GrepAI Configuration Reference

GrepAI配置参考

This skill provides a complete reference for all GrepAI configuration options in

.grepai/config.yaml

.

此技能提供了

.grepai/config.yaml

中所有GrepAI配置选项的完整参考。

When to Use This Skill

何时使用此技能

Understanding all available configuration options
Optimizing GrepAI for your specific use case
Troubleshooting configuration issues
Setting up advanced configurations

了解所有可用配置选项
根据你的特定用例优化GrepAI
排查配置问题
设置高级配置

Configuration File Location

配置文件位置

/your/project/.grepai/config.yaml

/your/project/.grepai/config.yaml

Complete Configuration Schema

完整配置 Schema

yaml

version: 1

yaml

version: 1

═══════════════════════════════════════════════════════════════

EMBEDDER CONFIGURATION

嵌入模型配置

Converts code text into vector embeddings

将代码文本转换为向量嵌入

═══════════════════════════════════════════════════════════════

embedder:

Provider: ollama | openai | lmstudio

provider: ollama

Model name (depends on provider)

Ollama: nomic-embed-text, bge-m3, mxbai-embed-large

OpenAI: text-embedding-3-small, text-embedding-3-large

LM Studio: nomic-embed-text-v1.5, bge-small-en-v1.5

model: nomic-embed-text

API endpoint URL

Ollama default: http://localhost:11434

LM Studio default: http://localhost:1234

OpenAI: uses official API

endpoint: http://localhost:11434

Vector dimensions (auto-detected if omitted)

nomic-embed-text: 768

text-embedding-3-small: 1536

text-embedding-3-large: 3072

dimensions: 768

API key (for OpenAI, supports env vars)

api_key: ${OPENAI_API_KEY}

Parallel requests (OpenAI only, for speed)

parallelism: 4

embedder:

提供商: ollama | openai | lmstudio

provider: ollama

模型名称（取决于提供商）

Ollama: nomic-embed-text, bge-m3, mxbai-embed-large

OpenAI: text-embedding-3-small, text-embedding-3-large

LM Studio: nomic-embed-text-v1.5, bge-small-en-v1.5

model: nomic-embed-text

API端点URL

Ollama默认值: http://localhost:11434

LM Studio默认值: http://localhost:1234

OpenAI: 使用官方API

endpoint: http://localhost:11434

向量维度（省略时自动检测）

nomic-embed-text: 768

text-embedding-3-small: 1536

text-embedding-3-large: 3072

dimensions: 768

API密钥（适用于OpenAI，支持环境变量）

api_key: ${OPENAI_API_KEY}

并行请求数（仅OpenAI支持，提升速度）

parallelism: 4

═══════════════════════════════════════════════════════════════

STORE CONFIGURATION

存储配置

Where vector embeddings are stored

向量嵌入的存储位置

═══════════════════════════════════════════════════════════════

store:

Backend: gob | postgres | qdrant

backend: gob

PostgreSQL configuration (when backend: postgres)

postgres: dsn: postgres://user:password@localhost:5432/grepai

Qdrant configuration (when backend: qdrant)

qdrant: endpoint: localhost port: 6334 use_tls: false api_key: your-qdrant-api-key # Optional

store:

后端存储: gob | postgres | qdrant

backend: gob

PostgreSQL配置（当backend为postgres时）

postgres: dsn: postgres://user:password@localhost:5432/grepai

Qdrant配置（当backend为qdrant时）

qdrant: endpoint: localhost port: 6334 use_tls: false api_key: your-qdrant-api-key # 可选

═══════════════════════════════════════════════════════════════

CHUNKING CONFIGURATION

代码分块配置

How code files are split for embedding

代码文件如何拆分以进行嵌入

═══════════════════════════════════════════════════════════════

chunking:

Tokens per chunk (smaller = more precise, larger = more context)

Recommended: 256-1024

size: 512

Overlap between chunks (preserves context at boundaries)

Recommended: 10-20% of size

overlap: 50

chunking:

