
Byted Data Search
This is a Chinese industry data search tool that plugs into compliant public data sources covering enterprise registration info, supply chain metrics, and A-share stock data. You query it by first calling describe_datasource to see what fields exist, then constructing filters with the right operators for each field type. The workflow is strict: text fields need "like", keywords need "eq", and you'll hit errors if you mix them up. It's built for questions like "show me all specialized and sophisticated enterprises in the semiconductor chain" or "what's the regional distribution of new energy companies." The documentation is thorough about field types and includes a separate script to enumerate possible values before filtering, which saves you from guessing whether a status field uses "存续" or "在业". Requires Volcengine credentials.
- skills.sh installs
- 140
- GitHub stars
- 484
- last updated
- Aug 21, 2026
Install
$ npx -y skills add bytedance/agentkit-samples --skill byted-data-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
数据查询工具
前置要求
需要环境变量(脚本会自动读取,若读取不到需提醒用户设置):
VOLCENGINE_ACCESS_KEY(或VOLC_ACCESS_KEY)VOLCENGINE_SECRET_KEY(或VOLC_SECRET_KEY)
工作流程(严格按顺序执行)
第一步:查询可用数据源(必须先执行)
在构造任何查询之前,必须先调用此步骤了解有哪些数据源及其字段定义。这一步的作用是:确认用户需要的数据存在于哪个数据源中,以及该数据源有哪些字段和过滤规则。跳过这一步直接去猜字段名几乎一定会出错。
# 列出所有可用数据源摘要(含 datasource_id、名称、描述、维度/过滤字段数量)
python3 scripts/describe_datasource.py --datasource-id all
# 获取某个数据源的完整字段定义(维度 dimensions、字段类型、可用过滤操作符)
python3 scripts/describe_datasource.py --datasource-id <数据源ID>
返回内容包含:
datasource_id:数据源唯一标识datasource_name:数据源中文名称description:数据源说明dimensions:所有字段列表,每个字段包含 field(字段名)、label(显示名)、type(类型)、description(描述)、filterable(是否可作为过滤条件字段)notes:使用备注
关键:根据返回的字段信息(尤其是 field 名称和 type 类型),确定需要用到的字段和过滤操作符,再进入第二步。
字段类型与操作符对照表
每种字段类型只支持特定操作符。用错操作符会直接报错,所以在构造 filters 之前请务必对照此表。
| 字段类型 | 支持的操作符 | 说明 |
|---|---|---|
keyword | eq, in, not_in | 精确匹配类字段(如编码、状态、类型) |
text | like, keyword | 文本类字段(如名称、地址、描述),支持模糊搜索 |
date / datetime | between, eq | 日期类字段,范围查询用 between |
long / integer / float / double | range, eq | 数值类字段,范围查询用 range |
Sponsors
Details
- Repository
- github.com/bytedance/agentkit-samples
- First seen
- Jun 3, 2026