Add API rate limits

config.py

@@ -7,6 +7,9 @@ Environment Variables:
     ELASTIC_INDEX: Target index name (default: this_little_corner_py).
     LOCAL_DATA_DIR: Root folder containing JSON metadata (default: ../data/video_metadata).
     YOUTUBE_API_KEY: Optional API key for pulling metadata directly from YouTube.
+    RATE_LIMIT_ENABLED: Toggle API rate limiting (default: 1).
+    RATE_LIMIT_REQUESTS: Max requests per window per client (default: 60).
+    RATE_LIMIT_WINDOW_SECONDS: Window size in seconds (default: 60).
 """
 
 from __future__ import annotations
@@ -53,11 +56,19 @@ class YoutubeSettings:
     api_key: Optional[str]
 
 
+@dataclass(frozen=True)
+class RateLimitSettings:
+    enabled: bool
+    requests: int
+    window_seconds: int
+
+
 @dataclass(frozen=True)
 class AppConfig:
     elastic: ElasticSettings
     data: DataSettings
     youtube: YoutubeSettings
+    rate_limit: RateLimitSettings
     qdrant_url: str
     qdrant_collection: str
     qdrant_vector_name: Optional[str]
@@ -94,10 +105,16 @@ def load_config() -> AppConfig:
     )
     data = DataSettings(root=data_root)
     youtube = YoutubeSettings(api_key=_env("YOUTUBE_API_KEY"))
+    rate_limit = RateLimitSettings(
+        enabled=_env("RATE_LIMIT_ENABLED", "1") in {"1", "true", "True"},
+        requests=max(int(_env("RATE_LIMIT_REQUESTS", "60")), 0),
+        window_seconds=max(int(_env("RATE_LIMIT_WINDOW_SECONDS", "60")), 1),
+    )
     return AppConfig(
         elastic=elastic,
         data=data,
         youtube=youtube,
+        rate_limit=rate_limit,
         qdrant_url=_env("QDRANT_URL", "http://localhost:6333"),
         qdrant_collection=_env("QDRANT_COLLECTION", "tlc_embeddings"),
         qdrant_vector_name=_env("QDRANT_VECTOR_NAME"),