From a59b38158d64be0a4118aa3c2800f797488e7aa5 Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Sat, 12 Jul 2025 20:21:34 +0300
Subject: [PATCH 1/6] Settings table & repo, tests

---
 pyproject.toml                               |  2 +-
 src/haiku/rag/store/engine.py                | 17 +++++++++
 src/haiku/rag/store/repositories/settings.py | 36 ++++++++++++++++++++
 tests/test_settings.py                       | 33 ++++++++++++++++++
 uv.lock                                      |  8 ++---
 5 files changed, 91 insertions(+), 5 deletions(-)
 create mode 100644 src/haiku/rag/store/repositories/settings.py
 create mode 100644 tests/test_settings.py

diff --git a/pyproject.toml b/pyproject.toml
index 49237c9a..30dbb443 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -56,7 +56,7 @@ dev = [
     "mkdocs>=1.6.1",
     "mkdocs-material>=9.6.14",
     "pre-commit>=4.2.0",
-    "pyright>=1.1.402",
+    "pyright>=1.1.403",
     "pytest>=8.4.0",
     "pytest-asyncio>=1.0.0",
     "pytest-cov>=6.2.1",
diff --git a/src/haiku/rag/store/engine.py b/src/haiku/rag/store/engine.py
index cdf1d2ca..4133b6dc 100644
--- a/src/haiku/rag/store/engine.py
+++ b/src/haiku/rag/store/engine.py
@@ -60,11 +60,28 @@ class Store:
             )
         """)
 
+        # Create settings table for storing current configuration
+        db.execute("""
+            CREATE TABLE IF NOT EXISTS settings (
+                id INTEGER PRIMARY KEY DEFAULT 1,
+                settings TEXT NOT NULL DEFAULT '{}'
+            )
+        """)
+
         # Create indexes for better performance
         db.execute(
             "CREATE INDEX IF NOT EXISTS idx_chunks_document_id ON chunks(document_id)"
         )
 
+        # Save current settings to the new database
+        from haiku.rag.config import Config
+
+        settings_json = Config.model_dump_json()
+        db.execute(
+            "INSERT OR IGNORE INTO settings (id, settings) VALUES (1, ?)",
+            (settings_json,),
+        )
+
         db.commit()
         return db
 
diff --git a/src/haiku/rag/store/repositories/settings.py b/src/haiku/rag/store/repositories/settings.py
new file mode 100644
index 00000000..d51cb0d5
--- /dev/null
+++ b/src/haiku/rag/store/repositories/settings.py
@@ -0,0 +1,36 @@
+import json
+from typing import Any
+
+from haiku.rag.store.engine import Store
+
+
+class SettingsRepository:
+    def __init__(self, store: Store):
+        self.store = store
+
+    def get(self) -> dict[str, Any]:
+        """Get all settings from the database."""
+        if self.store._connection is None:
+            raise ValueError("Store connection is not available")
+
+        cursor = self.store._connection.execute("SELECT settings FROM settings LIMIT 1")
+        row = cursor.fetchone()
+        if row:
+            return json.loads(row[0])
+        return {}
+
+    def save(self) -> None:
+        """Sync settings from the current AppConfig to database."""
+        if self.store._connection is None:
+            raise ValueError("Store connection is not available")
+
+        from haiku.rag.config import Config
+
+        settings_json = Config.model_dump_json()
+
+        self.store._connection.execute(
+            "INSERT INTO settings (id, settings) VALUES (1, ?) ON CONFLICT(id) DO UPDATE SET settings = excluded.settings",
+            (settings_json,),
+        )
+
+        self.store._connection.commit()
diff --git a/tests/test_settings.py b/tests/test_settings.py
new file mode 100644
index 00000000..aaec6ac5
--- /dev/null
+++ b/tests/test_settings.py
@@ -0,0 +1,33 @@
+from haiku.rag.config import Config
+from haiku.rag.store.engine import Store
+from haiku.rag.store.repositories.settings import SettingsRepository
+
+
+def test_settings_table_populated_on_store_init():
+    """Test that settings table is populated with current config when store is initialized."""
+
+    store = Store(":memory:")
+    settings_repo = SettingsRepository(store)
+
+    db_settings = settings_repo.get()
+    config_dict = Config.model_dump(mode="json")
+
+    assert db_settings == config_dict
+
+    store.close()
+
+
+def test_settings_save_and_retrieve():
+    """Test saving and retrieving settings after config change."""
+    store = Store(":memory:")
+    settings_repo = SettingsRepository(store)
+
+    original_chunk_size = Config.CHUNK_SIZE
+    Config.CHUNK_SIZE = 2 * original_chunk_size
+
+    settings_repo.save()
+    retrieved_settings = settings_repo.get()
+    assert retrieved_settings["CHUNK_SIZE"] == 2 * original_chunk_size
+
+    Config.CHUNK_SIZE = original_chunk_size
+    store.close()
diff --git a/uv.lock b/uv.lock
index 088ad51f..fd6b3649 100644
--- a/uv.lock
+++ b/uv.lock
@@ -881,7 +881,7 @@ dev = [
     { name = "mkdocs", specifier = ">=1.6.1" },
     { name = "mkdocs-material", specifier = ">=9.6.14" },
     { name = "pre-commit", specifier = ">=4.2.0" },
-    { name = "pyright", specifier = ">=1.1.402" },
+    { name = "pyright", specifier = ">=1.1.403" },
     { name = "pytest", specifier = ">=8.4.0" },
     { name = "pytest-asyncio", specifier = ">=1.0.0" },
     { name = "pytest-cov", specifier = ">=6.2.1" },
@@ -2305,15 +2305,15 @@ wheels = [
 
 [[package]]
 name = "pyright"
-version = "1.1.402"
+version = "1.1.403"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "nodeenv" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/aa/04/ce0c132d00e20f2d2fb3b3e7c125264ca8b909e693841210534b1ea1752f/pyright-1.1.402.tar.gz", hash = "sha256:85a33c2d40cd4439c66aa946fd4ce71ab2f3f5b8c22ce36a623f59ac22937683", size = 3888207, upload-time = "2025-06-11T08:48:35.759Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fe/f6/35f885264ff08c960b23d1542038d8da86971c5d8c955cfab195a4f672d7/pyright-1.1.403.tar.gz", hash = "sha256:3ab69b9f41c67fb5bbb4d7a36243256f0d549ed3608678d381d5f51863921104", size = 3913526, upload-time = "2025-07-09T07:15:52.882Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fe/37/1a1c62d955e82adae588be8e374c7f77b165b6cb4203f7d581269959abbc/pyright-1.1.402-py3-none-any.whl", hash = "sha256:2c721f11869baac1884e846232800fe021c33f1b4acb3929cff321f7ea4e2982", size = 5624004, upload-time = "2025-06-11T08:48:33.998Z" },
+    { url = "https://files.pythonhosted.org/packages/49/b6/b04e5c2f41a5ccad74a1a4759da41adb20b4bc9d59a5e08d29ba60084d07/pyright-1.1.403-py3-none-any.whl", hash = "sha256:c0eeca5aa76cbef3fcc271259bbd785753c7ad7bcac99a9162b4c4c7daed23b3", size = 5684504, upload-time = "2025-07-09T07:15:50.958Z" },
 ]
 
 [[package]]

From 4444ec50da96e236935c7784d731631aabf113ed Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Sat, 12 Jul 2025 20:56:49 +0300
Subject: [PATCH 2/6] Check if settings are compatible when loading a db

