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
fix(volcengine): update default doubao embedding model (#1438)
Qin Haojie3c2f095c4f38
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex 088cb3606..8801d0aa4 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -76,7 +76,7 @@ Create a configuration file `~/.openviking/ov.conf`:"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,"input": "multimodal"diff --git a/CONTRIBUTING_CN.md b/CONTRIBUTING_CN.mdindex 7073d6c03..649c82c8d 100644--- a/CONTRIBUTING_CN.md+++ b/CONTRIBUTING_CN.md@@ -76,7 +76,7 @@ uv pip install -e . --force-reinstall"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,"input": "multimodal"diff --git a/CONTRIBUTING_JA.md b/CONTRIBUTING_JA.mdindex 2011ce75f..7f27be750 100644--- a/CONTRIBUTING_JA.md+++ b/CONTRIBUTING_JA.md@@ -76,7 +76,7 @@ uv pip install -e . --force-reinstall"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,"input": "multimodal"diff --git a/README.md b/README.mdindex 4dc37240d..1bb8d3745 100644--- a/README.md+++ b/README.md@@ -263,7 +263,7 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"api_key" : "<your-api-key>", // Model service API Key"provider" : "<provider-type>", // Provider type: "volcengine" or "openai" (currently supported)"dimension": 1024, // Vector dimension- "model" : "<model-name>" // Embedding model name (e.g., doubao-embedding-vision-250615 or text-embedding-3-large)+ "model" : "<model-name>" // Embedding model name (e.g., doubao-embedding-vision-251215 or text-embedding-3-large)},"max_concurrent": 10 // Max concurrent embedding requests (default: 10)},@@ -301,7 +301,7 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"api_key" : "your-volcengine-api-key","provider" : "volcengine","dimension": 1024,- "model" : "doubao-embedding-vision-250615"+ "model" : "doubao-embedding-vision-251215"},"max_concurrent": 10},diff --git a/README_CN.md b/README_CN.mdindex c63d14361..14381a062 100644--- a/README_CN.md+++ b/README_CN.md@@ -287,7 +287,7 @@ ollama serve"provider" : "<provider-type>", // 提供商类型:"volcengine"、"openai"、"azure" 等"api_version": "2025-01-01-preview", // (仅 azure)API 版本,可选,默认 "2025-01-01-preview""dimension": 1024, // 向量维度- "model" : "<model-name>" // Embedding 模型名称或 Azure 部署名(如 doubao-embedding-vision-250615 或 text-embedding-3-large)+ "model" : "<model-name>" // Embedding 模型名称或 Azure 部署名(如 doubao-embedding-vision-251215 或 text-embedding-3-large)},"max_concurrent": 10 // 最大并发 embedding 请求(默认:10)},@@ -326,7 +326,7 @@ ollama serve"api_key" : "your-volcengine-api-key","provider" : "volcengine","dimension": 1024,- "model" : "doubao-embedding-vision-250615"+ "model" : "doubao-embedding-vision-251215"},"max_concurrent": 10},diff --git a/README_JA.md b/README_JA.mdindex 9ebc971e6..35608aa3b 100644--- a/README_JA.md+++ b/README_JA.md@@ -263,7 +263,7 @@ ollama serve"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" または "openai"(現在サポート済み)"dimension": 1024, // ベクトル次元- "model" : "<model-name>" // Embeddingモデル名(例:doubao-embedding-vision-250615 または text-embedding-3-large)+ "model" : "<model-name>" // Embeddingモデル名(例:doubao-embedding-vision-251215 または text-embedding-3-large)},"max_concurrent": 10 // 最大同時Embeddingリクエスト数(デフォルト: 10)},@@ -301,7 +301,7 @@ ollama serve"api_key" : "your-volcengine-api-key","provider" : "volcengine","dimension": 1024,- "model" : "doubao-embedding-vision-250615"+ "model" : "doubao-embedding-vision-251215"},"max_concurrent": 10},diff --git