llms.txt@site/public · git:20261117.a961be8 · 2026-11-17 · sha256 23bca86f317b58e8
llms.txt@site/public git:20261117.a961be8A
Immutable. This exact content never changes and is served at /api/v1/blob/23bca86f317b58e8.
# AVA - AI-native Visual Analytics > AVA is an AntV TypeScript framework for loading data, answering natural-language questions, and generating visualizations through an SDK, CLI, or Agent Skill. This documentation covers AVA 4.0. Install `@antv/ava@4` with Node.js 22.13.0 or later. Use `@antv/ava` in Node.js and `@antv/ava/browser` in browsers. The core workflow is `source()` → `analyze()` → `visualize()`. `source()` replaces the current dataset and returns no value; use `schema()` to inspect it and `profile()` for statistics. Use `suggest()` to discover questions, `translate()` and `query()` to control query execution, or `recommend()` and `viz()` to control chart generation. Always await `dispose()` when finished. DuckDB is the default Node.js engine. JavaScript supports browsers and Node.js; Python, Supabase, ClickHouse, and Snowflake provide additional Node.js execution options. Follow the linked guides for source support, configuration, and complete API signatures. ## Get started - [Introduction](https://ava.antv.vision/documentation/): Core workflow and ways to use AVA. - [Installation and quickstart](https://ava.antv.vision/documentation/quickstart/): Install AVA 4.0, configure a model, and run a complete Node.js example. - [Agent Skill](https://ava.antv.vision/documentation/agent-skill/): Install AVA's agent skill and analyze data with an AI coding agent. - [Command-line interface](https://ava.antv.vision/documentation/reference/cli/): Inspect datasets, run queries, and render charts using persistent local sessions. ## Data, analysis, and visualization - [Data sources](https://ava.antv.vision/documentation/data/sources/): Source types and parameters for inline data, files, and databases. - [Lark Base setup](https://ava.antv.vision/documentation/data/online-services/feishu-bitable/): Illustrated app creation, permissions, document access, credential binding, CLI / SDK examples, and troubleshooting for Lark Base. - [Tencent Docs SmartSheet](https://ava.antv.vision/documentation/data/online-services/tencent-smartsheet/): Credentials and connection options for reading fields and records. - [GitHub](https://ava.antv.vision/documentation/data/online-services/github/): Available issue and pull request data, and connection options. - [Inspect your data](https://ava.antv.vision/documentation/data/schema/): AVA discovers the structural starting point automatically; optionally compute statistics, then supply business meaning through semantic definitions. No schema needs to be authored for ordinary use. - [Define data semantics](https://ava.antv.vision/documentation/data/semantic/): Author business context, model and column mappings, relationships, views, and cubes; includes a worked sales example and links to the complete API fields. Definitions guide query generation and do not materialize objects or enforce access policies. - [Analyze data](https://ava.antv.vision/documentation/analysis/overview/): Ask questions, get suggestions, and translate or execute queries separately. - [Analysis strategies](https://ava.antv.vision/documentation/analysis/strategies/): Choose direct analysis or iterative reasoning. - [Generate visualizations](https://ava.antv.vision/documentation/visualization/overview/): Recommend charts and generate GPT-Vis syntax and HTML. ## Configuration and execution engines - [Model configuration](https://ava.antv.vision/documentation/configuration/): Configure an OpenAI-compatible provider, AI Gateway, or an AI SDK model. - [Browser usage](https://ava.antv.vision/documentation/browser/): Use the browser entry point and JavaScript engine with inline data. - [Engine overview](https://ava.antv.vision/documentation/engines/overview/): Compare execution environments, query languages, and supported sources. - [DuckDB](https://ava.antv.vision/documentation/engines/duckdb/): Run SQL against inline data, files, and attached databases. - [JavaScript](https://ava.antv.vision/documentation/engines/javascript/): Execute JavaScript against an in-memory dataset. - [Python](https://ava.antv.vision/documentation/engines/python/): Analyze with pandas using local Python or an application-provided executor. - [Supabase, ClickHouse, and Snowflake](https://ava.antv.vision/documentation/engines/remote/): Discover