diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.md index b44dab58..48125c94 100644 --- a/docs/en/guides/01-configuration.md +++ b/docs/en/guides/01-configuration.md @@ -306,7 +306,16 @@ If rerank is not configured, search uses vector similarity only. ### storage -Storage backend configuration. +Storage configuration for context data, including file storage (AGFS) and vector database storage (VectorDB). + +#### Root Configuration + +| Parameter | Type | Description | Default | +|-----------|------|-------------|---------| +| `workspace` | str | Local data storage path (main configuration) | "./data" | +| `agfs` | object | AGFS configuration | {} | +| `vectordb` | object | Vector database storage configuration | {} | + ```json { @@ -329,9 +338,9 @@ Storage backend configuration. |-----------|------|-------------|---------| | `mode` | str | `"http-client"` or `"binding-client"` | `"http-client"` | | `backend` | str | `"local"`, `"s3"`, or `"memory"` | `"local"` | -| `path` | str | Local directory path for `local` backend | `"./data"` | | `url` | str | AGFS service URL for `http-client` mode | `"http://localhost:1833"` | | `timeout` | float | Request timeout in seconds | `10.0` | +| `s3` | object | S3 backend configuration (when backend is 's3') | - | **Configuration Examples** @@ -365,8 +374,7 @@ Directly uses the AGFS Go implementation through a shared library. "storage": { "agfs": { "mode": "binding-client", - "backend": "local", - "path": "./data" + "backend": "local" } } } @@ -374,7 +382,25 @@ Directly uses the AGFS Go implementation through a shared library. -**S3 Backend** + +##### S3 Backend Configuration + +| Parameter | Type | Description | Default | +|-----------|------|-------------|---------| +| `bucket` | str | S3 bucket name | null | +| `region` | str | AWS region where the bucket is located (e.g., us-east-1, cn-beijing) | null | +| `access_key` | str | S3 access key ID | null | +| `secret_key` | str | S3 secret access key corresponding to the access key ID | null | +| `endpoint` | str | Custom S3 endpoint URL, required for S3-compatible services like MinIO or LocalStack | null | +| `prefix` | str | Optional key prefix for namespace isolation | "" | +| `use_ssl` | bool | Enable/disable SSL (HTTPS) for S3 connections | true | +| `use_path_style` | bool | true for PathStyle used by MinIO and some S3-compatible services; false for VirtualHostStyle used by TOS and some S3-compatible services | true | + + + +
+PathStyle S3 +Supports S3 storage in PathStyle mode, such as MinIO, SeaweedFS. ```json { @@ -392,9 +418,82 @@ Directly uses the AGFS Go implementation through a shared library. } } ``` +
+ + +
+VirtualHostStyle S3 +Supports S3 storage in VirtualHostStyle mode, such as TOS. + +```json +{ + "storage": { + "agfs": { + "backend": "s3", + "s3": { + "bucket": "my-bucket", + "endpoint": "s3.amazonaws.com", + "region": "us-east-1", + "access_key": "your-ak", + "secret_key": "your-sk", + "use_path_style": false + } + } + } +} +``` + +
+ #### vectordb +Vector database storage configuration + +| Parameter | Type | Description | Default | +|-----------|------|-------------|---------| +| `backend` | str | VectorDB backend type: 'local' (file-based), 'http' (remote service), 'volcengine' (cloud VikingDB), or 'vikingdb' (private deployment) | "local" | +| `name` | str | VectorDB collection name | "context" | +| `url` | str | Remote service URL for 'http' type (e.g., 'http://localhost:5000') | null | +| `project_name` | str | Project name (alias project) | "default" | +| `distance_metric` | str | Distance metric for vector similarity search (e.g., 'cosine', 'l2', 'ip') | "cosine" | +| `dimension` | int | Vector embedding dimension | 0 | +| `sparse_weight` | float | Sparse weight for hybrid vector search, only effective when using hybrid index | 0.0 | +| `volcengine` | object | 'volcengine' type VikingDB configuration | - | +| `vikingdb` | object | 'vikingdb' type private deployment configuration | - | + +Default local mode +``` +{ + "storage": { + "vectordb": { + "backend": "local" + } + } +} +``` + +
