src/config.py

import os
from dotenv import load_dotenv

load_dotenv(override=True)

# Model configuration
EMBEDDING_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
LLM_MODEL = "z-ai/glm-4.5-air:free"
LLM_BASE_URL = "https://openrouter.ai/api/v1"
LLM_TEMPERATURE = 0.7

# API configuration
OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")

# Vector store configuration
VECTOR_STORE_PATH = "chroma_db"

# Hugging Face dataset configuration
HF_REPO_ID = "ikReza/traffic_rules"
HF_FILENAME = "traffic_rules.pdf"
HF_REPO_TYPE = "dataset"

# Text chunking configuration
# These settings determine how the PDF document is broken into manageable pieces

# CHUNK_SIZE: The maximum number of characters in each chunk
# Larger chunks preserve more context but may be less precise
CHUNK_SIZE = 500

# CHUNK_OVERLAP: The number of characters that overlap between adjacent chunks
# Overlap helps ensure that important information isn't split between chunks
CHUNK_OVERLAP = 50

# BATCH_SIZE: The number of chunks to process at once
# Processing in batches improves efficiency and prevents timeouts
BATCH_SIZE = 100