Merge pull request #139 from ggozad/fix/create-db-only-on-write

Drop disable_auto_create flag, simply create only on write operations

CHANGELOG.md

@@ -50,9 +50,11 @@
 
 - **Document Creation**: Optimized `create_document` to skip unnecessary DoclingDocument conversion when chunks are pre-provided
 - **FileReader**: Error messages now include both original exception details and file path for easier debugging
+- **Database Auto-creation**: Read operations (search, list, get, ask, research) no longer auto-create empty databases. Write operations (add, add-src, delete, rebuild) still create the database as needed. This prevents the confusing scenario where a search query creates an empty database. Fixes issue #137.
 
 ### Removed
 
+- **BREAKING**: Removed `disable_autocreate` config option - the behavior is now automatic based on operation type
 - **BREAKING**: Removed legacy `ResearchStream` and `ResearchStreamEvent` classes (replaced by AG-UI event protocol)
 
 ## [0.15.0] - 2025-11-07

docs/configuration.md

@@ -52,7 +52,6 @@ environment: production
 
 storage:
   data_dir: ""  # Empty = use default platform location
-  disable_autocreate: false
   vacuum_retention_seconds: 86400
 
 monitor:
@@ -561,16 +560,14 @@ 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
+#### 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:
+haiku.rag intelligently handles database creation based on operation type:
 
-```yaml
-storage:
-  disable_autocreate: true
-```
+- **Write operations** (add, add-src, delete, rebuild): Automatically create the database and required tables if they don't exist
+- **Read operations** (list, get, search, ask, research): Fail with a clear error if the database doesn't exist
 
-When enabled, for local paths, haiku.rag errors if the LanceDB directory does not exist, and it will not create parent directories.
+This prevents the common mistake where a search query accidentally creates an empty database. To initialize your database, simply add your first document using `haiku-rag add` or `haiku-rag add-src`.
 
 ### Document Processing
 

haiku_rag_slim/haiku/rag/app.py

@@ -137,7 +137,9 @@ class HaikuRAGApp:
         )
 
     async def list_documents(self, filter: str | None = None):
-        async with HaikuRAG(db_path=self.db_path, config=self.config) as self.client:
+        async with HaikuRAG(
+            db_path=self.db_path, config=self.config, allow_create=False
+        ) as self.client:
             documents = await self.client.list_documents(filter=filter)
             for doc in documents:
                 self._rich_print_document(doc, truncate=True)
@@ -170,7 +172,9 @@ class HaikuRAGApp:
                 )
 
     async def get_document(self, doc_id: str):
-        async with HaikuRAG(db_path=self.db_path, config=self.config) as self.client:
+        async with HaikuRAG(
+            db_path=self.db_path, config=self.config, allow_create=False
+        ) as self.client:
             doc = await self.client.get_document_by_id(doc_id)
             if doc is None:
                 self.console.print(f"[red]Document with id {doc_id} not found.[/red]")
@@ -190,7 +194,9 @@ class HaikuRAGApp:
                 )
 
     async def search(self, query: str, limit: int = 5, filter: str | None = None):
-        async with HaikuRAG(db_path=self.db_path, config=self.config) as self.client:
+        async with HaikuRAG(
+            db_path=self.db_path, config=self.config, allow_create=False
+        ) as self.client:
             results = await self.client.search(query, limit=limit, filter=filter)
             if not results:
                 self.console.print("[yellow]No results found.[/yellow]")
@@ -213,7 +219,9 @@ class HaikuRAGApp:
             deep: Use deep QA mode (multi-step reasoning)
             verbose: Show verbose output
         """
-        async with HaikuRAG(db_path=self.db_path, config=self.config) as self.client:
+        async with HaikuRAG(
+            db_path=self.db_path, config=self.config, allow_create=False
+        ) as self.client:
             try:
                 if deep:
                     from haiku.rag.graph.deep_qa.dependencies import DeepQAContext
@@ -258,7 +266,9 @@ class HaikuRAGApp:
             question: The research question
             verbose: Show AG-UI event stream during execution
         """
-        async with HaikuRAG(db_path=self.db_path, config=self.config) as client:
+        async with HaikuRAG(
+            db_path=self.db_path, config=self.config, allow_create=False
+        ) as client:
             try:
                 self.console.print("[bold cyan]Starting research[/bold cyan]")
                 self.console.print(f"[bold blue]Question:[/bold blue] {question}")

haiku_rag_slim/haiku/rag/client.py

@@ -28,6 +28,7 @@ class HaikuRAG:
         db_path: Path | None = None,
         config: AppConfig = Config,
         skip_validation: bool = False,
+        allow_create: bool = True,
     ):
         """Initialize the RAG client with a database path.
 
