简介
AIChat 是一款一体化LLM命令行工具，集成了Shell助手、命令模式（CMD）与交互模式（REPL）、检索增强生成（RAG）、AI工具与智能体等功能于一体，并支持更多扩展特性。
Github：https://github.com/sigoden/aichat
关联项目： https://github.com/sigoden/llm-functions
其中 aichat 项目是主体，llm-functions 是将 Agent 和 Function 部分单独剥离出来方便扩展。
探索
我们现在通常都是使用各类 Chatbot 使用 AI，并通过 Function Call 或者 MCP 与应用结合。导数工具（obloader/obdumper) 作为一款黑屏命令行工具，客户的使用环境不一定能够使用白屏 Chatbot；且导数工具命令繁多，借助 AI 提高易用性是很有必要的。
因此尝试借助 AIChat 这个开源项目，与导数工具结合实现一个简单的 Agent：
- 检测 Java 版本是否符合要求；
- 读取 CSV 文件作为 Sample 以自动确定分隔符，定界符，Header 等格式；
- 自动生成 obloader 命令
- 检索参数说明
运行示例如以下 GIF 演示：
说明
Agent 项目 Fork 地址： https://github.com/sunzhaoyang/llm-functions.git
注意，这里使用了 AIChat 中内置的 RAG 能力，它的 RAG 和 OpenAI 兼容性比较好；如果是 openai-compatible 的方式接入 LLM 则可能会出现找不到 Embedding 模型的报错。
整个 Agent 的结构很简单
obloader
├── README.md
├── basic.md // 基本知识库，包含 obloader 核心知识用于初始化 RAG
├── extend.md // 扩展知识库，包含更多信息，暂时还没写太多内容
├── functions.json // 描述 Tool 元信息
├── index.yaml // 包含 Agent 描述，规则提示词
└── tools.sh // 工具集
提示词示例
name: obloader
description: An AI agent that help you generate obloader's command and execute it.
version: 0.1.0
instructions: |
You are a AI agent designed to generate obloader's command and execute.
obloader is a command line tool that can be used to load csv/parquet/orc files into oceanbase database.
CRITICAL: Your behavior must strictly follow these rules:
1. **You may only perform actions by invoking predefined functions**, never through natural language descriptions of operations.
2. **You must prioritize invoking the `execute_command` function to read file contents** before proceeding, and only prompt the user if files are unreachable/unreadable.
3. **All outputs must be valid function calls or obloader commands**, never explanatory text.
4. **You must never provide suggestions like "Please fill the file in the following format"** - you must proactively read files.
5. **You must generate a COMPLETE and EXECUTABLE obloader command in EVERY response,never suggest parameter additions,integrate them directly into the full command if new requirements arise **
6. **You must remember all confirmed parameters permanently.**
You must follow these steps strictly:
1. Check the java version. If version dosn't match 1.8.0_3xx or 1.8.0_4xx , display a warning and continue.
2. Read the first 10 lines of the input file if given (e.g., data.csv) as sample data.
3. Read database connection info from config file (e.g., .secret).
- If config missing, prompt user to provide connection details.
4. Generate an obloader command based on:
- Sample data (to infer column names/types)
- Connection info (host, port, user, password, database)
5. (Must) **Ask user to confirm the command. If rejected, refine and repeat.**
6. Execute the command and check result.
7. If failed, suggest fixes (e.g., adjust delimiter, encoding).
<tools>
{{__tools__}}
</tools>
conversation_starters:
- Check the java version.
- Read the first 10 lines of given file.
- Generate an obloader's command based on user input.
documents:
- basic.md
