From 896169aa3a556d434ebdb67d741e446ecbb61117 Mon Sep 17 00:00:00 2001 From: bnyashwanth Date: Fri, 16 Jan 2026 19:09:37 +0530 Subject: [PATCH 1/2] fix: handle invalid EMBEDDING_MAX_BATCH_SIZE gracefully (Fixes #244) --- backend/config.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/backend/config.py b/backend/config.py index dd5caa3d..bfe5c5de 100644 --- a/backend/config.py +++ b/backend/config.py @@ -12,5 +12,10 @@ GITHUB_TOKEN = os.getenv("GITHUB_TOKEN") or os.getenv("GH_TOKEN") MODEL_NAME = os.getenv("EMBEDDING_MODEL", "BAAI/bge-small-en-v1.5") -MAX_BATCH_SIZE = int(os.getenv("EMBEDDING_MAX_BATCH_SIZE", "32")) +raw_batch_size = os.getenv("EMBEDDING_MAX_BATCH_SIZE", "32") +try: + MAX_BATCH_SIZE = int(raw_batch_size) +except ValueError: + print(f"Warning: Invalid EMBEDDING_MAX_BATCH_SIZE '{raw_batch_size}'. Defaulting to 32.") + MAX_BATCH_SIZE = 32 EMBEDDING_DEVICE = os.getenv("EMBEDDING_DEVICE", "cpu") From 1828cf58282e5df104af70e00f59cf9895b20307 Mon Sep 17 00:00:00 2001 From: bnyashwanth Date: Fri, 16 Jan 2026 19:24:41 +0530 Subject: [PATCH 2/2] refactor: use logging and validate positive integer --- backend/config.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/backend/config.py b/backend/config.py index bfe5c5de..89bc6583 100644 --- a/backend/config.py +++ b/backend/config.py @@ -1,6 +1,8 @@ -from dotenv import load_dotenv, find_dotenv +import logging import os +from dotenv import load_dotenv, find_dotenv +logger = logging.getLogger(__name__) dotenv_path = find_dotenv(usecwd=True) if dotenv_path: @@ -12,10 +14,14 @@ GITHUB_TOKEN = os.getenv("GITHUB_TOKEN") or os.getenv("GH_TOKEN") MODEL_NAME = os.getenv("EMBEDDING_MODEL", "BAAI/bge-small-en-v1.5") + raw_batch_size = os.getenv("EMBEDDING_MAX_BATCH_SIZE", "32") try: MAX_BATCH_SIZE = int(raw_batch_size) + if MAX_BATCH_SIZE <= 0: + raise ValueError except ValueError: - print(f"Warning: Invalid EMBEDDING_MAX_BATCH_SIZE '{raw_batch_size}'. Defaulting to 32.") + logger.warning("Invalid EMBEDDING_MAX_BATCH_SIZE '%s'. Defaulting to 32.", raw_batch_size) MAX_BATCH_SIZE = 32 + EMBEDDING_DEVICE = os.getenv("EMBEDDING_DEVICE", "cpu")