---
 src/haiku/rag/store/engine.py                |  6 +++
 src/haiku/rag/store/repositories/settings.py | 42 ++++++++++++++++++++
 tests/test_settings.py                       | 42 +++++++++++++++++++-
 3 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/src/haiku/rag/store/engine.py b/src/haiku/rag/store/engine.py
index 4133b6dc..af7b27c4 100644
--- a/src/haiku/rag/store/engine.py
+++ b/src/haiku/rag/store/engine.py
@@ -13,6 +13,12 @@ class Store:
         self.db_path: Path | Literal[":memory:"] = db_path
         self._connection = self.create_db()
 
+        # Validate config compatibility after connection is established
+        from haiku.rag.store.repositories.settings import SettingsRepository
+
+        settings_repo = SettingsRepository(self)
+        settings_repo.validate_config_compatibility()
+
     def create_db(self) -> sqlite3.Connection:
         """Create the database and tables with sqlite-vec support for embeddings."""
         db = sqlite3.connect(self.db_path)
diff --git a/src/haiku/rag/store/repositories/settings.py b/src/haiku/rag/store/repositories/settings.py
index d51cb0d5..add87fa5 100644
--- a/src/haiku/rag/store/repositories/settings.py
+++ b/src/haiku/rag/store/repositories/settings.py
@@ -4,6 +4,12 @@ from typing import Any
 from haiku.rag.store.engine import Store
 
 
+class ConfigMismatchError(Exception):
+    """Raised when current config doesn't match stored settings."""
+
+    pass
+
+
 class SettingsRepository:
     def __init__(self, store: Store):
         self.store = store
@@ -34,3 +40,39 @@ class SettingsRepository:
         )
 
         self.store._connection.commit()
+
+    def validate_config_compatibility(self) -> None:
+        """Check if current config is compatible with stored settings.
+
+        Raises ConfigMismatchError if there are incompatible differences.
+        If no settings exist, saves current config.
+        """
+        db_settings = self.get()
+        if not db_settings:
+            # No settings in DB, save current config
+            self.save()
+            return
+
+        from haiku.rag.config import Config
+
+        current_config = Config.model_dump(mode="json")
+
+        # Critical settings that must match
+        critical_settings = [
+            "EMBEDDINGS_PROVIDER",
+            "EMBEDDINGS_MODEL",
+            "EMBEDDINGS_VECTOR_DIM",
+            "CHUNK_SIZE",
+            "CHUNK_OVERLAP",
+        ]
+
+        errors = []
+        for setting in critical_settings:
+            if db_settings.get(setting) != current_config.get(setting):
+                errors.append(
+                    f"{setting}: current={current_config.get(setting)}, stored={db_settings.get(setting)}"
+                )
+
+        if errors:
+            error_msg = f"Config mismatch detected: {'; '.join(errors)}. Consider rebuilding the database with the current configuration."
+            raise ConfigMismatchError(error_msg)
diff --git a/tests/test_settings.py b/tests/test_settings.py
index aaec6ac5..8f6f49d7 100644
--- a/tests/test_settings.py
+++ b/tests/test_settings.py
@@ -1,6 +1,14 @@
+import tempfile
+from pathlib import Path
+
+import pytest
+
 from haiku.rag.config import Config
 from haiku.rag.store.engine import Store
-from haiku.rag.store.repositories.settings import SettingsRepository
+from haiku.rag.store.repositories.settings import (
+    ConfigMismatchError,
+    SettingsRepository,
+)
 
 
 def test_settings_table_populated_on_store_init():
@@ -31,3 +39,35 @@ def test_settings_save_and_retrieve():
 
     Config.CHUNK_SIZE = original_chunk_size
     store.close()
+
+
+def test_config_validation_on_db_load():
+    """Test that config validation fails when loading db with mismatched settings."""
+    # Create a temporary database file
+    with tempfile.NamedTemporaryFile(suffix=".sqlite", delete=False) as tmp:
+        db_path = Path(tmp.name)
+
+    try:
+        # Create store and save settings
+        store1 = Store(db_path)
+        SettingsRepository(store1)
+        store1.close()
+
+        # Change config
+        original_chunk_size = Config.CHUNK_SIZE
+        Config.CHUNK_SIZE = 999
+
+        # Loading the database should raise ConfigMismatchError
+        with pytest.raises(ConfigMismatchError) as exc_info:
+            Store(db_path)
+
+        assert "CHUNK_SIZE" in str(exc_info.value)
+        assert "Consider rebuilding" in str(exc_info.value)
+
+        # Restore original config
+        Config.CHUNK_SIZE = original_chunk_size
+
+    finally:
+        # Cleanup
+        if db_path.exists():
+            db_path.unlink()

From 62a519b094cb5425e9aa558a139f461999db24df Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Sat, 12 Jul 2025 21:21:14 +0300
Subject: [PATCH 3/6] Prevent rebuild from throwing and recreate the embeddings
 table

---
 src/haiku/rag/app.py          |  2 +-
 src/haiku/rag/client.py       | 17 +++++++++++------
 src/haiku/rag/store/engine.py | 30 ++++++++++++++++++++++++++----
 tests/test_settings.py        | 16 ++++++++++++++--
 4 files changed, 52 insertions(+), 13 deletions(-)

diff --git a/src/haiku/rag/app.py b/src/haiku/rag/app.py
index dedfce4c..0e2d1822 100644
--- a/src/haiku/rag/app.py
+++ b/src/haiku/rag/app.py
@@ -74,7 +74,7 @@ class HaikuRAGApp:
                 self.console.print(f"[red]Error: {e}[/red]")
 
     async def rebuild(self):
-        async with HaikuRAG(db_path=self.db_path) as client:
+        async with HaikuRAG(db_path=self.db_path, skip_validation=True) as client:
             try:
                 documents = await client.list_documents()
                 total_docs = len(documents)
diff --git a/src/haiku/rag/client.py b/src/haiku/rag/client.py
index 74478654..72e5b0a6 100644
--- a/src/haiku/rag/client.py
+++ b/src/haiku/rag/client.py
@@ -24,12 +24,13 @@ class HaikuRAG:
         self,
         db_path: Path | Literal[":memory:"] = Config.DEFAULT_DATA_DIR
         / "haiku.rag.sqlite",
+        skip_validation: bool = False,
     ):
         """Initialize the RAG client with a database path."""
         if isinstance(db_path, Path):
             if not db_path.parent.exists():
                 Path.mkdir(db_path.parent, parents=True)
-        self.store = Store(db_path)
+        self.store = Store(db_path, skip_validation=skip_validation)
         self.document_repository = DocumentRepository(self.store)
         self.chunk_repository = ChunkRepository(self.store)
 
@@ -277,12 +278,16 @@ class HaikuRAG:
         Yields:
             int: The ID of the document currently being processed
         """
-        documents = await self.list_documents()
-
-        if not documents:
-            return
-
         await self.chunk_repository.delete_all()
+        self.store.recreate_embeddings_table()
+
+        # Update settings to current config
+        from haiku.rag.store.repositories.settings import SettingsRepository
+
+        settings_repo = SettingsRepository(self.store)
+        settings_repo.save()
+
+        documents = await self.list_documents()
 
         for doc in documents:
             if doc.id is not None:
diff --git a/src/haiku/rag/store/engine.py b/src/haiku/rag/store/engine.py
index af7b27c4..a2701ddf 100644
--- a/src/haiku/rag/store/engine.py
+++ b/src/haiku/rag/store/engine.py
@@ -9,15 +9,18 @@ from haiku.rag.embeddings import get_embedder
 
 
 class Store:
-    def __init__(self, db_path: Path | Literal[":memory:"]):
+    def __init__(
+        self, db_path: Path | Literal[":memory:"], skip_validation: bool = False
+    ):
         self.db_path: Path | Literal[":memory:"] = db_path
         self._connection = self.create_db()
 
