Populate DB Chromadb

backend/src/mongo/metadata.py

@@ -0,0 +1,62 @@
+from .connection import get_mongo_client
+from datetime import datetime
+
+DB_NAME = "hoya_metadata"
+
+def get_datasets_collection():
+    client = get_mongo_client()
+    db = client.get_database(DB_NAME)
+    return db["datasets"]
+
+def get_categories_collection():
+    client = get_mongo_client()
+    db = client.get_database(DB_NAME)
+    return db["categories"]
+
+def is_file_processed(filename):
+    collection = get_datasets_collection()
+    return collection.find_one({"filename": filename}) is not None
+
+def log_processed_file(filename, category=None, chunk_count=0):
+    collection = get_datasets_collection()
+    doc = {
+        "filename": filename,
+        "category": category,
+        "chunk_count": chunk_count,
+        "processed_at": datetime.utcnow(),
+        "status": "processed"
+    }
+    collection.insert_one(doc)
+
+def get_all_datasets():
+    collection = get_datasets_collection()
+    return list(collection.find({}, {"_id": 0}))
+
+def get_datasets_by_category(category):
+    collection = get_datasets_collection()
+    return list(collection.find({"category": category}, {"_id": 0}))
+
+def delete_dataset_record(filename):
+    collection = get_datasets_collection()
+    result = collection.delete_one({"filename": filename})
+    return result.deleted_count > 0
+
+def create_category(name, description=""):
+    collection = get_categories_collection()
+    if collection.find_one({"name": name}):
+        return False
+    collection.insert_one({
+        "name": name,
+        "description": description,
+        "created_at": datetime.utcnow()
+    })
+    return True
+
+def get_all_categories():
+    collection = get_categories_collection()
+    return list(collection.find({}, {"_id": 0}))
+
+def delete_category(name):
+    collection = get_categories_collection()
+    result = collection.delete_one({"name": name})
+    return result.deleted_count > 0