每个分块的令牌数（越小=精度越高，越大=上下文越多）

推荐值: 256-1024

size: 512

分块之间的重叠部分（保留边界处的上下文）

推荐值: 分块大小的10-20%

overlap: 50

═══════════════════════════════════════════════════════════════

WATCH CONFIGURATION

文件监听配置

File watching daemon settings

文件监听守护进程设置

═══════════════════════════════════════════════════════════════

watch:

Debounce delay in milliseconds

Groups rapid file changes together

debounce_ms: 500

watch:

防抖延迟（毫秒）

将频繁的文件变更合并处理

debounce_ms: 500

═══════════════════════════════════════════════════════════════

TRACE CONFIGURATION

调用追踪配置

Call graph analysis settings

调用图分析设置

═══════════════════════════════════════════════════════════════

trace:

Extraction mode: fast | precise

fast: Uses regex, no dependencies, faster

precise: Uses tree-sitter AST parsing, more accurate

mode: fast

Languages to analyze for call graphs

enabled_languages: - .go - .js - .ts - .jsx - .tsx - .py - .php - .c - .h - .cpp - .hpp - .cc - .cxx - .rs - .zig - .cs - .pas - .dpr

Patterns to exclude from trace analysis

exclude_patterns: - "_test.go" - ".spec.ts" - "*.test.js"

trace:

提取模式: fast | precise

fast: 使用正则表达式，无依赖，速度更快

precise: 使用tree-sitter AST解析，准确度更高

mode: fast

用于分析调用图的语言

enabled_languages: - .go - .js - .ts - .jsx - .tsx - .py - .php - .c - .h - .cpp - .hpp - .cc - .cxx - .rs - .zig - .cs - .pas - .dpr

调用追踪分析中排除的模式

exclude_patterns: - "_test.go" - ".spec.ts" - "*.test.js"

═══════════════════════════════════════════════════════════════

SEARCH CONFIGURATION

搜索配置

Search result scoring and ranking

搜索结果的评分与排序

═══════════════════════════════════════════════════════════════

search:

Score boosting configuration

boost: enabled: true

# Reduce scores for certain paths
penalties:
  - pattern: /tests/
    factor: 0.5
  - pattern: _test.
    factor: 0.5
  - pattern: .spec.
    factor: 0.5
  - pattern: /docs/
    factor: 0.6
  - pattern: /vendor/
    factor: 0.3
  - pattern: /node_modules/
    factor: 0.3

# Increase scores for certain paths
bonuses:
  - pattern: /src/
    factor: 1.1
  - pattern: /lib/
    factor: 1.1
  - pattern: /core/
    factor: 1.2
  - pattern: /app/
    factor: 1.1

Hybrid search (vector + keyword)

hybrid: enabled: false k: 60 # BM25 parameter

search:

分数权重配置

boost: enabled: true

# 降低特定路径的分数
penalties:
  - pattern: /tests/
    factor: 0.5
  - pattern: _test.
    factor: 0.5
  - pattern: .spec.
    factor: 0.5
  - pattern: /docs/
    factor: 0.6
  - pattern: /vendor/
    factor: 0.3
  - pattern: /node_modules/
    factor: 0.3

# 提高特定路径的分数
bonuses:
  - pattern: /src/
    factor: 1.1
  - pattern: /lib/
    factor: 1.1
  - pattern: /core/
    factor: 1.2
  - pattern: /app/
    factor: 1.1

混合搜索（向量+关键词）

hybrid: enabled: false k: 60 # BM25参数

═══════════════════════════════════════════════════════════════

IGNORE CONFIGURATION

忽略规则配置

Files and directories to exclude from indexing

索引时排除的文件和目录

═══════════════════════════════════════════════════════════════

ignore:

Directories

.git
.grepai
.svn
.hg
node_modules
vendor
target
pycache
.pytest_cache
dist
build
out
.next
.nuxt

Files

"*.min.js"
"*.min.css"
"*.bundle.js"
"*.map"
"*.lock"
package-lock.json
yarn.lock
pnpm-lock.yaml
go.sum