a/benchmark/RAG/ov.conf.example b/benchmark/RAG/ov.conf.exampleindex 9ea5f47e2..c34864bef 100644--- a/benchmark/RAG/ov.conf.example+++ b/benchmark/RAG/ov.conf.example@@ -10,7 +10,7 @@},"embedding": {"dense": {- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_key": "your_api_key_here","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,diff --git a/deploy/helm/README.md b/deploy/helm/README.mdindex 9e9a8f9cb..b1ac56de2 100644--- a/deploy/helm/README.md+++ b/deploy/helm/README.md@@ -55,7 +55,7 @@ config:api_key: "your-volcengine-api-key"provider: "volcengine"dimension: 1024- model: "doubao-embedding-vision-250615"+ model: "doubao-embedding-vision-251215"input: "multimodal"max_concurrent: 10vlm:diff --git a/deploy/helm/openviking/values.yaml b/deploy/helm/openviking/values.yamlindex 3d5dd9535..838296d62 100644--- a/deploy/helm/openviking/values.yaml+++ b/deploy/helm/openviking/values.yaml@@ -98,7 +98,7 @@ config:api_key: ""provider: "volcengine"dimension: 1024- model: "doubao-embedding-vision-250615"+ model: "doubao-embedding-vision-251215"input: "multimodal"max_concurrent: 10vlm:diff --git a/docs/en/faq/faq.md b/docs/en/faq/faq.mdindex 5fb567293..da9271be4 100644--- a/docs/en/faq/faq.md+++ b/docs/en/faq/faq.md@@ -92,7 +92,7 @@ Create an `~/.openviking/ov.conf` configuration file in your project directory:"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","dimension": 1024,"input": "multimodal"}diff --git a/docs/en/getting-started/03-quickstart-server.md b/docs/en/getting-started/03-quickstart-server.mdindex 8396280a9..45ec3d28b 100644--- a/docs/en/getting-started/03-quickstart-server.md+++ b/docs/en/getting-started/03-quickstart-server.md@@ -272,7 +272,7 @@ vim ~/.openviking/ov.conf"api_key" : "<your-api-key>", // Model service API Key"provider" : "<provider-type>", // volcengine or openai"dimension": 1024, // Vector dimension- "model" : "<model-name>", // e.g., doubao-embedding-vision-250615+ "model" : "<model-name>", // e.g., doubao-embedding-vision-251215"input" : "multimodal" // Use "multimodal" for doubao-embedding-vision models}},diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.mdindex 0d4a24542..fa1cc4921 100644--- a/docs/en/guides/01-configuration.md+++ b/docs/en/guides/01-configuration.md@@ -49,7 +49,7 @@ Create `~/.openviking/ov.conf` in your project directory:"api_key" : "your-volcengine-api-key","provider" : "volcengine","dimension": 1024,- "model" : "doubao-embedding-vision-250615",+ "model" : "doubao-embedding-vision-251215","input": "multimodal"}},@@ -105,7 +105,7 @@ Embedding model configuration for vector search, supporting dense, sparse, and h"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","dimension": 1024,"input": "multimodal"}@@ -154,7 +154,7 @@ When the embedding provider experiences consecutive transient failures (e.g. `42| Model | Dimension | Input Type | Notes ||-------|-----------|------------|-------|-| `doubao-embedding-vision-250615` | 1024 | multimodal | Recommended |+| `doubao-embedding-vision-251215` | 1024 | multimodal | Recommended || `doubao-embedding-250615` | 1024 | text | Text only |With `input: "multimodal"`, OpenViking can embed text, images (PNG, JPG, etc.), and mixed content.@@ -321,7 +321,7 @@ Supported task types: `RETRIEVAL_QUERY`, `RETRIEVAL_DOCUMENT`, `SEMANTIC_SIMILAR#### Sparse Embedding-> **Note:** Volcengine sparse embedding is supported starting from model `doubao-embedding-vision-250615`.