Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions packages/cli/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,20 @@ Knowledge bases accrue running-time charges from creation, even without queries.

Keep the returned IDs and recovery record. Closing the CLI or a later failure does not stop billing; follow the reported cleanup actions to delete unused knowledge bases. See the [Knowledge Studio quick start](packages/kscli/README.md#quick-start) for retrieval and cleanup. The `bailian-knowledge` Skill is available through `bl skill init`.

### Console dataset and deployment queries

```bash
bl dataset groups --page 1 --page-size 10 --output json
bl dataset version --dataset-group-id <group-id> --output json
bl dataset version --dataset-id <version-id> --include-status --output json
bl file url --file-key <console-file-key> --output json
bl deploy instances --page 1 --page-size 10 --output json
```

Use `dataset groups` (`--name` optionally filters on the server) to obtain `records[].datasetGroupId`, then `dataset version --dataset-group-id <group-id>` to get `{result:[...]}` with `result[].datasetId` and its optional `fileId`. Use `dataset version --dataset-id <version-id>` for details; `--include-status` is available only in detail mode. Exactly one of `--dataset-group-id` and `--dataset-id` is required; they cannot be combined. `fileId` is not `datasetId` and must not be passed as a version ID. Groups fetch one page with one embedded version preview per group; `version --dataset-group-id` does not promise exhaustive results or expose pagination. The API Key / `file_id` semantics of `dataset list` are unchanged.

These read-only commands use Console authentication. An optional `--workspace-id` resolves the workspace's Console identity before querying; resolution failure stops the request. `dataset version --dataset-id` keeps metadata and version/task state separate and does not infer validation success or training readiness. `file url` only resolves a download address. `deploy instances` returns one page of independent services (`records` is the list, `items` the total), not capacity instances. The API-key `dataset get --file-id` and `deploy list` commands are unchanged. Add `--dry-run` to preview without business requests; framework update checks/telemetry follow their settings.

### RAG audio and video

`bl knowledge doc import --index-id <id> --doc-id <fileId>` imports an existing file into a knowledge base; `doc list --details` shows per-file processing settings. Media support includes parser options, streaming uploads, and media references in search/chunk output. Chat JSON separates the final answer from phases, tools, docs, usage, and raw events; quiet mode hides progress and informational messages while preserving the final result, including every JSON field. See the [command guide](docs/knowledge/knowledge-cli-guide.md).
Expand Down
14 changes: 14 additions & 0 deletions packages/cli/README.zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,20 @@ bl knowledge init --workspace-id <workspace-id> --dry-run

保留返回的 ID 和恢复记录。退出 CLI 或后续步骤失败不会停止计费;按返回的清理动作删除不再需要的知识库。检索及清理示例见 [Knowledge Studio 快速开始](packages/kscli/README.zh.md#快速开始)。知识库 Skill `bailian-knowledge` 通过 `bl skill init` 安装。

### Console 数据集与部署查询

```bash
bl dataset groups --page 1 --page-size 10 --output json
bl dataset version --dataset-group-id <组ID> --output json
bl dataset version --dataset-id <版本ID> --include-status --output json
bl file url --file-key <Console文件键> --output json
bl deploy instances --page 1 --page-size 10 --output json
```

先用 `dataset groups`(可加 `--name` 服务端筛选)获取 `records[].datasetGroupId`,再用 `dataset version --dataset-group-id <组ID>` 获取 `{result:[...]}`,其中包含 `result[].datasetId` 及可能返回的 `fileId`。查询详情用 `dataset version --dataset-id <版本ID>`,`--include-status` 仅详情模式可用。`--dataset-group-id` 与 `--dataset-id` 必选一个且不能同传。`fileId` 不是 `datasetId`,不能作为版本 ID 传入。组列表仅取一页,每组附带一条版本预览;`version --dataset-group-id` 不承诺返回全部版本,也不提供分页选项。原有 `dataset list` 的 API Key / `file_id` 语义保持不变。

以上只读命令使用 Console 鉴权。可选 `--workspace-id` 会在查询前解析对应空间的 Console 身份,解析失败即停止。`dataset version --dataset-id` 分开保留元信息与版本/任务状态,不推导校验成功或训练就绪;`file url` 仅解析下载地址;`deploy instances` 返回独立部署服务的单页数据(`records` 为列表、`items` 为总数),不是容量实例。原有 API Key 域的 `dataset get --file-id` 与 `deploy list` 保持不变。添加 `--dry-run` 可预览且不发送业务请求;框架更新检查和埋点遵循其配置。

### RAG 音视频接入

`bl knowledge doc import --index-id <id> --doc-id <fileId>` 将历史文件导入已有库;`doc list --details` 查看文件级处理参数。支持音视频 parser、流式上传,以及检索/切片中的媒体来源展示。问答 JSON 将最终 answer 与 phases/tools/docs/usage/events 分开保存,quiet 只隐藏进度和过程提示,保留最终结果及完整 JSON 字段。参阅 [命令指南](docs/knowledge/knowledge-cli-guide.md)。
Expand Down
Loading