grepai-quickstart

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

GrepAI Quickstart

GrepAI 快速入门

This skill provides a complete walkthrough to get GrepAI running and searching your code in 5 minutes.

本指南提供完整流程，帮助你在5分钟内启动GrepAI并搜索你的代码。

When to Use This Skill

何时使用本指南

First time using GrepAI
Need a quick refresher on basic workflow
Setting up GrepAI on a new project
Demonstrating GrepAI to someone

首次使用GrepAI
需要快速回顾基础工作流程
在新项目中配置GrepAI
向他人演示GrepAI

Prerequisites

前置要求

Terminal access
A code project to index

终端访问权限
一个需要索引的代码项目

Step 1: Install GrepAI

步骤1：安装GrepAI

macOS

bash

brew install yoanbernabeu/tap/grepai

bash

brew install yoanbernabeu/tap/grepai

Linux/macOS (Alternative)

Linux/macOS（替代方案）

bash

curl -sSL https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.sh | sh

bash

curl -sSL https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.sh | sh

Windows

powershell

irm https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.ps1 | iex

Verify:

grepai version

powershell

irm https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.ps1 | iex

验证：

grepai version

Step 2: Install Ollama (Local Embeddings)

步骤2：安装Ollama（本地嵌入模型）

macOS

bash

brew install ollama
ollama serve &
ollama pull nomic-embed-text

bash

brew install ollama
ollama serve &
ollama pull nomic-embed-text

Linux

bash

curl -fsSL https://ollama.com/install.sh | sh
ollama serve &
ollama pull nomic-embed-text

Verify:

curl http://localhost:11434/api/tags

bash

curl -fsSL https://ollama.com/install.sh | sh
ollama serve &
ollama pull nomic-embed-text

验证：

curl http://localhost:11434/api/tags

Step 3: Initialize Your Project

步骤3：初始化你的项目

Navigate to your project and initialize GrepAI:

bash

cd /path/to/your/project
grepai init

This creates

.grepai/config.yaml

with default settings:

Ollama as embedding provider
```
nomic-embed-text
```
model
GOB file storage
Standard ignore patterns

导航到你的项目并初始化GrepAI：

bash

cd /path/to/your/project
grepai init

这会创建

.grepai/config.yaml

文件，包含默认设置：

使用Ollama作为嵌入模型提供商
```
nomic-embed-text
```
模型
GOB文件存储
标准忽略规则

Step 4: Start Indexing

步骤4：开始索引

Start the watch daemon to index your code:

bash

grepai watch

What happens:

Scans all source files (respects
```
.gitignore
```
)
Chunks code into ~512 token segments
Generates embeddings via Ollama
Stores vectors in
```
.grepai/index.gob
```

First indexing output:

🔍 GrepAI Watch
   Scanning files...
   Found 245 files
   Processing chunks...
   ████████████████████████████████ 100%
   Indexed 1,234 chunks
   Watching for changes...

启动监控守护进程以索引你的代码：

bash

grepai watch

执行过程：

扫描所有源文件（遵循
```
.gitignore
```
规则）
将代码分割为约512个token的片段
通过Ollama生成嵌入向量
将向量存储在
```
.grepai/index.gob
```
中

首次索引输出示例：

🔍 GrepAI Watch
   Scanning files...
   Found 245 files
   Processing chunks...
   ████████████████████████████████ 100%
   Indexed 1,234 chunks
   Watching for changes...

Background Mode

后台模式

For long-running projects:

bash

undefined

针对长期运行的项目：

bash

undefined

Start in background

后台启动

grepai watch --background

Check status

检查状态

grepai watch --status

Stop when done

停止进程

grepai watch --stop

undefined

grepai watch --stop

undefined

Step 5: Search Your Code

步骤5：搜索你的代码

Now search semantically:

bash

undefined

现在进行语义搜索：

bash

undefined

Basic search

基础搜索

grepai search "authentication flow"

Limit results

限制结果数量

grepai search "error handling" --limit 5

JSON output for scripts

输出JSON格式用于脚本

grepai search "database queries" --json

undefined

grepai search "database queries" --json

undefined

Example Output

示例输出

Score: 0.89 | src/auth/middleware.go:15-45
──────────────────────────────────────────
func AuthMiddleware() gin.HandlerFunc {
    return func(c *gin.Context) {
        token := c.GetHeader("Authorization")
        if token == "" {
            c.AbortWithStatus(401)
            return
        }
        // Validate JWT token...
    }
}

Score: 0.82 | src/auth/jwt.go:23-55
──────────────────────────────────────────
func ValidateToken(tokenString string) (*Claims, error) {
    token, err := jwt.Parse(tokenString, func(t *jwt.Token) (interface{}, error) {
        return []byte(secretKey), nil
    })
    // ...
}