+> **Note:** Volcengine sparse embedding is supported starting from model `doubao-embedding-vision-251215`.```json{@@ -329,7 +329,7 @@ Supported task types: `RETRIEVAL_QUERY`, `RETRIEVAL_DOCUMENT`, `SEMANTIC_SIMILAR"sparse": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615"+ "model": "doubao-embedding-vision-251215"}}}@@ -362,13 +362,13 @@ Two approaches are supported:"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","dimension": 1024},"sparse": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615"+ "model": "doubao-embedding-vision-251215"}}}diff --git a/docs/en/guides/02-volcengine-purchase-guide.md b/docs/en/guides/02-volcengine-purchase-guide.mdindex 27539b19c..4a95ca683 100644--- a/docs/en/guides/02-volcengine-purchase-guide.md+++ b/docs/en/guides/02-volcengine-purchase-guide.md@@ -9,7 +9,7 @@ OpenViking requires the following model services:| Model Type | Purpose | Recommended Model ||------------|---------|-------------------|| VLM (Vision Language Model) | Content understanding, semantic generation | `doubao-seed-2-0-pro-260215` |-| Embedding | Vectorization, semantic retrieval | `doubao-embedding-vision-250615` |+| Embedding | Vectorization, semantic retrieval | `doubao-embedding-vision-251215` |## Prerequisites@@ -82,7 +82,7 @@ Visit: [Model Management Page](https://console.volcengine.com/ark/region:ark+cn-<img src="../../images/activate_emb_model.gif" width="80%"></div>-After activation, use the model ID: `doubao-embedding-vision-250615`+After activation, use the model ID: `doubao-embedding-vision-251215`## Configure OpenViking@@ -132,7 +132,7 @@ 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-embedding-vision-250615` |+| `model` | string | Yes | Model ID, e.g., `doubao-embedding-vision-251215` || `api_base` | string | No | API endpoint address, defaults to Beijing region endpoint, see Appendix - Regional Endpoints for details || `dimension` | int | Yes | Vector dimension, depends on the model (usually 1024 or 768) || `input` | string | No | Input type: `"multimodal"` (multimodal) or `"text"` (plain text), default `"multimodal"` |@@ -155,7 +155,7 @@ Save the following content as `~/.openviking/ov.conf`:"dense": {"provider": "volcengine","api_key": "sk-1234567890abcdef1234567890abcdef",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,"input": "multimodal"@@ -278,6 +278,6 @@ Error: Connection timeout| Model Name | Current Version | Release Date ||------------|-----------------|--------------|| Doubao-Seed-1.8 | `doubao-seed-2-0-pro-260215` | 2025-12-28 |-| Doubao-Embedding-Vision | `doubao-embedding-vision-250615` | 2025-06-15 |+| Doubao-Embedding-Vision | `doubao-embedding-vision-251215` | 2025-06-15 |> Note: Model versions may be updated, please refer to the Volcano Ark Console for the latest information.diff --git a/docs/zh/faq/faq.md b/docs/zh/faq/faq.mdindex cba33546b..c4c69b011 100644--- a/docs/zh/faq/faq.md+++ b/docs/zh/faq/faq.md@@ -91,7 +91,7 @@ pip install openviking --upgrade --force-reinstall"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","dimension": 1024,"input": "multimodal"}diff --git a/docs/zh/getting-started/03-quickstart-server.md b/docs/zh/getting-started/03-quickstart-server.mdindex 683790609..9cdf32f70 100644--- a/docs/zh/getting-started/03-quickstart-server.md+++ b/docs/zh/getting-started/03-quickstart-server.md@@ -269,8 +269,8 @@ vim ~/.openviking/ov.conf"api_key" : "<your-api-key>", // Model service API Key"provider" : "<provider-type>", // Provider type (volcengine or