Fixed various code issues.

Author: AnthonyMalRivett

backend/app/models/paper.py

@@ -4,16 +4,16 @@
 from typing import TYPE_CHECKING, List, Optional
 
 from pgvector.sqlalchemy import Vector
-from sqlalchemy import Enum as SqlEnum
 from sqlalchemy import (
     JSON,
     BigInteger,
     Date,
     DateTime,
+    Index,
     String,
     Text,
-    Index,
 )
+from sqlalchemy import Enum as SqlEnum
 from sqlalchemy.orm import Mapped, mapped_column, relationship
 from sqlalchemy.sql import func
 
@@ -45,17 +45,13 @@ class Paper(Base):
     authors: Mapped[Optional[dict]] = mapped_column(JSON, nullable=True)
     abstract: Mapped[Optional[str]] = mapped_column(Text, nullable=True)
     published_at: Mapped[Optional[date]] = mapped_column(Date, nullable=True)
-    paper_id_external: Mapped[Optional[str]] = mapped_column(
-        String(255), nullable=True
-    )  # <-- added
+    paper_id_external: Mapped[Optional[str]] = mapped_column(String(255), nullable=True)
     fetched_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now()
     )
 
     # Vector Embedding
-    embedding: Mapped[Optional[List[float]]] = mapped_column(
-        Vector(768), nullable=True
-    )
+    embedding: Mapped[Optional[List[float]]] = mapped_column(Vector(768), nullable=True)
 
     # Relationships
     project_links: Mapped[List["ProjectPaper"]] = relationship(
@@ -72,9 +68,7 @@ class Paper(Base):
             "ix_paper_embedding_hnsw",
             "embedding",
             postgresql_using="hnsw",
-            postgresql_ops={
-                "embedding": "vector_cosine_ops"
-            },
+            postgresql_ops={"embedding": "vector_cosine_ops"},
             postgresql_with={"m": 16, "ef_construction": 64},
         ),
     )

backend/app/services/arxiv_ingestion.py

@@ -1,6 +1,7 @@
 import argparse
 import json
 import logging
+import os
 from datetime import datetime
 from pathlib import Path
 from typing import Iterable, List, Optional, Tuple
@@ -14,11 +15,11 @@
 logger = logging.getLogger(__name__)
 
 DB_CONFIG = {
-    "host": "inquiro-db.cxa6mocs0pr2.eu-central-1.rds.amazonaws.com",
-    "port": 5432,
-    "user": "postgres",
-    "password": "TODO",
-    "dbname": "inquiro_db",
+    "host": os.getenv("POSTGRES_HOST"),
+    "port": int(os.getenv("POSTGRES_PORT")),
+    "user": os.getenv("POSTGRES_USER"),
+    "password": os.getenv("POSTGRES_PASSWORD"),
+    "dbname": os.getenv("POSTGRES_DB"),
     "sslmode": "require",
 }
 
@@ -145,13 +146,17 @@ def main(data_dir: Path, batch_size: int):
 
 
 if __name__ == "__main__":
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    default_data_path = os.path.join(script_dir, "arxiv-vector-embeddings")
+
     parser = argparse.ArgumentParser(
         description="Bulk ingest arXiv parquet shards into paper table."
     )
     parser.add_argument(
         "--data-dir",
         type=str,
-        default=r"C:/Users/AnthonyMalRivett/Documents/arxiv-vector-embeddings",
+        default=default_data_path,
+        help="Path to the folder containing the embeddings",
     )
     parser.add_argument("--batch-size", type=int, default=1000)
     args = parser.parse_args()