schemas and execute queries in remote databases. - [Custom engines](https://ava.antv.vision/documentation/engines/custom/): Implement and register a custom analysis engine. ## API reference - [AVA API](https://ava.antv.vision/documentation/reference/api/): Constructor options, method signatures, parameters, defaults, return values, and complete semantic fields and merge rules. - [Events and lifecycle](https://ava.antv.vision/documentation/reference/events/): Observe source loading, model work, query execution, and cleanup. ## Optional - [Architecture and source map](https://ava.antv.vision/documentation/reference/architecture/): Map public capabilities to implementation modules. - [Benchmarks](https://ava.antv.vision/documentation/reference/benchmarks/): Evaluation results and instructions for reproducing them. - [AI](https://ava.antv.vision/ai/): Try browser-based visual analytics. - [GitHub repository](https://github.com/antvis/AVA): Source code and contribution information. - [Issues](https://github.com/antvis/AVA/issues): Bug reports and feature requests. ## 中文文档 中文首页:https://ava.antv.vision/zh/ 。英文 URL 保持不变,中文文档使用 /zh/documentation/。 - [认识 AVA](https://ava.antv.vision/zh/documentation/): 从一个问题开始,了解 AVA 如何连接数据、执行分析并呈现结果。 - [Agent Skill](https://ava.antv.vision/zh/documentation/agent-skill/): 让现有 AI Agent 用上 AVA,完成从数据探索到图表交付的完整流程。 - [安装与快速开始](https://ava.antv.vision/zh/documentation/quickstart/): 安装 AVA,接入第一份数据,跑通分析与图表生成。 - [接入数据](https://ava.antv.vision/zh/documentation/data/sources/): 连接内存数据、文件、数据库和飞书多维表格。 - [飞书多维表格配置](https://ava.antv.vision/zh/documentation/data/online-services/feishu-bitable/): 图文介绍应用创建、权限授权、凭证绑定、CLI / SDK 加载验证与常见问题。 - [腾讯文档智能表格](https://ava.antv.vision/zh/documentation/data/online-services/tencent-smartsheet/): 读取字段和记录所需的凭证和连接参数。 - [GitHub](https://ava.antv.vision/zh/documentation/data/online-services/github/): 可读取的 Issue 和 Pull Request 数据及连接参数。 - [了解你的数据](https://ava.antv.vision/zh/documentation/data/schema/): 自动发现表结构,按需查看统计信息,再补充业务背景。 - [补充业务语义](https://ava.antv.vision/zh/documentation/data/semantic/): 说明业务口径、字段映射与可复用指标,让分析更贴近实际业务。 - [分析数据](https://ava.antv.vision/zh/documentation/analysis/overview/): 用自然语言提问,获得可检查的查询结果与分析结论。 - [选择分析策略](https://ava.antv.vision/zh/documentation/analysis/strategies/): 根据问题复杂度,选择直接分析或多步迭代。 - [生成图表](https://ava.antv.vision/zh/documentation/visualization/overview/): 把分析结果或已有数据转换成合适的图表。 - [连接模型](https://ava.antv.vision/zh/documentation/configuration/): 配置兼容 OpenAI 的服务、AI Gateway 或 AI SDK 模型。 - [在浏览器中使用](https://ava.antv.vision/zh/documentation/browser/): 通过浏览器入口使用 JavaScript 引擎,避免引入 Node.js 依赖。 - [选择执行引擎](https://ava.antv.vision/zh/documentation/engines/overview/): 决定数据在哪里加载、查询用什么语言、代码在哪里执行。 - [DuckDB](https://ava.antv.vision/zh/documentation/engines/duckdb/): 用 SQL 分析内存数据、文件及可连接的数据库。 - [Python](https://ava.antv.vision/zh/documentation/engines/python/): 通过本地 Python 或自定义执行器,使用 pandas 分析数据。 - [Supabase 与 ClickHouse](https://ava.antv.vision/zh/documentation/engines/remote/): 在远程数据库中发现表结构、执行查询。 - [JavaScript](https://ava.antv.vision/zh/documentation/engines/javascript/): 在 Node.js 或浏览器中,对内存数据执行 JavaScript 分析。 - [扩展执行引擎](https://ava.antv.vision/zh/documentation/engines/custom/): 实现引擎接口,把自己的数据与执行环境接入 AVA。 - [API 参考](https://ava.antv.vision/zh/documentation/reference/api/): 查询构造参数、方法签名、默认值与返回结构。 - [事件与生命周期](https://ava.antv.vision/zh/documentation/reference/events/): 观察数据加载、模型调用、查询执行与资源清理。 - [命令行工具](https://ava.antv.vision/zh/documentation/reference/cli/): 在终端中加载数据、查询分析、生成图表,并复用本地会话。 - [评测结果](https://ava.antv.vision/zh/documentation/reference/benchmarks/): 了解数据上下文与分析策略的评测方法、结果及复现方式。 - [架构与源码导航](https://ava.antv.vision/zh/documentation/reference/architecture/): 从公开 API 出发,找到对应的实现与扩展位置。 ## Blog - [AVA Blog](https://ava.antv.vision/blog/): Practical guides, engineering ideas, and product updates. - [AVA 中文 Blog](https://ava.antv.vision/zh/blog/): 应用实践、技术思考与产品进展。 - [用 AVA 构建 Mini Data Agent](https://ava.antv.vision/zh/blog/mini-data-agent/): 第一篇中文实践教程,从销售数据出发,搭建支持分析、追问与图表生成的数据助手。 - [Build a Mini Data Agent with AVA](https://ava.antv.vision/blog/mini-data-agent/): Build a data assistant with AVA and the AI SDK, including business semantics, analysis tools, charts, and follow-up questions. - [AVA 4.0 发布](https://ava.antv.vision/zh/blog/ava-4-release/): 面向 AI Agent 的数据分析与可视化框架,介绍统一数据上下文、多源接入、分析执行与图表生成。 - [AVA 4.0 Release](https://ava.antv.vision/blog/ava-4-release/): Data context, heterogeneous sources, visualization, verifiable analysis, and integration options for AI agents.