openai)"dimension": 1024, // Vector dimension- "model" : "<model-name>", // Embedding model name (e.g., doubao-embedding-vision-250615)- "input" : "multimodal" // if use doubao-embedding-vision-250615, should be multimodal+ "model" : "<model-name>", // Embedding model name (e.g., doubao-embedding-vision-251215)+ "input" : "multimodal" // if use doubao-embedding-vision-251215, should be multimodal}},"vlm": {diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.mdindex 9f2c10ac5..cf5c58c0b 100644--- a/docs/zh/guides/01-configuration.md+++ b/docs/zh/guides/01-configuration.md@@ -50,7 +50,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支"api_key" : "your-volcengine-api-key","provider" : "volcengine","dimension": 1024,- "model" : "doubao-embedding-vision-250615",+ "model" : "doubao-embedding-vision-251215","input": "multimodal"}},@@ -106,7 +106,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","dimension": 1024,"input": "multimodal","batch_size": 32@@ -156,7 +156,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支| 模型 | 维度 | 输入类型 | 说明 ||------|------|----------|------|-| `doubao-embedding-vision-250615` | 1024 | multimodal | 推荐 |+| `doubao-embedding-vision-251215` | 1024 | multimodal | 推荐 || `doubao-embedding-250615` | 1024 | text | 仅文本 |使用 `input: "multimodal"` 时,OpenViking 可以嵌入文本、图片(PNG、JPG 等)和混合内容。@@ -291,7 +291,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支#### Sparse Embedding-> **注意:** 火山引擎的 Sparse embedding 从 `doubao-embedding-vision-250615` 模型版本起支持。+> **注意:** 火山引擎的 Sparse embedding 从 `doubao-embedding-vision-251215` 模型版本起支持。```json{@@ -299,7 +299,7 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支"sparse": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615"+ "model": "doubao-embedding-vision-251215"}}}@@ -332,13 +332,13 @@ OpenViking 使用 JSON 配置文件(`ov.conf`)进行设置。配置文件支"dense": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","dimension": 1024},"sparse": {"provider": "volcengine","api_key": "your-api-key",- "model": "doubao-embedding-vision-250615"+ "model": "doubao-embedding-vision-251215"}}}diff --git a/docs/zh/guides/02-volcengine-purchase-guide.md b/docs/zh/guides/02-volcengine-purchase-guide.mdindex b91e89dbb..4440a9e45 100644--- a/docs/zh/guides/02-volcengine-purchase-guide.md+++ b/docs/zh/guides/02-volcengine-purchase-guide.md@@ -9,7 +9,7 @@ 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-2-0-pro-260215` |-| Embedding | 向量化、语义检索 | `doubao-embedding-vision-250615` |+| Embedding | 向量化、语义检索 | `doubao-embedding-vision-251215` |## 前置条件@@ -84,7 +84,7 @@ OpenViking 需要以下模型服务:<img src="../../images/activate_emb_model.gif" width="80%"></div>-开通后使用模型 ID:`doubao-embedding-vision-250615`+开通后使用模型 ID:`doubao-embedding-vision-251215`## 配置 OpenViking@@ -134,7 +134,7 @@ 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-embedding-vision-250615` |+| `model` | string | 是 | 模型 ID,如 `doubao-embedding-vision-251215` || `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 || `dimension` | int | 是 | 向量维度,取决于模型(通常为 1024 或 768) || `input` | string | 否 | 输入类型:`"multimodal"`(多模态)或 `"text"`(纯文本),默认`"multimodal"` |@@ -157,7 +157,7 @@ OpenViking 需要以下模型服务:"dense": {"provider": "volcengine","api_key": "sk-1234567890abcdef1234567890abcdef",- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,"input": "multimodal"@@ -280,6 +280,6 @@ Error: Connection timeout| 模型名称 | 当前版本 | 发布日期 ||---------|---------|---------|| Doubao-Seed-1.8 | `doubao-seed-2-0-pro-260215` | 2025-12-28 |-| Doubao-Embedding-Vision | `doubao-embedding-vision-250615` | 2025-06-15 |+| Doubao-Embedding-Vision | `doubao-embedding-vision-251215` | 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/examples/cloud/GUIDE.md b/examples/cloud/GUIDE.mdindex df48a5626..1282ccc61 100644--- a/examples/cloud/GUIDE.md+++ b/examples/cloud/GUIDE.md@@ -80,7 +80,7 @@ AK/SK 同时用于 TOS 和 VikingDB 的鉴权。