BobAi
a7e3e6f474
- Create separate explore mode with thinking enabled for debugging/learning - Add lazy loading with LLM warmup using 'testing, just say "hi" <no_think>' - Implement context-aware conversation memory across questions - Add interactive CLI with help, summary, and session management - Enable Qwen3 thinking mode toggle for experimentation - Support multi-turn conversations for better debugging workflow - Clean separation between fast synthesis and deep exploration modes
55 lines
2.0 KiB
YAML
55 lines
2.0 KiB
YAML
# FSS-Mini-RAG Configuration
|
|
# Edit this file to customize indexing and search behavior
|
|
# See docs/GETTING_STARTED.md for detailed explanations
|
|
|
|
# Text chunking settings
|
|
chunking:
|
|
max_size: 2000 # Maximum characters per chunk
|
|
min_size: 150 # Minimum characters per chunk
|
|
strategy: semantic # 'semantic' (language-aware) or 'fixed'
|
|
|
|
# Large file streaming settings
|
|
streaming:
|
|
enabled: true
|
|
threshold_bytes: 1048576 # Files larger than this use streaming (1MB)
|
|
|
|
# File processing settings
|
|
files:
|
|
min_file_size: 50 # Skip files smaller than this
|
|
exclude_patterns:
|
|
- "node_modules/**"
|
|
- ".git/**"
|
|
- "__pycache__/**"
|
|
- "*.pyc"
|
|
- ".venv/**"
|
|
- "venv/**"
|
|
- "build/**"
|
|
- "dist/**"
|
|
include_patterns:
|
|
- "**/*" # Include all files by default
|
|
|
|
# Embedding generation settings
|
|
embedding:
|
|
preferred_method: ollama # 'ollama', 'ml', 'hash', or 'auto'
|
|
ollama_model: nomic-embed-text
|
|
ollama_host: localhost:11434
|
|
ml_model: sentence-transformers/all-MiniLM-L6-v2
|
|
batch_size: 32 # Embeddings processed per batch
|
|
|
|
# Search behavior settings
|
|
search:
|
|
default_limit: 10 # Default number of results
|
|
enable_bm25: true # Enable keyword matching boost
|
|
similarity_threshold: 0.1 # Minimum similarity score
|
|
expand_queries: false # Enable automatic query expansion (TUI auto-enables)
|
|
|
|
# LLM synthesis and query expansion settings
|
|
llm:
|
|
ollama_host: localhost:11434
|
|
synthesis_model: auto # 'auto' prefers qwen3:0.6b for CPU efficiency
|
|
expansion_model: auto # Usually same as synthesis_model
|
|
max_expansion_terms: 8 # Maximum terms to add to queries
|
|
enable_synthesis: false # Enable synthesis by default
|
|
synthesis_temperature: 0.3 # LLM temperature for analysis
|
|
cpu_optimized: true # Prefer ultra-lightweight models for CPU-only systems
|
|
enable_thinking: true # Enable thinking mode for Qwen3 models (production: true, testing: false) |