         # Validate config compatibility after connection is established
-        from haiku.rag.store.repositories.settings import SettingsRepository
+        if not skip_validation:
+            from haiku.rag.store.repositories.settings import SettingsRepository
 
-        settings_repo = SettingsRepository(self)
-        settings_repo.validate_config_compatibility()
+            settings_repo = SettingsRepository(self)
+            settings_repo.validate_config_compatibility()
 
     def create_db(self) -> sqlite3.Connection:
         """Create the database and tables with sqlite-vec support for embeddings."""
@@ -91,6 +94,25 @@ class Store:
         db.commit()
         return db
 
+    def recreate_embeddings_table(self) -> None:
+        """Recreate the embeddings table with current vector dimensions."""
+        if self._connection is None:
+            raise ValueError("Store connection is not available")
+
+        # Drop existing embeddings table
+        self._connection.execute("DROP TABLE IF EXISTS chunk_embeddings")
+
+        # Recreate with current dimensions
+        embedder = get_embedder()
+        self._connection.execute(f"""
+            CREATE VIRTUAL TABLE chunk_embeddings USING vec0(
+                chunk_id INTEGER PRIMARY KEY,
+                embedding FLOAT[{embedder._vector_dim}]
+            )
+        """)
+
+        self._connection.commit()
+
     @staticmethod
     def serialize_embedding(embedding: list[float]) -> bytes:
         """Serialize a list of floats to bytes for sqlite-vec storage."""
diff --git a/tests/test_settings.py b/tests/test_settings.py
index 8f6f49d7..0db16cc8 100644
--- a/tests/test_settings.py
+++ b/tests/test_settings.py
@@ -3,6 +3,7 @@ from pathlib import Path
 
 import pytest
 
+from haiku.rag.client import HaikuRAG
 from haiku.rag.config import Config
 from haiku.rag.store.engine import Store
 from haiku.rag.store.repositories.settings import (
@@ -41,7 +42,7 @@ def test_settings_save_and_retrieve():
     store.close()
 
 
-def test_config_validation_on_db_load():
+async def test_config_validation_on_db_load():
     """Test that config validation fails when loading db with mismatched settings."""
     # Create a temporary database file
     with tempfile.NamedTemporaryFile(suffix=".sqlite", delete=False) as tmp:
@@ -64,7 +65,18 @@ def test_config_validation_on_db_load():
         assert "CHUNK_SIZE" in str(exc_info.value)
         assert "Consider rebuilding" in str(exc_info.value)
 
-        # Restore original config
+        # Rebuild
+        async with HaikuRAG(db_path=db_path, skip_validation=True) as client:
+            async for _ in client.rebuild_database():
+                pass  # Process all documents
+
+        # Verify we can now load the database without exception (settings were updated)
+        store2 = Store(db_path)
+        settings_repo2 = SettingsRepository(store2)
+        db_settings = settings_repo2.get()
+        assert db_settings["CHUNK_SIZE"] == 999
+        store2.close()
+
         Config.CHUNK_SIZE = original_chunk_size
 
     finally:

From a2e0f2cefd50fabb9f3beac535913feea927ce3f Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Sat, 12 Jul 2025 23:00:49 +0300
Subject: [PATCH 4/6] Remove Claude nonsense, use context manager

---
 src/haiku/rag/client.py |  27 +-
 tests/test_client.py    | 638 +++++++++++++++++++---------------------
 tests/test_monitor.py   |  20 +-
 tests/test_rebuild.py   |  71 +++--
 tests/test_settings.py  |  42 ++-
 5 files changed, 366 insertions(+), 432 deletions(-)

diff --git a/src/haiku/rag/client.py b/src/haiku/rag/client.py
index 72e5b0a6..ca30098c 100644
--- a/src/haiku/rag/client.py
+++ b/src/haiku/rag/client.py
@@ -166,29 +166,26 @@ class HaikuRAG:
 
             # Create a temporary file with the appropriate extension
             with tempfile.NamedTemporaryFile(
-                mode="wb", suffix=file_extension, delete=False
+                mode="wb", suffix=file_extension
             ) as temp_file:
                 temp_file.write(response.content)
+                temp_file.flush()  # Ensure content is written to disk
                 temp_path = Path(temp_file.name)
 
-            try:
                 # Parse the content using FileReader
                 content = FileReader.parse_file(temp_path)
 
-                # Merge metadata with contentType and md5
-                metadata.update({"contentType": content_type, "md5": md5_hash})
+            # Merge metadata with contentType and md5
+            metadata.update({"contentType": content_type, "md5": md5_hash})
 
-                if existing_doc:
-                    existing_doc.content = content
-                    existing_doc.metadata = metadata
-                    return await self.update_document(existing_doc)
-                else:
-                    return await self.create_document(
-                        content=content, uri=url, metadata=metadata
-                    )
-            finally:
-                # Clean up temporary file
-                temp_path.unlink(missing_ok=True)
+            if existing_doc:
+                existing_doc.content = content
+                existing_doc.metadata = metadata
+                return await self.update_document(existing_doc)
+            else:
+                return await self.create_document(
+                    content=content, uri=url, metadata=metadata
+                )
 
     def _get_extension_from_content_type_or_url(
         self, url: str, content_type: str
diff --git a/tests/test_client.py b/tests/test_client.py
index 086facc0..c5aaeb1c 100644
--- a/tests/test_client.py
+++ b/tests/test_client.py
@@ -12,300 +12,270 @@ from haiku.rag.client import HaikuRAG
 @pytest.mark.asyncio
 async def test_client_document_crud(qa_corpus: Dataset):
     """Test HaikuRAG CRUD operations for documents."""
-    # Create client with in-memory database
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Get test data
+        first_doc = qa_corpus[0]
+        document_text = first_doc["document_extracted"]
+        test_uri = "file:///path/to/test.txt"
+        test_metadata = {"source": "test", "topic": "testing"}
 
-    # Get test data
-    first_doc = qa_corpus[0]
-    document_text = first_doc["document_extracted"]
-    test_uri = "file:///path/to/test.txt"
-    test_metadata = {"source": "test", "topic": "testing"}
+        # Test create_document
+        created_doc = await client.create_document(
+            content=document_text, uri=test_uri, metadata=test_metadata
+        )
 
-    # Test create_document
-    created_doc = await client.create_document(
-        content=document_text, uri=test_uri, metadata=test_metadata
-    )
+        assert created_doc.id is not None
+        assert created_doc.content == document_text
+        assert created_doc.uri == test_uri
+        assert created_doc.metadata == test_metadata
 
-    assert created_doc.id is not None
-    assert created_doc.content == document_text
-    assert created_doc.uri == test_uri
-    assert created_doc.metadata == test_metadata
+        # Test get_document_by_id
+        retrieved_doc = await client.get_document_by_id(created_doc.id)
+        assert retrieved_doc is not None
+        assert retrieved_doc.id == created_doc.id
+        assert retrieved_doc.content == document_text
+        assert retrieved_doc.uri == test_uri
 
