OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add yoanbernabeu/grepai-skills --skill grepai-chunking
Configure code chunking in GrepAI. Use this skill to optimize how code is split for embedding.
npx skills add yoanbernabeu/grepai-skills --skill grepai-chunking
This skill covers how GrepAI splits code files into chunks for embedding, and how to optimize chunking for your codebase.
Chunking is the process of splitting source files into smaller segments for embedding:
Embedding models have optimal input sizes:
The target number of tokens per chunk.
| Size | Effect |
|---|---|
| 256 | More precise, less context |
| 512 | Balanced (default) |
| 1024 | More context, less precise |
Tokens shared between adjacent chunks. Preserves context at boundaries.
| Overlap | Effect |
|---|---|
| 0 | No overlap, may lose context at boundaries |
| 50 | Standard overlap (default) |
| 100 | More context, larger index |
With size=512 and overlap=50:
GrepAI uses approximate token counting:
Example:
≈ 45 tokens
Larger overlap = more chunks = larger index:
| Size | Overlap | Chunks per 10K tokens | Index Impact |
|---|---|---|---|
| 512 | 0 | ~20 | Smallest |
| 512 | 50 | ~22 | Standard |
| 512 | 100 | ~24 | +10% |
| 256 | 50 | ~44 | +100% |
Before changing settings, save a search result:
After changing settings and re-indexing:
GrepAI tries to split at logical boundaries:
This means actual chunk sizes may vary slightly from the target.
❌ Problem: Search results are too fragmented ✅ Solution: Increase chunk size:
❌ Problem: Search results have too much irrelevant context ✅ Solution: Decrease chunk size:
❌ Problem: Results miss related code at function boundaries ✅ Solution: Increase overlap:
❌ Problem: Index is too large ✅ Solutions:
Chunking status:
# .grepai/config.yaml
chunking:
size: 512 # Tokens per chunk
overlap: 50 # Overlap between chunksFile: auth.go (1000 tokens)
Chunk 1: tokens 1-512
┌────────────────────────────────────┐
│ func Login(user, pass)... │
└────────────────────────────────────┘
↘
50 token overlap
↙
Chunk 2: tokens 463-974
┌────────────────────────────────────┐
│ ...validate credentials... │
└────────────────────────────────────┘
↘
50 token overlap
↙
Chunk 3: tokens 925-1000
┌──────────────┐
│ ...return │
└──────────────┘chunking:
size: 768 # Larger to capture full methods
overlap: 75chunking:
size: 512 # Standard size
overlap: 50chunking:
size: 384 # Smaller for precise results
overlap: 40chunking:
size: 384 # Capture individual functions
overlap: 40chunking:
size: 768 # Capture more context
overlap: 100chunking:
size: 512 # Balanced default
overlap: 50func calculateTotal(items []Item) float64 {
total := 0.0
for _, item := range items {
total += item.Price * float64(item.Quantity)
}
return total
}Query: "authentication middleware"
Result: "...c.AbortWithStatus(401)..."
(Fragment, missing context)Query: "authentication middleware"
Result: "func AuthMiddleware() gin.HandlerFunc {
return func(c *gin.Context) {
token := c.GetHeader("Authorization")
if token == "" {
c.AbortWithStatus(401)
return
}
// validate token...
}
}"
(Complete function with context)Query: "authentication middleware"
Result: "// Multiple unrelated functions...
func AuthMiddleware()... (your match)
func LoggingMiddleware()...
func CORSMiddleware()..."
(Too much noise)chunking:
size: 384
overlap: 40rm .grepai/index.gob
grepai watchgrepai search "your query"grepai search "authentication" > before.txtgrepai search "authentication" > after.txt
diff before.txt after.txtchunking:
size: 768chunking:
size: 384chunking:
overlap: 100✅ Chunking Configuration
Size: 512 tokens
Overlap: 50 tokens
Index Statistics:
- Total files: 245
- Total chunks: 1,234
- Avg chunks/file: 5.0
- Avg chunk size: 478 tokens
Recommendations:
- Current settings are balanced
- Consider size: 384 for more precise results
- Consider size: 768 for more context