Generated

".generated."
"*.pb.go"
"*.d.ts"

undefined

ignore:

文件

"*.min.js"
"*.min.css"
"*.bundle.js"
"*.map"
"*.lock"
package-lock.json
yarn.lock
pnpm-lock.yaml
go.sum

生成文件

".generated."
"*.pb.go"
"*.d.ts"

undefined

Configuration by Use Case

按用例配置

Small Personal Project

小型个人项目

yaml

version: 1
embedder:
  provider: ollama
  model: nomic-embed-text
store:
  backend: gob
chunking:
  size: 512
  overlap: 50

yaml

version: 1
embedder:
  provider: ollama
  model: nomic-embed-text
store:
  backend: gob
chunking:
  size: 512
  overlap: 50

Large Codebase

大型代码库

yaml

version: 1
embedder:
  provider: ollama
  model: bge-m3  # Larger model
  parallelism: 4
store:
  backend: postgres  # Scalable storage
  postgres:
    dsn: postgres://user:pass@localhost:5432/grepai
chunking:
  size: 768  # Larger chunks
  overlap: 100

yaml

version: 1
embedder:
  provider: ollama
  model: bge-m3  # 更大的模型
  parallelism: 4
store:
  backend: postgres  # 可扩展存储
  postgres:
    dsn: postgres://user:pass@localhost:5432/grepai
chunking:
  size: 768  # 更大的分块
  overlap: 100

Team Environment

团队环境

yaml

version: 1
embedder:
  provider: openai
  model: text-embedding-3-small
  api_key: ${OPENAI_API_KEY}
  parallelism: 8
store:
  backend: qdrant
  qdrant:
    endpoint: qdrant.internal.company.com
    port: 6334
    use_tls: true

yaml

version: 1
embedder:
  provider: openai
  model: text-embedding-3-small
  api_key: ${OPENAI_API_KEY}
  parallelism: 8
store:
  backend: qdrant
  qdrant:
    endpoint: qdrant.internal.company.com
    port: 6334
    use_tls: true

Maximum Privacy

最高隐私配置

yaml

version: 1
embedder:
  provider: ollama
  model: nomic-embed-text
  endpoint: http://localhost:11434
store:
  backend: gob  # Local file only

yaml

version: 1
embedder:
  provider: ollama
  model: nomic-embed-text
  endpoint: http://localhost:11434
store:
  backend: gob  # 仅本地文件存储

Environment Variables

环境变量

GrepAI supports environment variable substitution:

yaml

embedder:
  api_key: ${OPENAI_API_KEY}

store:
  postgres:
    dsn: ${DATABASE_URL}

Set in your shell:

bash

export OPENAI_API_KEY="sk-..."
export DATABASE_URL="postgres://..."

GrepAI支持环境变量替换：

yaml

embedder:
  api_key: ${OPENAI_API_KEY}

store:
  postgres:
    dsn: ${DATABASE_URL}

在Shell中设置：

bash

export OPENAI_API_KEY="sk-..."
export DATABASE_URL="postgres://..."

Validating Configuration

验证配置

Check your config is valid:

bash

grepai status

If there are config errors, they'll be displayed.

检查你的配置是否有效：

bash

grepai status

如果存在配置错误，会显示相关信息。

Configuration Precedence

配置优先级

```
.grepai/config.yaml
```
in current directory
Workspace configuration (if using workspaces)
Default values

当前目录下的
```
.grepai/config.yaml
```
工作区配置（如果使用工作区）
默认值

Best Practices

最佳实践

Start simple: Use defaults, optimize later
Match chunking to code style: Larger chunks for verbose code
Use boosting: Penalize test/vendor, boost src/lib
Secure API keys: Use environment variables, never commit
Exclude noise: Ignore generated files, dependencies

从简开始：使用默认值，之后再优化
匹配代码风格调整分块：对于冗长的代码使用更大的分块
使用权重调整：降低测试/依赖库的分数，提高源码/库目录的分数
保护API密钥：使用环境变量，绝不要提交到代码仓库
排除干扰文件：忽略生成文件和依赖目录