-    # Test get_document_by_id
-    retrieved_doc = await client.get_document_by_id(created_doc.id)
-    assert retrieved_doc is not None
-    assert retrieved_doc.id == created_doc.id
-    assert retrieved_doc.content == document_text
-    assert retrieved_doc.uri == test_uri
+        # Test get_document_by_uri
+        retrieved_by_uri = await client.get_document_by_uri(test_uri)
+        assert retrieved_by_uri is not None
+        assert retrieved_by_uri.id == created_doc.id
+        assert retrieved_by_uri.content == document_text
 
-    # Test get_document_by_uri
-    retrieved_by_uri = await client.get_document_by_uri(test_uri)
-    assert retrieved_by_uri is not None
-    assert retrieved_by_uri.id == created_doc.id
-    assert retrieved_by_uri.content == document_text
+        # Test get_document_by_uri with non-existent URI
+        non_existent = await client.get_document_by_uri("file:///non/existent.txt")
+        assert non_existent is None
 
-    # Test get_document_by_uri with non-existent URI
-    non_existent = await client.get_document_by_uri("file:///non/existent.txt")
-    assert non_existent is None
+        # Test update_document
+        retrieved_doc.content = "Updated content"
+        retrieved_doc.uri = "file:///updated/path.txt"
+        updated_doc = await client.update_document(retrieved_doc)
+        assert updated_doc.content == "Updated content"
+        assert updated_doc.uri == "file:///updated/path.txt"
 
-    # Test update_document
-    retrieved_doc.content = "Updated content"
-    retrieved_doc.uri = "file:///updated/path.txt"
-    updated_doc = await client.update_document(retrieved_doc)
-    assert updated_doc.content == "Updated content"
-    assert updated_doc.uri == "file:///updated/path.txt"
+        # Test list_documents
+        all_docs = await client.list_documents()
+        assert len(all_docs) == 1
+        assert all_docs[0].id == created_doc.id
 
-    # Test list_documents
-    all_docs = await client.list_documents()
-    assert len(all_docs) == 1
-    assert all_docs[0].id == created_doc.id
+        # Test list_documents with pagination
+        limited_docs = await client.list_documents(limit=10, offset=0)
+        assert len(limited_docs) == 1
 
-    # Test list_documents with pagination
-    limited_docs = await client.list_documents(limit=10, offset=0)
-    assert len(limited_docs) == 1
+        # Test delete_document
+        deleted = await client.delete_document(created_doc.id)
+        assert deleted is True
 
-    # Test delete_document
-    deleted = await client.delete_document(created_doc.id)
-    assert deleted is True
+        # Verify document is gone
+        retrieved_doc = await client.get_document_by_id(created_doc.id)
+        assert retrieved_doc is None
 
-    # Verify document is gone
-    retrieved_doc = await client.get_document_by_id(created_doc.id)
-    assert retrieved_doc is None
-
-    # Test delete non-existent document
-    deleted_again = await client.delete_document(created_doc.id)
-    assert deleted_again is False
-
-    client.close()
+        # Test delete non-existent document
+        deleted_again = await client.delete_document(created_doc.id)
+        assert deleted_again is False
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_source():
     """Test creating a document from a file source."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            test_content = "This is test content from a file."
+            temp_path = Path(temp_dir) / "test.txt"
+            temp_path.write_text(test_content)
 
-    # Create a temporary text file
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-        test_content = "This is test content from a file."
-        f.write(test_content)
-        temp_path = Path(f.name)
+            # Test create_document_from_source with Path
+            doc = await client.create_document_from_source(source=temp_path)
 
-    try:
-        # Test create_document_from_source with Path
-        doc = await client.create_document_from_source(
-            source=temp_path, metadata={"source_type": "file"}
-        )
+            assert doc.id is not None
+            assert doc.content == test_content
+            assert doc.uri == temp_path.as_uri()
+            assert "contentType" in doc.metadata
+            assert "md5" in doc.metadata
+            assert doc.metadata["contentType"] == "text/plain"
 
-        assert doc.id is not None
-        assert doc.content == test_content
-        assert doc.uri == temp_path.as_uri()
-        assert doc.metadata["source_type"] == "file"
-        assert "contentType" in doc.metadata
-        assert "md5" in doc.metadata
-        assert doc.metadata["contentType"] == "text/plain"
+            # Test create_document_from_source with string path
+            doc2 = await client.create_document_from_source(source=str(temp_path))
 
-        # Test create_document_from_source with string path
-        doc2 = await client.create_document_from_source(source=str(temp_path))
-
-        assert doc2.id is not None
-        assert doc2.content == test_content
-        assert doc2.uri == temp_path.as_uri()
-        assert "contentType" in doc2.metadata
-        assert "md5" in doc2.metadata
-
-    finally:
-        # Clean up
-        temp_path.unlink()
-        client.close()
+            assert doc2.id is not None
+            assert doc2.content == test_content
+            assert doc2.uri == temp_path.as_uri()
+            assert "contentType" in doc2.metadata
+            assert "md5" in doc2.metadata
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_source_unsupported():
     """Test creating a document from an unsupported file type."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Create a temporary file with unsupported extension
+        with tempfile.NamedTemporaryFile(
+            mode="w", suffix=".unsupported", delete=False
+        ) as f:
+            f.write("content")
+            temp_path = Path(f.name)
 
-    # Create a temporary file with unsupported extension
-    with tempfile.NamedTemporaryFile(
-        mode="w", suffix=".unsupported", delete=False
-    ) as f:
-        f.write("content")
-        temp_path = Path(f.name)
-
-    try:
-        # Should raise ValueError for unsupported extension
-        with pytest.raises(ValueError, match="Unsupported file extension"):
-            await client.create_document_from_source(temp_path)
-
-    finally:
-        temp_path.unlink()
-        client.close()
+            # Should raise ValueError for unsupported extension
+            with pytest.raises(ValueError, match="Unsupported file extension"):
+                await client.create_document_from_source(temp_path)
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_source_nonexistent():
     """Test creating a document from a non-existent file."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        non_existent_path = Path("/non/existent/file.txt")
 
-    non_existent_path = Path("/non/existent/file.txt")
-
-    # Should raise ValueError when file doesn't exist
-    with pytest.raises(ValueError, match="File does not exist"):
-        await client.create_document_from_source(non_existent_path)
-
-    client.close()
+        # Should raise ValueError when file doesn't exist
+        with pytest.raises(ValueError, match="File does not exist"):
+            await client.create_document_from_source(non_existent_path)
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_url():
     """Test creating a document from a URL."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Mock the HTTP response
+        mock_response = AsyncMock()
+        mock_response.content = b"<html><body><h1>Test Page</h1><p>This is test content from a webpage.</p></body></html>"
+        mock_response.headers = {"content-type": "text/html"}
+        mock_response.raise_for_status = AsyncMock()
 
-    # Mock the HTTP response
-    mock_response = AsyncMock()
-    mock_response.content = b"<html><body><h1>Test Page</h1><p>This is test content from a webpage.</p></body></html>"
-    mock_response.headers = {"content-type": "text/html"}
-    mock_response.raise_for_status = AsyncMock()
+        with patch("httpx.AsyncClient.get", return_value=mock_response):
+            doc = await client.create_document_from_source(
+                source="https://example.com/test.html", metadata={"source_type": "web"}
+            )
 