Score: 0.89 | src/auth/middleware.go:15-45
──────────────────────────────────────────
func AuthMiddleware() gin.HandlerFunc {
    return func(c *gin.Context) {
        token := c.GetHeader("Authorization")
        if token == "" {
            c.AbortWithStatus(401)
            return
        }
        // Validate JWT token...
    }
}

Score: 0.82 | src/auth/jwt.go:23-55
──────────────────────────────────────────
func ValidateToken(tokenString string) (*Claims, error) {
    token, err := jwt.Parse(tokenString, func(t *jwt.Token) (interface{}, error) {
        return []byte(secretKey), nil
    })
    // ...
}

Step 6: Analyze Call Graphs (Optional)

步骤6：分析调用图（可选）

Trace function relationships:

bash

undefined

追踪函数关系：

bash

undefined

Who calls this function?

哪些函数调用了该函数？

grepai trace callers "Login"

What does this function call?

该函数调用了哪些函数？

grepai trace callees "ProcessPayment"

Full dependency graph

完整依赖图

grepai trace graph "ValidateToken" --depth 3

undefined

grepai trace graph "ValidateToken" --depth 3

undefined

Complete Workflow Summary

完整工作流程总结

bash

undefined

bash

undefined

1. Install (once)

1. 安装（仅需一次）

brew install yoanbernabeu/tap/grepai brew install ollama && ollama serve & && ollama pull nomic-embed-text

2. Setup project (once per project)

2. 项目配置（每个项目仅需一次）

cd /your/project grepai init

3. Index (run in background)

3. 启动索引（后台运行）

grepai watch --background

4. Search (as needed)

4. 搜索（按需使用）

grepai search "your query here"

5. Trace (as needed)

5. 追踪（按需使用）

grepai trace callers "FunctionName"

undefined

grepai trace callers "FunctionName"

undefined

Quick Command Reference

快速命令参考

Command	Purpose
`grepai init`	Initialize project config
`grepai watch`	Start indexing daemon
`grepai watch --background`	Run daemon in background
`grepai watch --status`	Check daemon status
`grepai watch --stop`	Stop daemon
`grepai search "query"`	Semantic search
`grepai search --json`	JSON output
`grepai trace callers "fn"`	Find callers
`grepai trace callees "fn"`	Find callees
`grepai status`	Index statistics
`grepai version`	Show version

命令	用途
`grepai init`	初始化项目配置
`grepai watch`	启动索引守护进程
`grepai watch --background`	后台运行守护进程
`grepai watch --status`	检查守护进程状态
`grepai watch --stop`	停止守护进程
`grepai search "query"`	语义搜索
`grepai search --json`	输出JSON格式结果
`grepai trace callers "fn"`	查找调用方
`grepai trace callees "fn"`	查找被调用方
`grepai status`	查看索引统计信息
`grepai version`	显示版本信息

Search Tips

搜索技巧

Be descriptive, not literal:

✅ "user authentication and session management"
❌ "auth"

Describe intent:

✅ "where errors are logged to the console"
❌ "console.error"

Use English:

Models are trained primarily on English text
Works best with English queries

描述性而非字面化：

✅ "user authentication and session management"
❌ "auth"

描述意图：

✅ "where errors are logged to the console"
❌ "console.error"

使用英文：

模型主要基于英文文本训练
英文查询效果最佳

Next Steps

后续步骤

After mastering the basics:

Configure embeddings: See
```
grepai-embeddings-*
```
skills
Setup storage: See
```
grepai-storage-*
```
skills
Advanced search: See
```
grepai-search-*
```
skills
MCP integration: See
```
grepai-mcp-*
```
skills

掌握基础操作后：

配置嵌入模型： 查看
```
grepai-embeddings-*
```
相关指南
配置存储： 查看
```
grepai-storage-*
```
相关指南
高级搜索： 查看
```
grepai-search-*
```
相关指南
MCP集成： 查看
```
grepai-mcp-*
```
相关指南

Output Format

输出格式

Successful quickstart:

✅ GrepAI Quickstart Complete

   Project: /path/to/your/project
   Files indexed: 245
   Chunks created: 1,234
   Embedder: Ollama (nomic-embed-text)
   Storage: GOB (local file)

   Try these searches:
   - grepai search "main entry point"
   - grepai search "database connection"
   - grepai search "error handling"

快速入门成功完成后：

✅ GrepAI Quickstart Complete

   Project: /path/to/your/project
   Files indexed: 245
   Chunks created: 1,234
   Embedder: Ollama (nomic-embed-text)
   Storage: GOB (local file)

   Try these searches:
   - grepai search "main entry point"
   - grepai search "database connection"
   - grepai search "error handling"