Merge pull request #68 from ggozad/feat/disable-autocreation

DISABLE_DB_AUTOCREATE option to prevent auto-creation of dbs

docs/configuration.md

@@ -211,6 +211,16 @@ Authentication is handled through standard cloud provider credentials (AWS CLI,
 
 **Note:** Table optimization is automatically handled by LanceDB Cloud (`db://` URIs) and is disabled for better performance. For object storage backends (S3, Azure, GCS), optimization is still performed locally.
 
+#### Disable database auto-creation
+
+By default, haiku.rag creates the local LanceDB directory and required tables on first use. To prevent accidental database creation and fail fast if a database hasn’t been set up yet, set:
+
+```bash
+DISABLE_DB_AUTOCREATE=true
+```
+
+When enabled, for local paths, haiku.rag errors if the LanceDB directory does not exist, and it will not create parent directories.
+
 ### Document Processing
 
 ```bash

src/haiku/rag/client.py

@@ -33,8 +33,6 @@ class HaikuRAG:
             db_path: Path to the database file.
             skip_validation: Whether to skip configuration validation on database load.
         """
-        if not db_path.parent.exists():
-            Path.mkdir(db_path.parent, parents=True)
         self.store = Store(db_path, skip_validation=skip_validation)
         self.document_repository = DocumentRepository(self.store)
         self.chunk_repository = ChunkRepository(self.store)

src/haiku/rag/config.py

@@ -53,6 +53,10 @@ class AppConfig(BaseModel):
     ANTHROPIC_API_KEY: str = ""
     COHERE_API_KEY: str = ""
 
+    # If true, refuse to auto-create a new LanceDB database or tables
+    # and error out when the database does not already exist.
+    DISABLE_DB_AUTOCREATE: bool = False
+
     @field_validator("MONITOR_DIRECTORIES", mode="before")
     @classmethod
     def parse_monitor_directories(cls, v):

src/haiku/rag/store/engine.py

@@ -54,6 +54,19 @@ class Store:
         # Create the ChunkRecord model with the correct vector dimension
         self.ChunkRecord = create_chunk_model(self.embedder._vector_dim)
 
+        # Local filesystem handling for DB directory
+        if not self._has_cloud_config():
+            if Config.DISABLE_DB_AUTOCREATE:
+                # LanceDB uses a directory path for local databases; enforce presence
+                if not db_path.exists():
+                    raise FileNotFoundError(
+                        f"LanceDB path does not exist: {db_path}. Auto-creation is disabled."
+                    )
+            else:
+                # Ensure parent directories exist when autocreation allowed
+                if not db_path.parent.exists():
+                    Path.mkdir(db_path.parent, parents=True)
+
         # Connect to LanceDB
         self.db = self._connect_to_lancedb(db_path)