-    with patch("httpx.AsyncClient.get", return_value=mock_response):
-        doc = await client.create_document_from_source(
-            source="https://example.com/test.html", metadata={"source_type": "web"}
-        )
-
-        assert doc.id is not None
-        assert "Test Page" in doc.content
-        assert "test content" in doc.content
-        assert doc.uri == "https://example.com/test.html"
-        assert doc.metadata["source_type"] == "web"
-        assert "contentType" in doc.metadata
-        assert "md5" in doc.metadata
-        assert doc.metadata["contentType"] == "text/html"
-
-    client.close()
+            assert doc.id is not None
+            assert "Test Page" in doc.content
+            assert "test content" in doc.content
+            assert doc.uri == "https://example.com/test.html"
+            assert doc.metadata["source_type"] == "web"
+            assert "contentType" in doc.metadata
+            assert "md5" in doc.metadata
+            assert doc.metadata["contentType"] == "text/html"
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_url_with_different_content_types():
     """Test creating documents from URLs with different content types."""
-    client = HaikuRAG(":memory:")
-
-    # Test JSON content
-    mock_json_response = AsyncMock()
-    mock_json_response.content = (
-        b'{"title": "Test JSON", "content": "This is JSON content"}'
-    )
-    mock_json_response.headers = {"content-type": "application/json"}
-    mock_json_response.raise_for_status = AsyncMock()
-
-    with patch("httpx.AsyncClient.get", return_value=mock_json_response):
-        doc = await client.create_document_from_source(
-            "https://api.example.com/data.json"
+    async with HaikuRAG(":memory:") as client:
+        # Test JSON content
+        mock_json_response = AsyncMock()
+        mock_json_response.content = (
+            b'{"title": "Test JSON", "content": "This is JSON content"}'
         )
+        mock_json_response.headers = {"content-type": "application/json"}
+        mock_json_response.raise_for_status = AsyncMock()
 
-        assert doc.id is not None
-        assert "Test JSON" in doc.content
-        assert doc.uri == "https://api.example.com/data.json"
-        assert "contentType" in doc.metadata
-        assert "md5" in doc.metadata
-        assert doc.metadata["contentType"] == "application/json"
+        with patch("httpx.AsyncClient.get", return_value=mock_json_response):
+            doc = await client.create_document_from_source(
+                "https://api.example.com/data.json"
+            )
 
-    # Test plain text content
-    mock_text_response = AsyncMock()
-    mock_text_response.content = b"This is plain text content from a URL."
-    mock_text_response.headers = {"content-type": "text/plain"}
-    mock_text_response.raise_for_status = AsyncMock()
+            assert doc.id is not None
+            assert "Test JSON" in doc.content
+            assert doc.uri == "https://api.example.com/data.json"
+            assert "contentType" in doc.metadata
+            assert "md5" in doc.metadata
+            assert doc.metadata["contentType"] == "application/json"
 
-    with patch("httpx.AsyncClient.get", return_value=mock_text_response):
-        doc = await client.create_document_from_source("https://example.com/readme.txt")
+        # Test plain text content
+        mock_text_response = AsyncMock()
+        mock_text_response.content = b"This is plain text content from a URL."
+        mock_text_response.headers = {"content-type": "text/plain"}
+        mock_text_response.raise_for_status = AsyncMock()
 
-        assert doc.id is not None
-        assert doc.content == "This is plain text content from a URL."
-        assert doc.uri == "https://example.com/readme.txt"
-        assert "contentType" in doc.metadata
-        assert "md5" in doc.metadata
-        assert doc.metadata["contentType"] == "text/plain"
+        with patch("httpx.AsyncClient.get", return_value=mock_text_response):
+            doc = await client.create_document_from_source(
+                "https://example.com/readme.txt"
+            )
 
-    client.close()
+            assert doc.id is not None
+            assert doc.content == "This is plain text content from a URL."
+            assert doc.uri == "https://example.com/readme.txt"
+            assert "contentType" in doc.metadata
+            assert "md5" in doc.metadata
+            assert doc.metadata["contentType"] == "text/plain"
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_url_unsupported_content():
     """Test creating a document from URL with unsupported content type."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Mock response with unsupported content type
+        mock_response = AsyncMock()
+        mock_response.content = b"binary content"
+        mock_response.headers = {"content-type": "application/octet-stream"}
+        mock_response.raise_for_status = AsyncMock()
 
-    # Mock response with unsupported content type
-    mock_response = AsyncMock()
-    mock_response.content = b"binary content"
-    mock_response.headers = {"content-type": "application/octet-stream"}
-    mock_response.raise_for_status = AsyncMock()
-
-    with patch("httpx.AsyncClient.get", return_value=mock_response):
-        with pytest.raises(ValueError, match="Unsupported content type"):
-            await client.create_document_from_source("https://example.com/binary.bin")
-
-    client.close()
+        with patch("httpx.AsyncClient.get", return_value=mock_response):
+            with pytest.raises(ValueError, match="Unsupported content type"):
+                await client.create_document_from_source(
+                    "https://example.com/binary.bin"
+                )
 
 
 @pytest.mark.asyncio
 async def test_client_create_document_from_url_http_error():
     """Test handling HTTP errors when creating document from URL."""
-    client = HaikuRAG(":memory:")
-
-    with patch("httpx.AsyncClient.get") as mock_get:
-        mock_get.side_effect = httpx.HTTPStatusError(
-            "404 Not Found",
-            request=httpx.Request("GET", "https://example.com/notfound.html"),
-            response=httpx.Response(404),
-        )
-
-        with pytest.raises(httpx.HTTPStatusError):
-            await client.create_document_from_source(
-                "https://example.com/notfound.html"
+    async with HaikuRAG(":memory:") as client:
+        with patch("httpx.AsyncClient.get") as mock_get:
+            mock_get.side_effect = httpx.HTTPStatusError(
+                "404 Not Found",
+                request=httpx.Request("GET", "https://example.com/notfound.html"),
+                response=httpx.Response(404),
             )
 
-    client.close()
+            with pytest.raises(httpx.HTTPStatusError):
+                await client.create_document_from_source(
+                    "https://example.com/notfound.html"
+                )
 
 
 @pytest.mark.asyncio
 async def test_get_extension_from_content_type_or_url():
     """Test the helper method for determining file extensions."""
-    client = HaikuRAG(":memory:")
-
-    # Test content type mappings
-    assert client._get_extension_from_content_type_or_url("", "text/html") == ".html"
-    assert (
-        client._get_extension_from_content_type_or_url("", "application/pdf") == ".pdf"
-    )
-    assert client._get_extension_from_content_type_or_url("", "text/plain") == ".txt"
-
-    # Test URL extension detection
-    assert (
-        client._get_extension_from_content_type_or_url(
-            "https://example.com/doc.pdf", ""
+    async with HaikuRAG(":memory:") as client:
+        # Test content type mappings
+        assert (
+            client._get_extension_from_content_type_or_url("", "text/html") == ".html"
         )
-        == ".pdf"
-    )
-    assert (
-        client._get_extension_from_content_type_or_url(
-            "https://example.com/data.json", ""
+        assert (
+            client._get_extension_from_content_type_or_url("", "application/pdf")
+            == ".pdf"
         )
-        == ".json"
-    )
-
-    # Test default fallback
-    assert (
-        client._get_extension_from_content_type_or_url("https://example.com/", "")
-        == ".html"
-    )
-
-    # Test content type priority over URL extension
-    assert (
-        client._get_extension_from_content_type_or_url(
-            "https://example.com/file.txt", "application/pdf"
+        assert (
+            client._get_extension_from_content_type_or_url("", "text/plain") == ".txt"
         )
-        == ".pdf"
-    )
 
