.py:1-80"], "answer": "语义处理队列通过 SemanticQueue 异步生成 L0/L1 内容。\n\n**工作机制**:\n\n1. **处理流水线**:\n```\nInput → Parser → TreeBuilder → AGFS → SemanticQueue → Vector Index\n```\n\n2. **队列处理**:\n - TreeBuilder 将文件移动到 AGFS 后入队\n - SemanticQueue 异步处理队列项\n - 自底向上生成 L0/L1\n\n3. **异步处理优势**:\n - 不阻塞资源添加操作\n - 支持大规模文档处理\n - LLM 调用并行化\n\n**监控和调试**:\n\n1. **等待处理完成**:\n```python\nresult = client.add_resource(\"./docs\", wait=False)\nclient.wait_processed() # 等待队列处理完成\n```\n\n2. **超时控制**:\n```python\nresult = client.add_resource(\n \"./docs\",\n wait=True,\n timeout=300 # 超时时间(秒)\n)\n```\n\n3. **DebugService**:\n - 提供 ObserverService 用于调试\n - 可视化检索轨迹\n\n4. **日志监控**:\n - 通过 logger 获取处理状态\n - 监控队列长度和处理延迟\n\n**Service 层支持**:\n- ResourceService 管理 add_resource 操作\n- wait_processed() 方法等待语义处理完成"}{"question": "如何通过代码动态创建和管理 Session?Session 与 Memory 的关系是什么?", "files": ["OpenViking/docs/en/concepts/08-session.md", "OpenViking/openviking/session/memory_extractor.py"], "answer": "Session 通过 client API 动态创建,commit 后自动提取 Memory。\n\n**Session 创建和管理**:\n\n1. **创建 Session**:\n```python\n# 创建新会话\nsession = client.session(session_id=\"chat_001\")\n\n# 或使用 create_session\nresult = client.create_session()\n```\n\n2. **添加消息**:\n```python\nsession.add_message(\n \"user\",\n [TextPart(\"How to configure embedding?\")]\n)\n\nsession.add_message(\n \"assistant\",\n [\n TextPart(\"Here's how...\"),\n ContextPart(uri=\"viking://user/memories/profile.md\"),\n ]\n)\n```\n\n3. **记录使用**:\n```python\nsession.used(contexts=[\"viking://user/memories/profile.md\"])\nsession.used(skill={\n \"uri\": \"viking://agent/skills/code-search\",\n \"input\": \"search config\",\n \"output\": \"found 3 files\",\n \"success\": True\n})\n```\n\n4. **提交会话**:\n```python\nresult = session.commit()\n# {\"status\": \"committed\", \"memories_extracted\": 5}\n```\n\n**Session 与 Memory 的关系**:\n\n1. **Memory 来源**:\n - Memory 从 Session 消息中提取\n - MemoryExtractor 在 commit 时触发\n\n2. **提取流程**:\n - 格式化会话消息\n - 调用 LLM 提取 6 类记忆\n - 写入对应目录并索引\n\n3. **记忆类别映射**:\n - profile → `user/memories/profile.md`\n - preferences → `user/memories/preferences/`\n - entities → `user/memories/entities/`\n - events → `user/memories/events/`\n - cases → `agent/memories/cases/`\n - patterns → `agent/memories/patterns/`"}diff --git a/openviking/models/vlm/backends/volcengine_vlm.py b/openviking/models/vlm/backends/volcengine_vlm.pyindex 3b80bdc67..985025cac 100644--- a/openviking/models/vlm/backends/volcengine_vlm.py+++ b/openviking/models/vlm/backends/volcengine_vlm.py@@ -27,7 +27,7 @@ class VolcEngineVLM(OpenAIVLM):if not self.api_base:self.api_base = "https://ark.cn-beijing.volces.com/api/v3"if not self.model:- self.model = "doubao-seed-1-8-251228"+ self.model = "doubao-seed-2-0-pro-260215"def get_client(self):"""Get sync client"""@@ -63,7 +63,7 @@ class VolcEngineVLM(OpenAIVLM):"""Get text completion"""client = self.get_client()kwargs = {- "model": self.model or "doubao-seed-1-8-251228",+ "model": self.model or "doubao-seed-2-0-pro-260215","messages": [{"role": "user", "content": prompt}],"temperature": self.temperature,"thinking": {"type": "disabled" if not thinking else "enabled"},@@ -79,7 +79,7 @@ class VolcEngineVLM(OpenAIVLM):"""Get text completion asynchronously"""client = self.get_async_client()kwargs = {- "model": self.model or "doubao-seed-1-8-251228",+ "model": self.model or "doubao-seed-2-0-pro-260215","messages": [{"role": "user", "content": prompt}],"temperature": self.temperature,"thinking": {"type": "disabled" if not thinking else "enabled"},@@ -230,7 +230,7 @@ class VolcEngineVLM(OpenAIVLM):content.append({"type": "text", "text": prompt})kwargs = {- "model": self.model or "doubao-seed-1-8-251228",+ "model": self.model or "doubao-seed-2-0-pro-260215","messages": [{"role": "user", "content": content}],"temperature": self.temperature,"thinking": {"type": "disabled" if not thinking else "enabled"},@@ -255,7 +255,7 @@ class VolcEngineVLM(OpenAIVLM):content.append({"type": "text", "text": prompt})kwargs = {- "model": self.model or "doubao-seed-1-8-251228",+ "model": self.model or "doubao-seed-2-0-pro-260215","messages": [{"role": "user", "content": content}],"temperature": self.temperature,"thinking": {"type": "disabled" if not thinking else "enabled"},diff --git a/openviking_cli/client/http.py b/openviking_cli/client/http.pyindex 312f5d08c..f45417818 100644--- a/openviking_cli/client/http.py+++ b/openviking_cli/client/http.py@@ -35,11 +35,13 @@ from openviking_cli.retrieve.types import FindResultfrom openviking_cli.session.user_id import UserIdentifierfrom openviking_cli.utils import run_asyncfrom openviking_cli.utils.config.config_loader import (- DEFAULT_OVCLI_CONF,- OPENVIKING_CLI_CONFIG_ENV,load_json_config,resolve_config_path,)+from openviking_cli.utils.config.consts import (+ DEFAULT_OVCLI_CONF,+ OPENVIKING_CLI_CONFIG_ENV,+)from openviking_cli.utils.uri import VikingURI# Error code to exception class mapping@@ -143,8 +145,8 @@ class AsyncHTTPClient(BaseClient):timeout: HTTP request timeout in seconds. Default 60.0."""if url is None:- print(f'OPENVIKING_CLI_CONFIG_ENV={OPENVIKING_CLI_CONFIG_ENV}')- print(f'DEFAULT_OVCLI_CONF={DEFAULT_OVCLI_CONF}')+ # print(f"OPENVIKING_CLI_CONFIG_ENV={OPENVIKING_CLI_CONFIG_ENV}")+ # print(f"DEFAULT_OVCLI_CONF={DEFAULT_OVCLI_CONF}")config_path = resolve_config_path(None, OPENVIKING_CLI_CONFIG_ENV, DEFAULT_OVCLI_CONF)if config_path:cfg = load_json_config(config_path)diff --git a/pyproject.toml b/pyproject.tomlindex 0bcb91956..c25ca5db1 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -67,6 +67,7 @@ dependencies = ["tree-sitter-rust>=0.23.0","tree-sitter-go>=0.23.0","tree-sitter-c-sharp>=0.23.0",+ "loguru>=0.7.3",][tool.uv.sources]diff --git a/test_chat_command.py b/test_chat_command.pydeleted file mode 100644index 520e7a8c2..000000000--- a/test_chat_command.py+++ /dev/null@@ -1,31 +0,0 @@-#!/usr/bin/env python3-"""Test script to verify the ov chat command implementation."""--import sys-from pathlib import Path--# Add the root directory to Python path-root_dir = Path(__file__).parent-sys.path.insert(0, str(root_dir))--from openviking_cli.cli.commands.chat import _check_vikingbot---def test_vikingbot_detection():- """Test that vikingbot detection works."""- print("Testing vikingbot detection...")- has_vikingbot = _check_vikingbot()- print(f"vikingbot available: {has_vikingbot}")-- # Also check via import- try:- import vikingbot- print(f"Direct import successful: vikingbot {vikingbot.__version__}")- except ImportError:- print("Direct import: vikingbot not found")-- return has_vikingbot---if __name__ == "__main__":- test_vikingbot_detection()diff --git a/test_chat_integration.py b/tests/client/test_chat_integration.pysimilarity index 100%rename from test_chat_integration.pyrename to tests/client/test_chat_integration.pyindex 9d97178bb..175e8125f 100644--- a/test_chat_integration.py+++ b/tests/client/test_chat_integration.py@@ -1,8 +1,8 @@#!/usr/bin/env python3"""Integration test for ov chat command."""