Mohit Raj
Sync from GitHub via hub-sync
be91bf9 verified
Raw History Blame Contribute Delete
1.75 kB
"""
Configuration module for Study Ocean RAG Student Mentor.
Loads environment variables and provides default settings.
"""
import os
from dotenv import load_dotenv
load_dotenv()
# ─── API Keys ────────────────────────────────────────────────
GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY", "").strip()
GROQ_API_KEY = os.getenv("GROQ_API_KEY", "").strip()
# ─── Model Configuration ────────────────────────────────────
EMBEDDING_MODEL = os.getenv("EMBEDDING_MODEL", "all-MiniLM-L6-v2")
LLM_MODEL = os.getenv("LLM_MODEL", "llama-3.3-70b-versatile")
# ─── Paths ───────────────────────────────────────────────────
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
PDF_DIR = os.path.join(BASE_DIR, os.getenv("PDF_DIR", "data/pdfs"))
VECTOR_STORE_PATH = os.path.join(BASE_DIR, os.getenv("VECTOR_STORE_PATH", "data/vector_store"))
# ─── Text Splitting ─────────────────────────────────────────
CHUNK_SIZE = int(os.getenv("CHUNK_SIZE", "1000"))
CHUNK_OVERLAP = int(os.getenv("CHUNK_OVERLAP", "200"))
# ─── RAG Parameters ─────────────────────────────────────────
TOP_K_RESULTS = 2 # Number of relevant chunks to retrieve (lowered for faster responses)
TEMPERATURE = 0.3 # LLM temperature (lower = more focused)
MAX_OUTPUT_TOKENS = 2048 # Max tokens in LLM response