BobAi
a1f84e2bd5
- Changed primary model recommendation from qwen3:1.7b to qwen3:4b - Added Q8 quantization info in technical docs for production users - Fixed method name error: get_embedding_info() -> get_status() - Updated all error messages and test files with new recommendations - Maintained beginner-friendly options (1.7b still very good, 0.6b surprisingly good) - Added explanation of why small models work well with RAG context - Comprehensive testing completed - system ready for clean release
53 lines
1.7 KiB
YAML
53 lines
1.7 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
|
|
|
|
# LLM synthesis and query expansion settings
|
|
llm:
|
|
ollama_host: localhost:11434
|
|
synthesis_model: auto # 'auto', 'qwen3:1.7b', etc.
|
|
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 |