2. 左侧菜单 → **API Key 管理** → 创建 API Key3. 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-embedding-vision-251215`(多模态 Embedding)- `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`@@ -333,7 +333,7 @@ openviking:use_path_style: falseembedding:dense:- model: "doubao-embedding-vision-250615"+ model: "doubao-embedding-vision-251215"api_key: "your-ark-api-key"api_base: "https://ark.cn-beijing.volces.com/api/v3"dimension: 1024@@ -604,7 +604,7 @@ sudo systemctl start docker### Embedding 模型调用失败-- **模型未开通**:在方舟控制台 **模型广场** 中确认 `doubao-embedding-vision-250615` 已申请并通过+- **模型未开通**:在方舟控制台 **模型广场** 中确认 `doubao-embedding-vision-251215` 已申请并通过- **API Key 错误**:确认 `embedding.dense.api_key` 填写正确- **API Base 错误**:确认为 `https://ark.cn-beijing.volces.com/api/v3`diff --git a/examples/cloud/ov.conf.example b/examples/cloud/ov.conf.exampleindex 97ff69792..c6bd98189 100644--- a/examples/cloud/ov.conf.example+++ b/examples/cloud/ov.conf.example@@ -34,7 +34,7 @@},"embedding": {"dense": {- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_key": "<your-ark-api-key>","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,diff --git a/examples/k8s-helm/README.md b/examples/k8s-helm/README.mdindex 69033cd84..03dda0b24 100644--- a/examples/k8s-helm/README.md+++ b/examples/k8s-helm/README.md@@ -89,7 +89,7 @@ openviking:dense:api_key: "your-api-key-here"api_base: "https://ark.cn-beijing.volces.com/api/v3"- model: "doubao-embedding-vision-250615"+ model: "doubao-embedding-vision-251215"```### VLM Configurationdiff --git a/examples/k8s-helm/README_CN.md b/examples/k8s-helm/README_CN.mdindex b3c7db600..c6e6d2324 100644--- a/examples/k8s-helm/README_CN.md+++ b/examples/k8s-helm/README_CN.md@@ -89,7 +89,7 @@ openviking:dense:api_key: "your-api-key-here"api_base: "https://ark.cn-beijing.volces.com/api/v3"- model: "doubao-embedding-vision-250615"+ model: "doubao-embedding-vision-251215"```### VLM 配置diff --git a/examples/k8s-helm/values.yaml b/examples/k8s-helm/values.yamlindex 792d992eb..ab3655066 100644--- a/examples/k8s-helm/values.yaml+++ b/examples/k8s-helm/values.yaml@@ -25,7 +25,7 @@ openviking:config:embedding:dense:- model: "doubao-embedding-vision-250615"+ model: "doubao-embedding-vision-251215"api_key: nullapi_base: "https://ark.cn-beijing.volces.com/api/v3"dimension: "1024"diff --git a/examples/multi_tenant/ov.conf.example b/examples/multi_tenant/ov.conf.exampleindex 0ed595599..4da5105ad 100644--- a/examples/multi_tenant/ov.conf.example+++ b/examples/multi_tenant/ov.conf.example@@ -18,7 +18,7 @@},"embedding": {"dense": {- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_key": "{your-api-key}","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,diff --git a/examples/ov.conf.example b/examples/ov.conf.exampleindex 456c995d5..4769db20e 100644--- a/examples/ov.conf.example+++ b/examples/ov.conf.example@@ -35,7 +35,7 @@},"embedding": {"dense": {- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_key": "{your-api-key}","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,diff --git a/examples/skills/ov-server-operate/SKILL.md