BobAi
a84ff94fba
This comprehensive update enhances user experience with several key improvements: ## Enhanced Streaming & Thinking Display - Implement real-time streaming with gray thinking tokens that collapse after completion - Fix thinking token redisplay bug with proper content filtering - Add clear "AI Response:" headers to separate thinking from responses - Enable streaming by default for better user engagement - Keep thinking visible for exploration, collapse only for suggested questions ## Natural Conversation Responses - Convert clunky JSON exploration responses to natural, conversational format - Improve exploration prompts for friendly, colleague-style interactions - Update summary generation with better context handling - Eliminate double response display issues ## Model Reference Updates - Remove all llama3.2 references in favor of qwen3 models - Fix non-existent qwen3:3b references, replace with proper model names - Update model rankings to prioritize working qwen models across all components - Ensure consistent model recommendations in docs and examples ## Cross-Platform Icon Integration - Add desktop icon setup to Linux installer with .desktop entry - Add Windows shortcuts for desktop and Start Menu integration - Improve installer user experience with visual branding ## Configuration & Navigation Fixes - Fix "0" option in configuration menu to properly go back - Improve configuration menu user-friendliness - Update troubleshooting guides with correct model suggestions These changes significantly improve the beginner experience while maintaining technical accuracy and system reliability.
111 lines
5.2 KiB
YAML
111 lines
5.2 KiB
YAML
# 💎 QUALITY CONFIG - Best Possible Results
|
|
# When you want the highest quality search and AI responses
|
|
# Perfect for: learning new codebases, research, complex analysis
|
|
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
# 🎯 QUALITY-OPTIMIZED SETTINGS - Everything tuned for best results!
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
|
|
# 📝 Chunking for maximum context and quality
|
|
chunking:
|
|
max_size: 3000 # Larger chunks = more context per result
|
|
min_size: 200 # Ensure substantial content per chunk
|
|
strategy: semantic # Smart splitting that respects code structure
|
|
|
|
# 🌊 Conservative streaming (favor quality over speed)
|
|
streaming:
|
|
enabled: true
|
|
threshold_bytes: 2097152 # 2MB - less aggressive chunking
|
|
|
|
# 📁 Comprehensive file inclusion
|
|
files:
|
|
min_file_size: 20 # Include even small files (might contain important info)
|
|
|
|
# 🎯 Minimal exclusions (include more content)
|
|
exclude_patterns:
|
|
- "node_modules/**" # Still skip these (too much noise)
|
|
- ".git/**" # Git history not useful for code search
|
|
- "__pycache__/**" # Python bytecode
|
|
- "*.pyc"
|
|
- ".venv/**"
|
|
- "build/**" # Compiled artifacts
|
|
- "dist/**"
|
|
# Note: We keep logs, docs, configs that might have useful context
|
|
|
|
include_patterns:
|
|
- "**/*" # Include everything not explicitly excluded
|
|
|
|
# 🧠 Best embedding quality
|
|
embedding:
|
|
preferred_method: ollama # Highest quality embeddings (needs Ollama)
|
|
ollama_model: nomic-embed-text # Excellent code understanding
|
|
ml_model: sentence-transformers/all-MiniLM-L6-v2 # Good fallback
|
|
batch_size: 16 # Smaller batches for stability
|
|
|
|
# 🔍 Search optimized for comprehensive results
|
|
search:
|
|
default_top_k: 15 # More results to choose from
|
|
enable_bm25: true # Use both semantic and keyword matching
|
|
similarity_threshold: 0.05 # Very permissive (show more possibilities)
|
|
expand_queries: true # Automatic query expansion for better recall
|
|
|
|
# 🤖 High-quality AI analysis
|
|
llm:
|
|
synthesis_model: auto # Use best available model
|
|
enable_synthesis: true # AI explanations by default
|
|
synthesis_temperature: 0.4 # Good balance of accuracy and insight
|
|
cpu_optimized: false # Use powerful models if available
|
|
enable_thinking: true # Show detailed reasoning process
|
|
max_expansion_terms: 10 # Comprehensive query expansion
|
|
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
# 💎 WHAT THIS CONFIG MAXIMIZES:
|
|
#
|
|
# 🎯 Search comprehensiveness - find everything relevant
|
|
# 🎯 Result context - larger chunks with more information
|
|
# 🎯 AI explanation quality - detailed, thoughtful analysis
|
|
# 🎯 Query understanding - automatic expansion and enhancement
|
|
# 🎯 Semantic accuracy - best embedding models available
|
|
#
|
|
# ⚖️ TRADE-OFFS:
|
|
# ⏳ Slower indexing (larger chunks, better embeddings)
|
|
# ⏳ Slower searching (query expansion, more results)
|
|
# 💾 More storage space (larger index, more files included)
|
|
# 🧠 More memory usage (larger batches, bigger models)
|
|
# ⚡ Higher CPU/GPU usage (better models)
|
|
#
|
|
# 🎯 PERFECT FOR:
|
|
# • Learning new, complex codebases
|
|
# • Research and analysis tasks
|
|
# • When you need to understand WHY code works a certain way
|
|
# • Finding subtle connections and patterns
|
|
# • Code review and security analysis
|
|
# • Academic or professional research
|
|
#
|
|
# 💻 REQUIREMENTS:
|
|
# • Ollama installed and running (ollama serve)
|
|
# • At least one language model (ollama pull qwen3:1.7b)
|
|
# • Decent computer specs (4GB+ RAM recommended)
|
|
# • Patience for thorough analysis 😊
|
|
#
|
|
# 🚀 TO USE THIS CONFIG:
|
|
# 1. Install Ollama: curl -fsSL https://ollama.ai/install.sh | sh
|
|
# 2. Start Ollama: ollama serve
|
|
# 3. Install a model: ollama pull qwen3:1.7b
|
|
# 4. Copy config: cp examples/config-quality.yaml .mini-rag/config.yaml
|
|
# 5. Index project: ./rag-mini index /path/to/project
|
|
# 6. Enjoy comprehensive analysis: ./rag-mini explore /path/to/project
|
|
#═══════════════════════════════════════════════════════════════════════
|
|
|
|
# 🧪 ADVANCED QUALITY TUNING (optional):
|
|
#
|
|
# For even better results, try these model combinations:
|
|
# • ollama pull nomic-embed-text:latest (best embeddings)
|
|
# • ollama pull qwen3:1.7b (good general model)
|
|
# • ollama pull qwen3:4b (excellent for analysis)
|
|
#
|
|
# Or adjust these settings for your specific needs:
|
|
# • similarity_threshold: 0.3 (more selective results)
|
|
# • max_size: 4000 (even more context per result)
|
|
# • enable_thinking: false (hide reasoning, show just answers)
|
|
# • synthesis_temperature: 0.2 (more conservative AI responses) |