-    client.close()
+        # Test URL extension detection
+        assert (
+            client._get_extension_from_content_type_or_url(
+                "https://example.com/doc.pdf", ""
+            )
+            == ".pdf"
+        )
+        assert (
+            client._get_extension_from_content_type_or_url(
+                "https://example.com/data.json", ""
+            )
+            == ".json"
+        )
+
+        # Test default fallback
+        assert (
+            client._get_extension_from_content_type_or_url("https://example.com/", "")
+            == ".html"
+        )
+
+        # Test content type priority over URL extension
+        assert (
+            client._get_extension_from_content_type_or_url(
+                "https://example.com/file.txt", "application/pdf"
+            )
+            == ".pdf"
+        )
 
 
 @pytest.mark.asyncio
@@ -313,165 +283,147 @@ async def test_client_metadata_content_type_and_md5():
     """Test that contentType and md5 metadata are correctly set."""
     import hashlib
 
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Create a temporary file with known content
+        test_content = "Test content for MD5 calculation."
+        expected_md5 = hashlib.md5(test_content.encode()).hexdigest()
 
-    # Create a temporary file with known content
-    test_content = "Test content for MD5 calculation."
-    expected_md5 = hashlib.md5(test_content.encode()).hexdigest()
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_path = Path(temp_dir) / "test.txt"
+            temp_path.write_text(test_content)
 
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-        f.write(test_content)
-        temp_path = Path(f.name)
+            doc = await client.create_document_from_source(temp_path)
 
-    try:
-        doc = await client.create_document_from_source(temp_path)
+            assert doc.metadata["contentType"] == "text/plain"
+            assert doc.metadata["md5"] == expected_md5
 
-        assert doc.metadata["contentType"] == "text/plain"
-        assert doc.metadata["md5"] == expected_md5
+            mock_response = AsyncMock()
+            mock_response.content = test_content.encode()
+            mock_response.headers = {"content-type": "text/plain"}
+            mock_response.raise_for_status = AsyncMock()
 
-        mock_response = AsyncMock()
-        mock_response.content = test_content.encode()
-        mock_response.headers = {"content-type": "text/plain"}
-        mock_response.raise_for_status = AsyncMock()
+            with patch("httpx.AsyncClient.get", return_value=mock_response):
+                url_doc = await client.create_document_from_source(
+                    "https://example.com/test.txt"
+                )
 
-        with patch("httpx.AsyncClient.get", return_value=mock_response):
-            url_doc = await client.create_document_from_source(
-                "https://example.com/test.txt"
-            )
-
-            assert url_doc.metadata["contentType"] == "text/plain"
-            assert url_doc.metadata["md5"] == expected_md5
-
-    finally:
-        temp_path.unlink()
-        client.close()
+                assert url_doc.metadata["contentType"] == "text/plain"
+                assert url_doc.metadata["md5"] == expected_md5
 
 
 @pytest.mark.asyncio
 async def test_client_create_update_no_op_behavior():
     """Test create/update/no-op behavior based on MD5 changes."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Create a temporary file
+        test_content = "Original content for testing."
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_path = Path(temp_dir) / "test.txt"
+            temp_path.write_text(test_content)
 
-    # Create a temporary file
-    test_content = "Original content for testing."
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-        f.write(test_content)
-        temp_path = Path(f.name)
+            # First call - should create new document
+            doc1 = await client.create_document_from_source(temp_path)
+            assert doc1.id is not None
+            assert doc1.content == test_content
+            original_id = doc1.id
 
-    try:
-        # First call - should create new document
-        doc1 = await client.create_document_from_source(temp_path)
-        assert doc1.id is not None
-        assert doc1.content == test_content
-        original_id = doc1.id
+            # Second call with same content - should return existing document (no-op)
+            doc2 = await client.create_document_from_source(temp_path)
+            assert doc2.id == original_id  # Same document
+            assert doc2.content == test_content
 
-        # Second call with same content - should return existing document (no-op)
-        doc2 = await client.create_document_from_source(temp_path)
-        assert doc2.id == original_id  # Same document
-        assert doc2.content == test_content
+            # Modify file content
+            updated_content = "Updated content for testing."
+            temp_path.write_text(updated_content)
 
-        # Modify file content
-        updated_content = "Updated content for testing."
-        temp_path.write_text(updated_content)
+            # Third call with changed content - should update existing document
+            doc3 = await client.create_document_from_source(temp_path)
+            assert doc3.id == original_id  # Same document ID
+            assert doc3.content == updated_content  # Updated content
 
-        # Third call with changed content - should update existing document
-        doc3 = await client.create_document_from_source(temp_path)
-        assert doc3.id == original_id  # Same document ID
-        assert doc3.content == updated_content  # Updated content
-
-        # Verify the document was actually updated in database
-        retrieved_doc = await client.get_document_by_id(original_id)
-        assert retrieved_doc is not None
-        assert retrieved_doc.content == updated_content
-
-    finally:
-        temp_path.unlink()
-        client.close()
+            # Verify the document was actually updated in database
+            retrieved_doc = await client.get_document_by_id(original_id)
+            assert retrieved_doc is not None
+            assert retrieved_doc.content == updated_content
 
 
 @pytest.mark.asyncio
 async def test_client_url_create_update_no_op_behavior():
     """Test create/update/no-op behavior for URLs based on MD5 changes."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        url = "https://example.com/test.txt"
+        original_content = b"Original URL content"
+        updated_content = b"Updated URL content"
 
-    url = "https://example.com/test.txt"
-    original_content = b"Original URL content"
-    updated_content = b"Updated URL content"
+        # Mock first response
+        mock_response1 = AsyncMock()
+        mock_response1.content = original_content
+        mock_response1.headers = {"content-type": "text/plain"}
+        mock_response1.raise_for_status = AsyncMock()
 
-    # Mock first response
-    mock_response1 = AsyncMock()
-    mock_response1.content = original_content
-    mock_response1.headers = {"content-type": "text/plain"}
-    mock_response1.raise_for_status = AsyncMock()
+        with patch("httpx.AsyncClient.get", return_value=mock_response1):
+            # First call - should create new document
+            doc1 = await client.create_document_from_source(url)
+            assert doc1.id is not None
+            original_id = doc1.id
 
-    with patch("httpx.AsyncClient.get", return_value=mock_response1):
-        # First call - should create new document
-        doc1 = await client.create_document_from_source(url)
-        assert doc1.id is not None
-        original_id = doc1.id
+            # Second call with same content - should return existing document (no-op)
+            doc2 = await client.create_document_from_source(url)
+            assert doc2.id == original_id  # Same document
 
-        # Second call with same content - should return existing document (no-op)
-        doc2 = await client.create_document_from_source(url)
-        assert doc2.id == original_id  # Same document
+        mock_response2 = AsyncMock()
+        mock_response2.content = updated_content
+        mock_response2.headers = {"content-type": "text/plain"}
+        mock_response2.raise_for_status = AsyncMock()
 
-    mock_response2 = AsyncMock()
-    mock_response2.content = updated_content
-    mock_response2.headers = {"content-type": "text/plain"}
-    mock_response2.raise_for_status = AsyncMock()
-
-    with patch("httpx.AsyncClient.get", return_value=mock_response2):
-        # Third call with changed content - should update existing document
-        doc3 = await client.create_document_from_source(url)
-        assert doc3.id == original_id  # Same document ID
-        assert doc3.content == updated_content.decode()  # Updated content
-
-    client.close()
+        with patch("httpx.AsyncClient.get", return_value=mock_response2):
+            # Third call with changed content - should update existing document
+            doc3 = await client.create_document_from_source(url)
+            assert doc3.id == original_id  # Same document ID
+            assert doc3.content == updated_content.decode()  # Updated content
 
 
 @pytest.mark.asyncio
 async def test_client_search():
     """Test HaikuRAG search functionality."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        # Add multiple documents to search from
+        doc1_text = "Python is a high-level programming language known for its simplicity and readability."
+        doc2_text = "Machine learning algorithms help computers learn patterns from data without explicit programming."
+        doc3_text = "Data science combines statistics, programming, and domain expertise to extract insights."
 