+volcengine vikingDB +Supports cloud-deployed VikingDB on Volcengine + +```json +{ + "storage": { + "vectordb": { + "name": "context", + "backend": "volcengine", + "project": "default", + "volcengine": { + "region": "cn-beijing", + "ak": "your-access-key", + "sk": "your-secret-key" + } + } +} +``` +
+ ## Config Files @@ -560,7 +659,7 @@ Volcengine has rate limits. Consider batch processing with delays or upgrading y ## Related Documentation -- [Volcengine Purchase Guide](./volcengine-purchase-guide.md) - API key setup +- [Volcengine Purchase Guide](./02-volcengine-purchase-guide.md) - API key setup - [API Overview](../api/01-overview.md) - Client initialization - [Server Deployment](./03-deployment.md) - Server configuration - [Context Layers](../concepts/03-context-layers.md) - L0/L1/L2 diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.md index e8376043..e525951b 100644 --- a/docs/zh/guides/01-configuration.md +++ b/docs/zh/guides/01-configuration.md @@ -313,7 +313,16 @@ OpenViking 使用 JSON 配置文件（`ov.conf`）进行设置。配置文件支 ### storage -存储后端配置。 +用于存储上下文数据 ，包括文件存储（AGFS）和向量库存储（VectorDB）。 + +#### 根级配置 + +| 参数 | 类型 | 说明 | 默认值 | +|------|------|------|--------| +| `workspace` | str | 本地数据存储路径（主要配置） | "./data" | +| `agfs` | object | agfs 配置 | {} | +| `vectordb` | object | 向量库存储配置 | {} | + ```json { @@ -336,9 +345,10 @@ OpenViking 使用 JSON 配置文件（`ov.conf`）进行设置。配置文件支 |------|------|------|--------| | `mode` | str | `"http-client"` 或 `"binding-client"` | `"http-client"` | | `backend` | str | `"local"`、`"s3"` 或 `"memory"` | `"local"` | -| `path` | str | `local` 后端的本地目录路径 | `"./data"` | | `url` | str | `http-client` 模式下的 AGFS 服务地址 | `"http://localhost:1833"` | | `timeout` | float | 请求超时时间（秒） | `10.0` | +| `s3` | object | S3 backend configuration (when backend is 's3') | - | + **配置示例** @@ -372,8 +382,7 @@ OpenViking 使用 JSON 配置文件（`ov.conf`）进行设置。配置文件支 "storage": { "agfs": { "mode": "binding-client", - "backend": "local", - "path": "./data" + "backend": "local" } } } @@ -381,7 +390,25 @@ OpenViking 使用 JSON 配置文件（`ov.conf`）进行设置。配置文件支 -**S3 后端** + +##### S3 后端配置 + +| 参数 | 类型 | 说明 | 默认值 | +|------|------|------|--------| +| `bucket` | str | S3 存储桶名称 | null | +| `region` | str | 存储桶所在的 AWS 区域（例如 us-east-1, cn-beijing） | null | +| `access_key` | str | S3 访问密钥 ID | null | +| `secret_key` | str | 与访问密钥 ID 对应的 S3 秘密访问密钥 | null | +| `endpoint` | str | 自定义 S3 端点 URL，对于 MinIO 或 LocalStack 等 S3 兼容服务是必需的 | null | +| `prefix` | str | 用于命名空间隔离的可选键前缀 | "" | +| `use_ssl` | bool | 为 S3 连接启用/禁用 SSL（HTTPS） | true | +| `use_path_style` | bool | true 表示对 MinIO 和某些 S3 兼容服务使用 PathStyle；false 表示对 TOS 和某些 S3 兼容服务使用 VirtualHostStyle | true | + + + +
+PathStyle S3 +支持 PathStyle 模式的 S3 存储， 如 MinIO、SeaweedFS. ```json { @@ -399,9 +426,84 @@ OpenViking 使用 JSON 配置文件（`ov.conf`）进行设置。配置文件支 } } ``` +
+ + +
+VirtualHostStyle S3 +支持 VirtualHostStyle 模式的 S3 存储， 如 TOS. + +```json +{ + "storage": { + "agfs": { + "backend": "s3", + "s3": { + "bucket": "my-bucket", + "endpoint": "s3.amazonaws.com", + "region": "us-east-1", + "access_key": "your-ak", + "secret_key": "your-sk", + "use_path_style": false + } + } + } +} +``` + +
+ #### vectordb +向量库存储的配置 + +| 参数 | 类型 | 说明 | 默认值 | +|------|------|------|--------| +| `backend` | str | VectorDB 后端类型: 'local'（基于文件）, 'http'（远程服务）, 'volcengine'（云上VikingDB）或 'vikingdb'（私有部署） | "local" | +| `name` | str | VectorDB 的集合名称 | "context" | +| `url` | str | 'http' 类型的远程服务 URL（例如 'http://localhost:5000'） | null | +| `project_name` | str | 项目名称（别名 project） | "default" | +| `distance_metric` | str | 向量相似度搜索的距离度量（例如 'cosine', 'l2', 'ip'） | "cosine" | +| `dimension` | int | 向量嵌入的维度 | 0 | +| `sparse_weight` | float | 混合向量搜索的稀疏权重，仅在使用混合索引时生效 | 0.0 | +| `volcengine` | object | 'volcengine' 类型的 VikingDB 配置 | - | +| `vikingdb` | object | 'vikingdb' 类型的私有部署配置 | - | + +默认使用本地模式 +``` +{ + "storage": { + "vectordb": { + "backend": "local" + } + } +} +``` + +
+volcengine vikingDB +支持火山引擎云上部署的 VikingDB + +```json +{ + "storage": { + "vectordb": { + "name": "context", + "backend": "volcengine", + "project": "default", + "volcengine": { + "region": "cn-beijing", + "ak": "your-access-key", + "sk": "your-secret-key" + } + } +} +``` +
+ + + ## 配置文件 OpenViking 使用两个配置文件：