-import sysimport subprocess+import sysfrom pathlib import Path# Add root to pathdiff --git a/third_party/agfs/agfs-fuse/go.mod b/third_party/agfs/agfs-fuse/go.modindex b8e6d6b1a..c2a06bb83 100644--- a/third_party/agfs/agfs-fuse/go.mod+++ b/third_party/agfs/agfs-fuse/go.mod@@ -1,6 +1,6 @@module github.com/dongxuny/agfs-fuse-go 1.21.1+go 1.19require github.com/c4pt0r/agfs/agfs-sdk/go v0.0.0-00010101000000-000000000000diff --git a/third_party/agfs/agfs-sdk/go/go.mod b/third_party/agfs/agfs-sdk/go/go.modindex 05fc4f6e9..8405299e2 100644--- a/third_party/agfs/agfs-sdk/go/go.mod+++ b/third_party/agfs/agfs-sdk/go/go.mod@@ -1,3 +1,3 @@module github.com/c4pt0r/agfs/agfs-sdk/go-go 1.20+go 1.19diff --git a/third_party/agfs/agfs-server/go.mod b/third_party/agfs/agfs-server/go.modindex b65f492b3..623b91618 100644--- a/third_party/agfs/agfs-server/go.mod+++ b/third_party/agfs/agfs-server/go.mod@@ -1,6 +1,6 @@module github.com/c4pt0r/agfs/agfs-server-go 1.25+go 1.19require (github.com/aws/aws-sdk-go-v2 v1.39.2diff --git a/uv.lock b/uv.lockindex d31b61fec..460ad1602 100644--- a/uv.lock+++ b/uv.lock@@ -1752,6 +1752,19 @@ wheels = [{ url = "https://files.pythonhosted.org/packages/d8/b3/e8fe151c1b81666575552835a3a79127c5aa6bd460fcecc51e032d2f4019/litellm-1.81.14-py3-none-any.whl", hash = "sha256:6394e61bbdef7121e5e3800349f6b01e9369e7cf611e034f1832750c481abfed", size = 14603260, upload-time = "2026-02-22T00:33:32.464Z" },]+[[package]]+name = "loguru"+version = "0.7.3"+source = { registry = "https://pypi.org/simple" }+dependencies = [+ { name = "colorama", marker = "sys_platform == 'win32'" },+ { name = "win32-setctime", marker = "sys_platform == 'win32'" },+]+sdist = { url = "https://files.pythonhosted.org/packages/3a/05/a1dae3dffd1116099471c643b8924f5aa6524411dc6c63fdae648c4f1aca/loguru-0.7.3.tar.gz", hash = "sha256:19480589e77d47b8d85b2c827ad95d49bf31b0dcde16593892eb51dd18706eb6", size = 63559, upload-time = "2024-12-06T11:20:56.608Z" }+wheels = [+ { url = "https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c", size = 61595, upload-time = "2024-12-06T11:20:54.538Z" },+]+[[package]]name = "lxml"version = "6.0.2"@@ -2561,6 +2574,7 @@ dependencies = [{ name = "jinja2" },{ name = "json-repair" },{ name = "litellm" },+ { name = "loguru" },{ name = "markdownify" },{ name = "openai" },{ name = "openpyxl" },@@ -2636,6 +2650,7 @@ requires-dist = [{ name = "jinja2", specifier = ">=3.1.6" },{ name = "json-repair", specifier = ">=0.25.0" },{ name = "litellm", specifier = ">=1.0.0" },+ { name = "loguru", specifier = ">=0.7.3" },{ name = "markdownify", specifier = ">=0.11.0" },{ name = "mypy", marker = "extra == 'dev'", specifier = ">=1.0.0" },{ name = "myst-parser", marker = "extra == 'doc'", specifier = ">=2.0.0" },@@ -5137,6 +5152,15 @@ wheels = [{ url = "https://files.pythonhosted.org/packages/f4/24/2a3e3df732393fed8b3ebf2ec078f05546de641fe1b667ee316ec1dcf3b7/webencodings-0.5.1-py2.py3-none-any.whl", hash = "sha256:a0af1213f3c2226497a97e2b3aa01a7e4bee4f403f95be16fc9acd2947514a78", size = 11774, upload-time = "2017-04-05T20:21:32.581Z" },]+[[package]]+name = "win32-setctime"+version = "1.2.0"+source = { registry = "https://pypi.org/simple" }+sdist = { url = "https://files.pythonhosted.org/packages/b3/8f/705086c9d734d3b663af0e9bb3d4de6578d08f46b1b101c2442fd9aecaa2/win32_setctime-1.2.0.tar.gz", hash = "sha256:ae1fdf948f5640aae05c511ade119313fb6a30d7eabe25fef9764dca5873c4c0", size = 4867, upload-time = "2024-12-07T15:28:28.314Z" }+wheels = [+ { url = "https://files.pythonhosted.org/packages/e1/07/c6fe3ad3e685340704d314d765b7912993bcb8dc198f0e7a89382d37974b/win32_setctime-1.2.0-py3-none-any.whl", hash = "sha256:95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390", size = 4083, upload-time = "2024-12-07T15:28:26.465Z" },+]+[[package]]name = "xlsxwriter"version = "3.2.9"