-    # Add multiple documents to search from
-    doc1_text = "Python is a high-level programming language known for its simplicity and readability."
-    doc2_text = "Machine learning algorithms help computers learn patterns from data without explicit programming."
-    doc3_text = "Data science combines statistics, programming, and domain expertise to extract insights."
+        # Create documents
+        doc1 = await client.create_document(
+            content=doc1_text, uri="doc1.txt", metadata={"topic": "python"}
+        )
+        doc2 = await client.create_document(
+            content=doc2_text, uri="doc2.txt", metadata={"topic": "ml"}
+        )
+        await client.create_document(
+            content=doc3_text, uri="doc3.txt", metadata={"topic": "data_science"}
+        )
 
-    # Create documents
-    doc1 = await client.create_document(
-        content=doc1_text, uri="doc1.txt", metadata={"topic": "python"}
-    )
-    doc2 = await client.create_document(
-        content=doc2_text, uri="doc2.txt", metadata={"topic": "ml"}
-    )
-    await client.create_document(
-        content=doc3_text, uri="doc3.txt", metadata={"topic": "data_science"}
-    )
+        # Test search with keyword that should match doc1
+        results = await client.search("Python programming", limit=3)
 
-    # Test search with keyword that should match doc1
-    results = await client.search("Python programming", limit=3)
+        assert len(results) > 0
+        assert all(len(result) == 2 for result in results)
 
-    assert len(results) > 0
-    assert all(len(result) == 2 for result in results)
+        # Verify first result is from the Python document (doc1)
+        first_chunk, _ = results[0]
+        assert first_chunk.document_id == doc1.id
 
-    # Verify first result is from the Python document (doc1)
-    first_chunk, _ = results[0]
-    assert first_chunk.document_id == doc1.id
+        # Test search with different query
+        ml_results = await client.search("machine learning data", limit=2)
+        assert len(ml_results) > 0
 
-    # Test search with different query
-    ml_results = await client.search("machine learning data", limit=2)
-    assert len(ml_results) > 0
+        # Verify first result is from the machine learning document (doc2)
+        first_ml_chunk, _ = ml_results[0]
+        assert first_ml_chunk.document_id == doc2.id
 
-    # Verify first result is from the machine learning document (doc2)
-    first_ml_chunk, _ = ml_results[0]
-    assert first_ml_chunk.document_id == doc2.id
-
-    # Test search with limit parameter
-    limited_results = await client.search("programming", limit=1)
-    assert len(limited_results) <= 1
-
-    client.close()
+        # Test search with limit parameter
+        limited_results = await client.search("programming", limit=1)
+        assert len(limited_results) <= 1
 
 
 @pytest.mark.asyncio
diff --git a/tests/test_monitor.py b/tests/test_monitor.py
index ac909631..73992416 100644
--- a/tests/test_monitor.py
+++ b/tests/test_monitor.py
@@ -13,11 +13,10 @@ from haiku.rag.store.models.document import Document
 async def test_file_watcher_upsert_document():
     """Test FileWatcher._upsert_document method."""
 
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-        f.write("Test content for file watcher")
-        temp_path = Path(f.name)
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_path = Path(temp_dir) / "test.txt"
+        temp_path.write_text("Test content for file watcher")
 
-    try:
         mock_client = AsyncMock(spec=HaikuRAG)
         mock_doc = Document(id=1, content="Test content", uri=temp_path.as_uri())
         mock_client.create_document_from_source.return_value = mock_doc
@@ -32,19 +31,15 @@ async def test_file_watcher_upsert_document():
         mock_client.get_document_by_uri.assert_called_once_with(temp_path.as_uri())
         mock_client.create_document_from_source.assert_called_once_with(str(temp_path))
 
-    finally:
-        temp_path.unlink(missing_ok=True)
-
 
 @pytest.mark.asyncio
 async def test_file_watcher_upsert_existing_document():
     """Test FileWatcher._upsert_document with existing document."""
 
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-        f.write("Test content for file watcher")
-        temp_path = Path(f.name)
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_path = Path(temp_dir) / "test.txt"
+        temp_path.write_text("Test content for file watcher")
 
-    try:
         mock_client = AsyncMock(spec=HaikuRAG)
         existing_doc = Document(id=1, content="Old content", uri=temp_path.as_uri())
         updated_doc = Document(id=1, content="Updated content", uri=temp_path.as_uri())
@@ -61,9 +56,6 @@ async def test_file_watcher_upsert_existing_document():
         mock_client.get_document_by_uri.assert_called_once_with(temp_path.as_uri())
         mock_client.create_document_from_source.assert_called_once_with(str(temp_path))
 
-    finally:
-        temp_path.unlink(missing_ok=True)
-
 
 @pytest.mark.asyncio
 async def test_file_watcher_delete_document():
diff --git a/tests/test_rebuild.py b/tests/test_rebuild.py
index 3254ce1d..04fd8533 100644
--- a/tests/test_rebuild.py
+++ b/tests/test_rebuild.py
@@ -8,45 +8,42 @@ from haiku.rag.store.models.document import Document
 @pytest.mark.asyncio
 async def test_rebuild_database(qa_corpus: Dataset):
     """Test rebuild functionality with existing documents."""
-    client = HaikuRAG(":memory:")
+    async with HaikuRAG(":memory:") as client:
+        created_docs: list[Document] = []
+        for content in qa_corpus["document_extracted"][:3]:
+            doc = await client.create_document(
+                content=content,
+            )
+            created_docs.append(doc)
 
-    created_docs: list[Document] = []
-    for content in qa_corpus["document_extracted"][:3]:
-        doc = await client.create_document(
-            content=content,
-        )
-        created_docs.append(doc)
+        documents_before = await client.list_documents()
+        assert len(documents_before) == 3
 
-    documents_before = await client.list_documents()
-    assert len(documents_before) == 3
-
-    chunks_before = []
-    for doc in created_docs:
-        assert doc.id is not None
-        doc_chunks = await client.chunk_repository.get_by_document_id(doc.id)
-        chunks_before.extend(doc_chunks)
-
-    assert len(chunks_before) > 0
-
-    # Perform rebuild
-    processed_doc_ids = []
-    async for doc_id in client.rebuild_database():
-        processed_doc_ids.append(doc_id)
-
-    # Verify all documents were processed
-    expected_doc_ids = [doc.id for doc in created_docs]
-    assert set(processed_doc_ids) == set(expected_doc_ids)
-
-    documents_after = await client.list_documents()
-    assert len(documents_after) == 3
-
-    # Verify chunks were recreated
-    chunks_after = []
-    for doc in documents_after:
-        if doc.id is not None:
+        chunks_before = []
+        for doc in created_docs:
+            assert doc.id is not None
             doc_chunks = await client.chunk_repository.get_by_document_id(doc.id)
-            chunks_after.extend(doc_chunks)
+            chunks_before.extend(doc_chunks)
 