@@ -35,12 +36,17 @@ class HaikuRAG:
             db_path: Path to the database file. If None, uses config.storage.data_dir.
             config: Configuration to use. Defaults to global Config.
             skip_validation: Whether to skip configuration validation on database load.
+            allow_create: Whether to allow database creation. If False, will raise error
+                         if database doesn't exist (for read operations).
         """
         self._config = config
         if db_path is None:
             db_path = self._config.storage.data_dir / "haiku.rag.lancedb"
         self.store = Store(
-            db_path, config=self._config, skip_validation=skip_validation
+            db_path,
+            config=self._config,
+            skip_validation=skip_validation,
+            allow_create=allow_create,
         )
         self.document_repository = DocumentRepository(self.store)
         self.chunk_repository = ChunkRepository(self.store)

haiku_rag_slim/haiku/rag/config/loader.py

@@ -53,7 +53,6 @@ def generate_default_config() -> dict:
         "environment": "production",
         "storage": {
             "data_dir": "",
-            "disable_autocreate": False,
             "vacuum_retention_seconds": 86400,
         },
         "monitor": {

haiku_rag_slim/haiku/rag/config/models.py

@@ -7,7 +7,6 @@ from haiku.rag.utils import get_default_data_dir
 
 class StorageConfig(BaseModel):
     data_dir: Path = Field(default_factory=get_default_data_dir)
-    disable_autocreate: bool = False
     vacuum_retention_seconds: int = 86400
 
 

haiku_rag_slim/haiku/rag/store/engine.py

@@ -50,7 +50,11 @@ class SettingsRecord(LanceModel):
 
 class Store:
     def __init__(
-        self, db_path: Path, config: AppConfig = Config, skip_validation: bool = False
+        self,
+        db_path: Path,
+        config: AppConfig = Config,
+        skip_validation: bool = False,
+        allow_create: bool = True,
     ):
         self.db_path: Path = db_path
         self._config = config
@@ -62,14 +66,14 @@ class Store:
 
         # Local filesystem handling for DB directory
         if not self._has_cloud_config():
-            if self._config.storage.disable_autocreate:
-                # LanceDB uses a directory path for local databases; enforce presence
+            if not allow_create:
+                # Read operations should not create the database
                 if not db_path.exists():
                     raise FileNotFoundError(
-                        f"LanceDB path does not exist: {db_path}. Auto-creation is disabled."
+                        f"Database does not exist: {db_path}. Use a write operation (add, add-src) to create it."
                     )
             else:
-                # Ensure parent directories exist when autocreation allowed
+                # Write operations - ensure parent directories exist
                 if not db_path.parent.exists():
                     Path.mkdir(db_path.parent, parents=True)
 

tests/conftest.py

@@ -40,7 +40,6 @@ def temp_yaml_config(tmp_path, monkeypatch):
         "storage": {
             "data_dir": "",
             "monitor_directories": [],
-            "disable_autocreate": False,
             "vacuum_retention_seconds": 60,
         },
         "embeddings": {

tests/test_database_autocreate.py

@@ -0,0 +1,105 @@
+import tempfile
+from pathlib import Path
+
+import pytest
+
+from haiku.rag.client import HaikuRAG
+from haiku.rag.config import AppConfig
+
+
+def test_read_operations_do_not_create_database():
+    """Test that read operations fail if database doesn't exist."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        db_path = Path(tmpdir) / "test.lancedb"
+
+        config = AppConfig()
+
+        # Read operation with allow_create=False should fail
+        with pytest.raises(
+            FileNotFoundError,
+            match="Database does not exist.*Use a write operation",
+        ):
+            HaikuRAG(db_path=db_path, config=config, allow_create=False)
+
+
+def test_write_operations_create_database():
+    """Test that write operations create the database."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        db_path = Path(tmpdir) / "test.lancedb"
+
+        config = AppConfig()
+
+        # Write operation with allow_create=True (default) should succeed
+        client = HaikuRAG(db_path=db_path, config=config, allow_create=True)
+        assert db_path.exists()
+        client.close()
+
+
+async def test_add_document_creates_database():
+    """Test that add operations create the database."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        db_path = Path(tmpdir) / "test.lancedb"
+
+        config = AppConfig()
+
+        # Create a document (write operation) should work and create DB
+        async with HaikuRAG(
+            db_path=db_path, config=config, allow_create=True
+        ) as client:
+            doc = await client.create_document("Test content")
+            assert doc.id is not None
+            assert doc.content == "Test content"
+            assert db_path.exists()
+
+
+async def test_search_fails_if_database_does_not_exist():
+    """Test that search operations fail if DB doesn't exist."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        db_path = Path(tmpdir) / "test.lancedb"
+
+        config = AppConfig()
+
+        # Read operation (search) should fail if DB doesn't exist
+        with pytest.raises(
+            FileNotFoundError,
+            match="Database does not exist.*Use a write operation",
+        ):
+            async with HaikuRAG(
+                db_path=db_path, config=config, allow_create=False
+            ) as client:
+                await client.search("test query")
+
+
+async def test_read_operations_work_after_database_created():
+    """Test that read operations work after DB is created via write operation."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        db_path = Path(tmpdir) / "test.lancedb"
+
+        config = AppConfig()
+
+        # First, create DB via write operation
+        async with HaikuRAG(
+            db_path=db_path, config=config, allow_create=True
+        ) as client:
+            await client.create_document("Test content", uri="test://doc1")
+
+        # Now read operations should work since DB exists
+        async with HaikuRAG(
+            db_path=db_path, config=config, allow_create=False
+        ) as client:
+            docs = await client.list_documents()
+            assert len(docs) == 1
+            assert docs[0].content == "Test content"
+
+
+def test_default_allow_create_is_true():
+    """Test that allow_create defaults to True for backward compatibility."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        db_path = Path(tmpdir) / "test.lancedb"
+
+        config = AppConfig()
+
+        # Without specifying allow_create, it should default to True
+        client = HaikuRAG(db_path=db_path, config=config)
+        assert db_path.exists()
+        client.close()