b/examples/skills/ov-server-operate/SKILL.mdindex 03a7d4811..1d5693cb6 100644--- a/examples/skills/ov-server-operate/SKILL.md+++ b/examples/skills/ov-server-operate/SKILL.md@@ -60,7 +60,7 @@ Note 2: Replace the root_api_key with your own root-api-key. Ask the user to set},"embedding": {"dense": {- "model": "doubao-embedding-vision-250615",+ "model": "doubao-embedding-vision-251215","api_key": "your-volcengine-api-key","api_base": "https://ark.cn-beijing.volces.com/api/v3","dimension": 1024,diff --git a/openviking/eval/datasets/local_doc_example_glm5.jsonl b/openviking/eval/datasets/local_doc_example_glm5.jsonlindex 0c4516cde..9d731f54e 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-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": "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-251215\",\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_cli/setup_wizard.py b/openviking_cli/setup_wizard.pyindex e25281e10..9a348105e 100644--- a/openviking_cli/setup_wizard.py+++ b/openviking_cli/setup_wizard.py@@ -275,12 +275,20 @@ class CloudProvider:CLOUD_PROVIDERS: list[CloudProvider] = [CloudProvider(- "OpenAI", "openai", "https://api.openai.com/v1",- "text-embedding-3-small", 1536, "gpt-4o-mini",+ "OpenAI",+ "openai",+ "https://api.openai.com/v1",+ "text-embedding-3-small",+ 1536,+ "gpt-4o-mini",),CloudProvider(- "Volcengine (Doubao)", "volcengine", "https://ark.cn-beijing.volces.com/api/v3",- "doubao-embedding-vision-250615", 1024, "doubao-seed-2-0-pro-260215",+ "Volcengine (Doubao)",+ "volcengine",+ "https://ark.cn-beijing.volces.com/api/v3",+ "doubao-embedding-vision-251215",+ 1024,+ "doubao-seed-2-0-pro-260215",),]@@ -368,8 +376,9 @@ def _write_config(config_dict: dict[str, Any], config_path: Path) -> bool:backup = config_path.with_suffix(".conf.bak")config_path.rename(backup)print(f" {_dim('Existing config backed up to ' + str(backup))}")- config_path.write_text(json.dumps(config_dict, indent=2, ensure_ascii=False) + "\n",- encoding="utf-8")+ config_path.write_text(+ json.dumps(config_dict, indent=2, ensure_ascii=False) + "\n", encoding="utf-8"+ )return Trueexcept OSError as exc:print(f" {_red(f'Failed to write config: {exc}')}")@@ -408,10 +417,12 @@ def _wizard_ollama() -> dict[str, Any] | None:avail = ""if ollama_running and is_model_available(p.model, available_models):avail = _green(" [downloaded]")- embed_options.append((- f"{p.label}",- f"({p.dimension}d, {p.size_hint}){avail}{rec}",- ))+ embed_options.append(+ (+ f"{p.label}",+ f"({p.dimension}d, {p.size_hint}){avail}{rec}",+ )+ )embed_choice = _prompt_choice("Embedding model:", embed_options, default=rec_embed_idx + 1)embedding = EMBEDDING_PRESETS[embed_choice - 1]@@ -421,7 +432,9 @@ def _wizard_ollama() -> dict[str, Any] | None:if _prompt_confirm(f"'{embedding.model}' not found locally. Pull now?"):print()if not ollama_pull_model(embedding.model):- print(f" {_yellow('Pull failed. You can pull it later: ollama pull ' + embedding.model)}")+ print(+ f" {_yellow('Pull failed. You can pull it later: ollama pull ' + embedding.model)}"+ )else:print(f" {_green('OK')} {embedding.model} pulled successfully")@@ -432,10 +445,12 @@ def _wizard_ollama() -> dict[str, Any] | None:avail = ""if ollama_running and is_model_available(p.ollama_model, available_models):avail = _green(" [downloaded]")- vlm_options.append((- f"{p.label}",- f"({p.size_hint}){avail}{rec}",- ))+ vlm_options.append(+ (+ f"{p.label}",+ f"({p.size_hint}){avail}{rec}",+ )+ )vlm_choice = _prompt_choice("Language model (VLM):", vlm_options, default=rec_vlm_idx + 1)vlm = VLM_PRESETS[vlm_choice - 1]@@ -445,7 +460,9 @@ def _wizard_ollama() -> dict[str, Any] | None:if _prompt_confirm(f"'{vlm.ollama_model}' not found locally. Pull now?"):print()if not ollama_pull_model(vlm.ollama_model):- print(f" {_yellow('Pull failed. You can pull it later: ollama pull ' + vlm.ollama_model)}")+ print(+ f" {_yellow('Pull failed. You can pull it later: ollama pull ' + vlm.ollama_model)}"+ )else:print(f" {_green('OK')} {vlm.ollama_model} pulled successfully")@@ -494,9 +511,15 @@ def _wizard_cloud() -> dict[str, Any] | None:workspace = _prompt_input("Workspace", default=_DEFAULT_WORKSPACE)return _build_cloud_config(- provider, embedding_api_key, embedding_model, embedding_dim,- vlm_api_key, vlm_model, workspace,- embedding_api_base, vlm_api_base,+ provider,+ embedding_api_key,+ embedding_model,+ embedding_dim,+ vlm_api_key,+ vlm_model,+ workspace,+ embedding_api_base,+ vlm_api_base,)@@ -514,8 +537,9 @@ def _wizard_custom() -> dict[str, Any] | None:if not _DEFAULT_CONFIG_PATH.exists():# Copy example as starting pointtry:- _DEFAULT_CONFIG_PATH.write_text(example.read_text(encoding="utf-8"),- encoding="utf-8")+ _DEFAULT_CONFIG_PATH.write_text(+ example.read_text(encoding="utf-8"), encoding="utf-8"+ )except OSError:passsubprocess.run([editor, str(_DEFAULT_CONFIG_PATH)], check=False)@@ -542,11 +566,15 @@ def run_init() -> int:return 0# Deployment mode- mode = _prompt_choice("Choose setup mode:", [- ("Local models via Ollama", "(recommended for macOS / Apple Silicon)"),- ("Cloud API", "(OpenAI, Volcengine, etc.)"),- ("Custom", "(manual editing)"),- ], default=1)+ mode = _prompt_choice(+ "Choose setup mode:",+ [+ ("Local models via Ollama", "(recommended for macOS / Apple Silicon)"),+ ("Cloud API", "(OpenAI, Volcengine, etc.)"),+ ("Custom", "(manual editing)"),+ ],+ default=1,+ )config_dict: dict[str, Any] | None = None@@ -568,7 +596,9 @@ def run_init() -> int:ws = config_dict.get("storage", {}).get("workspace", _DEFAULT_WORKSPACE)print(f"\n {_bold('Summary:')}")- print(f" Embedding: {emb.get('provider', '')} / {emb.get('model', '')} ({emb.get('dimension', '')}d)")+ print(+ f" Embedding: {emb.get('provider', '')} / {emb.get('model', '')} ({emb.get('dimension', '')}d)"+ )print(f" VLM: {vlm.get('provider', '')} / {vlm.get('model', '')}")print(f" Workspace: {ws}")print(f" Config: {_DEFAULT_CONFIG_PATH}")diff --git a/tests/models/test_embedding_telemetry_usage.py b/tests/models/test_embedding_telemetry_usage.pyindex 12a0168de..d268361d1 100644--- a/tests/models/test_embedding_telemetry_usage.py+++ b/tests/models/test_embedding_telemetry_usage.py@@ -56,7 +56,7 @@ def test_volcengine_dense_embedder_reports_embedding_telemetry_usage(monkeypatchtelemetry = MemoryOperationTelemetry(operation="resources.add_resource", enabled=True)with bind_telemetry(telemetry):embedder = VolcengineDenseEmbedder(- model_name="doubao-embedding-vision-250615",+ model_name="doubao-embedding-vision-251215",api_key="test",input_type="multimodal",dimension=3,@@ -92,7 +92,7 @@ def test_volcengine_dense_embedder_reports_embedding_telemetry_usage_from_dict_utelemetry = MemoryOperationTelemetry(operation="search.find", enabled=True)with bind_telemetry(telemetry):embedder = VolcengineDenseEmbedder(- model_name="doubao-embedding-vision-250615",+ model_name="doubao-embedding-vision-251215",api_key="test",input_type="multimodal",dimension=3,