-    assert len(chunks_after) > 0
+        assert len(chunks_before) > 0
 
-    client.close()
+        # Perform rebuild
+        processed_doc_ids = []
+        async for doc_id in client.rebuild_database():
+            processed_doc_ids.append(doc_id)
+
+        # Verify all documents were processed
+        expected_doc_ids = [doc.id for doc in created_docs]
+        assert set(processed_doc_ids) == set(expected_doc_ids)
+
+        documents_after = await client.list_documents()
+        assert len(documents_after) == 3
+
+        # Verify chunks were recreated
+        chunks_after = []
+        for doc in documents_after:
+            if doc.id is not None:
+                doc_chunks = await client.chunk_repository.get_by_document_id(doc.id)
+                chunks_after.extend(doc_chunks)
+
+        assert len(chunks_after) > 0
diff --git a/tests/test_settings.py b/tests/test_settings.py
index 0db16cc8..6a531685 100644
--- a/tests/test_settings.py
+++ b/tests/test_settings.py
@@ -45,10 +45,9 @@ def test_settings_save_and_retrieve():
 async def test_config_validation_on_db_load():
     """Test that config validation fails when loading db with mismatched settings."""
     # Create a temporary database file
-    with tempfile.NamedTemporaryFile(suffix=".sqlite", delete=False) as tmp:
+    with tempfile.NamedTemporaryFile(suffix=".sqlite") as tmp:
         db_path = Path(tmp.name)
 
-    try:
         # Create store and save settings
         store1 = Store(db_path)
         SettingsRepository(store1)
@@ -58,28 +57,25 @@ async def test_config_validation_on_db_load():
         original_chunk_size = Config.CHUNK_SIZE
         Config.CHUNK_SIZE = 999
 
-        # Loading the database should raise ConfigMismatchError
-        with pytest.raises(ConfigMismatchError) as exc_info:
-            Store(db_path)
+        try:
+            # Loading the database should raise ConfigMismatchError
+            with pytest.raises(ConfigMismatchError) as exc_info:
+                Store(db_path)
 
-        assert "CHUNK_SIZE" in str(exc_info.value)
-        assert "Consider rebuilding" in str(exc_info.value)
+            assert "CHUNK_SIZE" in str(exc_info.value)
+            assert "Consider rebuilding" in str(exc_info.value)
 
-        # Rebuild
-        async with HaikuRAG(db_path=db_path, skip_validation=True) as client:
-            async for _ in client.rebuild_database():
-                pass  # Process all documents
+            # Rebuild
+            async with HaikuRAG(db_path=db_path, skip_validation=True) as client:
+                async for _ in client.rebuild_database():
+                    pass  # Process all documents
 
-        # Verify we can now load the database without exception (settings were updated)
-        store2 = Store(db_path)
-        settings_repo2 = SettingsRepository(store2)
-        db_settings = settings_repo2.get()
-        assert db_settings["CHUNK_SIZE"] == 999
-        store2.close()
+            # Verify we can now load the database without exception (settings were updated)
+            store2 = Store(db_path)
+            settings_repo2 = SettingsRepository(store2)
+            db_settings = settings_repo2.get()
+            assert db_settings["CHUNK_SIZE"] == 999
+            store2.close()
 
-        Config.CHUNK_SIZE = original_chunk_size
-
-    finally:
-        # Cleanup
-        if db_path.exists():
-            db_path.unlink()
+        finally:
+            Config.CHUNK_SIZE = original_chunk_size

From a2d7e527d193ea4677d2fe813d87ed7fda8307a8 Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Mon, 14 Jul 2025 12:00:03 +0300
Subject: [PATCH 5/6] Update docs on configuration changes

---
 docs/configuration.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/docs/configuration.md b/docs/configuration.md
index a9846508..5dbba71b 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -2,6 +2,9 @@
 
 Configuration is done through the use of environment variables.
 
+!!! note
+    If you create a db with certain settings and later change them, `haiku.rag` will detect incompatibilities (for example, if you change embedding provider) and will exit. You can **rebuild** the database to apply the new settings, see [Rebuild Database](./cli.md#rebuild-database).
+
 ## File Monitoring
 
 Set directories to monitor for automatic indexing:

From f4aef4eb9c55d4ad6fb7e9c7732f201a64c4077e Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Mon, 14 Jul 2025 12:13:01 +0300
Subject: [PATCH 6/6] Check pypi version on startup

---
 src/haiku/rag/cli.py   | 19 ++++++++++++++++++-
 src/haiku/rag/utils.py | 24 ++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/src/haiku/rag/cli.py b/src/haiku/rag/cli.py
index 426af784..80ee047e 100644
--- a/src/haiku/rag/cli.py
+++ b/src/haiku/rag/cli.py
@@ -5,7 +5,7 @@ import typer
 from rich.console import Console
 
 from haiku.rag.app import HaikuRAGApp
-from haiku.rag.utils import get_default_data_dir
+from haiku.rag.utils import get_default_data_dir, is_up_to_date
 
 cli = typer.Typer(
     context_settings={"help_option_names": ["-h", "--help"]}, no_args_is_help=True
@@ -15,6 +15,23 @@ console = Console()
 event_loop = asyncio.get_event_loop()
 
 
+async def check_version():
+    """Check if haiku.rag is up to date and show warning if not."""
+    up_to_date, current_version, latest_version = await is_up_to_date()
+    if not up_to_date:
+        console.print(
+            f"[yellow]Warning: haiku.rag is outdated. Current: {current_version}, Latest: {latest_version}[/yellow]"
+        )
+        console.print("[yellow]Please update.[/yellow]")
+
+
+@cli.callback()
+def main():
+    """haiku.rag CLI - SQLite-based RAG system"""
+    # Run version check before any command
+    event_loop.run_until_complete(check_version())
+
+
 @cli.command("list", help="List all stored documents")
 def list_documents(
     db: Path = typer.Option(
diff --git a/src/haiku/rag/utils.py b/src/haiku/rag/utils.py
index 03c160bf..8b78f008 100644
--- a/src/haiku/rag/utils.py
+++ b/src/haiku/rag/utils.py
@@ -1,6 +1,10 @@
 import sys
+from importlib import metadata
 from pathlib import Path
 
+import httpx
+from packaging.version import Version, parse
+
 
 def get_default_data_dir() -> Path:
     """
@@ -23,3 +27,23 @@ def get_default_data_dir() -> Path:
 
     data_path = system_paths[sys.platform]
     return data_path
+
+
+async def is_up_to_date() -> tuple[bool, Version, Version]:
+    """
+    Checks whether haiku.rag is current.
+
+    :return: A tuple containing a boolean indicating whether haiku.rag is current, the running version and the latest version
+    :rtype: tuple[bool, Version, Version]
+    """
+
+    async with httpx.AsyncClient() as client:
+        running_version = parse(metadata.version("haiku.rag"))
+        try:
+            response = await client.get("https://pypi.org/pypi/haiku.rag/json")
+            data = response.json()
+            pypi_version = parse(data["info"]["version"])
+        except Exception:
+            # If no network connection, do not raise alarms.
+            pypi_version = running_version
+    return running_version >= pypi_version, running_version, pypi_version