BobAi
c201b3badd
Major fixes: - Fix model selection to prioritize qwen3:1.7b instead of qwen3:4b for testing - Correct context length from 80,000 to 32,000 tokens (proper Qwen3 limit) - Implement content-preserving safeguards instead of dropping responses - Fix all test imports from claude_rag to mini_rag module naming - Add virtual environment warnings to all test entry points - Fix TUI EOF crash handling with proper error handling - Remove warmup delays that were causing startup lag and unwanted model calls - Fix command mappings between bash wrapper and Python script - Update documentation to reflect qwen3:1.7b as primary recommendation - Improve TUI box alignment and formatting - Make language generic for any documents, not just codebases - Add proper folder names in user feedback instead of generic terms Technical improvements: - Unified model rankings across all components - Better error handling for missing dependencies - Comprehensive testing and validation of all fixes - All tests now pass and system is deployment-ready All major crashes and deployment issues resolved.
105 lines
4.2 KiB
YAML
105 lines
4.2 KiB
YAML
# ⚡ FAST CONFIG - Maximum Speed
|
|
# When you need quick results and don't mind slightly lower quality
|
|
# Perfect for: large projects, frequent searches, older computers
|
|
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
# 🚀 SPEED-OPTIMIZED SETTINGS - Everything tuned for performance!
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
|
|
# 📝 Chunking optimized for speed
|
|
chunking:
|
|
max_size: 1500 # Smaller chunks = faster processing
|
|
min_size: 100 # More aggressive minimum
|
|
strategy: fixed # Simple splitting (faster than semantic)
|
|
|
|
# 🌊 More aggressive streaming for memory efficiency
|
|
streaming:
|
|
enabled: true
|
|
threshold_bytes: 512000 # 512KB - process big files in smaller chunks
|
|
|
|
# 📁 File filtering optimized for speed
|
|
files:
|
|
min_file_size: 100 # Skip more tiny files
|
|
|
|
# 🚫 Aggressive exclusions for speed
|
|
exclude_patterns:
|
|
- "node_modules/**"
|
|
- ".git/**"
|
|
- "__pycache__/**"
|
|
- "*.pyc"
|
|
- ".venv/**"
|
|
- "venv/**"
|
|
- "build/**"
|
|
- "dist/**"
|
|
- "*.min.js" # Skip minified files
|
|
- "*.min.css" # Skip minified CSS
|
|
- "*.log" # Skip log files
|
|
- "*.tmp" # Skip temp files
|
|
- "target/**" # Rust/Java build dirs
|
|
- ".next/**" # Next.js build dir
|
|
- ".nuxt/**" # Nuxt build dir
|
|
|
|
include_patterns:
|
|
- "**/*.py" # Focus on common code files only
|
|
- "**/*.js"
|
|
- "**/*.ts"
|
|
- "**/*.jsx"
|
|
- "**/*.tsx"
|
|
- "**/*.java"
|
|
- "**/*.cpp"
|
|
- "**/*.c"
|
|
- "**/*.h"
|
|
- "**/*.rs"
|
|
- "**/*.go"
|
|
- "**/*.php"
|
|
- "**/*.rb"
|
|
- "**/*.md"
|
|
|
|
# 🧠 Fastest embedding method
|
|
embedding:
|
|
preferred_method: hash # Instant embeddings (lower quality but very fast)
|
|
batch_size: 64 # Larger batches for efficiency
|
|
|
|
# 🔍 Search optimized for speed
|
|
search:
|
|
default_top_k: 5 # Fewer results = faster display
|
|
enable_bm25: false # Skip keyword matching for speed
|
|
similarity_threshold: 0.2 # Higher threshold = fewer results to process
|
|
expand_queries: false # No query expansion (much faster)
|
|
|
|
# 🤖 Minimal AI for speed
|
|
llm:
|
|
synthesis_model: qwen3:0.6b # Smallest/fastest model
|
|
enable_synthesis: false # Only use when explicitly requested
|
|
synthesis_temperature: 0.1 # Fast, factual responses
|
|
cpu_optimized: true # Use lightweight models
|
|
enable_thinking: false # Skip thinking process for speed
|
|
max_expansion_terms: 4 # Shorter expansions
|
|
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
# ⚡ WHAT THIS CONFIG PRIORITIZES:
|
|
#
|
|
# 🚀 Indexing speed - get up and running quickly
|
|
# 🚀 Search speed - results in milliseconds
|
|
# 🚀 Memory efficiency - won't slow down your computer
|
|
# 🚀 CPU efficiency - good for older/slower machines
|
|
# 🚀 Storage efficiency - smaller index files
|
|
#
|
|
# ⚖️ TRADE-OFFS:
|
|
# ⚠️ Lower search quality (might miss some relevant results)
|
|
# ⚠️ Less context in results (smaller chunks)
|
|
# ⚠️ No query expansion (might need more specific search terms)
|
|
# ⚠️ Basic embeddings (hash-based, not semantic)
|
|
#
|
|
# 🎯 PERFECT FOR:
|
|
# • Large codebases (>10k files)
|
|
# • Older computers with limited resources
|
|
# • When you know exactly what you're looking for
|
|
# • Frequent, quick lookups
|
|
# • CI/CD environments where speed matters
|
|
#
|
|
# 🚀 TO USE THIS CONFIG:
|
|
# 1. Copy to project: cp examples/config-fast.yaml .mini-rag/config.yaml
|
|
# 2. Index: ./rag-mini index /path/to/project
|
|
# 3. Enjoy lightning-fast searches! ⚡
|
|
#═══════════════════════════════════════════════════════════════════════ |