Output Format

输出格式

Valid configuration status:

✅ GrepAI Configuration Valid

   Embedder: ollama (nomic-embed-text)
   Storage: gob (.grepai/index.gob)
   Chunking: 512 tokens, 50 overlap
   Trace mode: fast
   Languages: 18 enabled
   Ignore patterns: 12 configured
   Boosting: enabled

有效的配置状态：

✅ GrepAI Configuration Valid

   Embedder: ollama (nomic-embed-text)
   Storage: gob (.grepai/index.gob)
   Chunking: 512 tokens, 50 overlap
   Trace mode: fast
   Languages: 18 enabled
   Ignore patterns: 12 configured
   Boosting: enabled

grepai-config-reference

Original

Translation

GrepAI Configuration Reference

GrepAI配置参考

When to Use This Skill

何时使用此技能

Configuration File Location

配置文件位置

Complete Configuration Schema

完整配置 Schema

═══════════════════════════════════════════════════════════════

═══════════════════════════════════════════════════════════════

EMBEDDER CONFIGURATION

嵌入模型配置

Converts code text into vector embeddings

将代码文本转换为向量嵌入

═══════════════════════════════════════════════════════════════

═══════════════════════════════════════════════════════════════

Provider: ollama | openai | lmstudio

Model name (depends on provider)

Ollama: nomic-embed-text, bge-m3, mxbai-embed-large

OpenAI: text-embedding-3-small, text-embedding-3-large

LM Studio: nomic-embed-text-v1.5, bge-small-en-v1.5

API endpoint URL

Ollama default: http://localhost:11434

LM Studio default: http://localhost:1234

OpenAI: uses official API

Vector dimensions (auto-detected if omitted)

nomic-embed-text: 768

text-embedding-3-small: 1536

text-embedding-3-large: 3072

API key (for OpenAI, supports env vars)

Parallel requests (OpenAI only, for speed)

提供商: ollama | openai | lmstudio

模型名称（取决于提供商）

Ollama: nomic-embed-text, bge-m3, mxbai-embed-large

OpenAI: text-embedding-3-small, text-embedding-3-large

LM Studio: nomic-embed-text-v1.5, bge-small-en-v1.5

API端点URL

Ollama默认值: http://localhost:11434

LM Studio默认值: http://localhost:1234

OpenAI: 使用官方API

向量维度（省略时自动检测）

nomic-embed-text: 768

text-embedding-3-small: 1536

text-embedding-3-large: 3072

API密钥（适用于OpenAI，支持环境变量）

并行请求数（仅OpenAI支持，提升速度）

═══════════════════════════════════════════════════════════════

═══════════════════════════════════════════════════════════════

STORE CONFIGURATION

存储配置

Where vector embeddings are stored

向量嵌入的存储位置

═══════════════════════════════════════════════════════════════

═══════════════════════════════════════════════════════════════

Backend: gob | postgres | qdrant

PostgreSQL configuration (when backend: postgres)

Qdrant configuration (when backend: qdrant)

后端存储: gob | postgres | qdrant

PostgreSQL配置（当backend为postgres时）

Qdrant配置（当backend为qdrant时）

═══════════════════════════════════════════════════════════════

═══════════════════════════════════════════════════════════════

CHUNKING CONFIGURATION

代码分块配置

How code files are split for embedding

代码文件如何拆分以进行嵌入

═══════════════════════════════════════════════════════════════

═══════════════════════════════════════════════════════════════

Tokens per chunk (smaller = more precise, larger = more context)

Recommended: 256-1024

Overlap between chunks (preserves context at boundaries)

Recommended: 10-20% of size

每个分块的令牌数（越小=精度越高，越大=上下文越多）

推荐值: 256-1024

分块之间的重叠部分（保留边界处的上下文）

推荐值: 分块大小的10-20%

═══════════════════════════════════════════════════════════════