haiku.rag 0.7.6__py3-none-any.whl → 0.8.0__py3-none-any.whl

haiku/rag/app.py

@@ -102,6 +102,15 @@ class HaikuRAGApp:
             except Exception as e:
                 self.console.print(f"[red]Error rebuilding database: {e}[/red]")
 
+    async def vacuum(self):
+        """Run database maintenance: optimize and cleanup table history."""
+        try:
+            async with HaikuRAG(db_path=self.db_path, skip_validation=True) as client:
+                await client.vacuum()
+            self.console.print("[b]Vacuum completed successfully.[/b]")
+        except Exception as e:
+            self.console.print(f"[red]Error during vacuum: {e}[/red]")
+
     def show_settings(self):
         """Display current configuration settings."""
         self.console.print("[bold]haiku.rag configuration[/bold]")

haiku/rag/cli.py

@@ -256,6 +256,18 @@ def rebuild(
     asyncio.run(app.rebuild())
 
 
+@cli.command("vacuum", help="Optimize and clean up all tables to reduce disk usage")
+def vacuum(
+    db: Path = typer.Option(
+        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        "--db",
+        help="Path to the LanceDB database file",
+    ),
+):
+    app = HaikuRAGApp(db_path=db)
+    asyncio.run(app.vacuum())
+
+
 @cli.command(
     "serve", help="Start the haiku.rag MCP server (by default in streamable HTTP mode)"
 )

haiku/rag/client.py

@@ -550,6 +550,16 @@ class HaikuRAG:
                 )
                 yield doc.id
 
+        # Final maintenance: centralized vacuum to curb disk usage
+        try:
+            self.store.vacuum()
+        except Exception:
+            pass
+
+    async def vacuum(self) -> None:
+        """Optimize and clean up old versions across all tables."""
+        self.store.vacuum()
+
     def close(self):
         """Close the underlying store connection."""
         self.store.close()

haiku/rag/embeddings/__init__.py

@@ -27,4 +27,9 @@ def get_embedder() -> EmbedderBase:
 
         return OpenAIEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
 
+    if Config.EMBEDDINGS_PROVIDER == "vllm":
+        from haiku.rag.embeddings.vllm import Embedder as VllmEmbedder
+
+        return VllmEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
+
     raise ValueError(f"Unsupported embedding provider: {Config.EMBEDDINGS_PROVIDER}")

haiku/rag/logging.py

@@ -1,4 +1,5 @@
 import logging
+import warnings
 
 from rich.console import Console
 from rich.logging import RichHandler
@@ -50,4 +51,6 @@ def configure_cli_logging(level: int = logging.INFO) -> logging.Logger:
     logger = get_logger()
     logger.setLevel(level)
     logger.propagate = False
+
+    warnings.filterwarnings("ignore")
     return logger

haiku/rag/migration.py

@@ -47,7 +47,7 @@ class SQLiteToLanceDBMigrator:
 
             # Load the sqlite-vec extension
             try:
-                import sqlite_vec
+                import sqlite_vec  # type: ignore
 
                 sqlite_conn.enable_load_extension(True)
                 sqlite_vec.load(sqlite_conn)
@@ -91,10 +91,10 @@ class SQLiteToLanceDBMigrator:
 
             sqlite_conn.close()
 
-            # Optimize the chunks table after migration
+            # Optimize and cleanup using centralized vacuum
             self.console.print("[blue]Optimizing LanceDB...[/blue]")
             try:
-                lance_store.chunks_table.optimize()
+                lance_store.vacuum()
                 self.console.print("[green]✅ Optimization completed[/green]")
             except Exception as e:
                 self.console.print(

haiku/rag/store/engine.py

@@ -1,5 +1,6 @@
 import json
 import logging
+from datetime import timedelta
 from importlib import metadata
 from pathlib import Path
 from uuid import uuid4
@@ -62,6 +63,15 @@ class Store:
         if not skip_validation:
             self._validate_configuration()
 
+    def vacuum(self) -> None:
+        """Optimize and clean up old versions across all tables to reduce disk usage."""
+        if self._has_cloud_config() and str(Config.LANCEDB_URI).startswith("db://"):
+            return
+
+        # Perform maintenance per table using optimize() with cleanup_older_than 0
+        for table in [self.documents_table, self.chunks_table, self.settings_table]:
+            table.optimize(cleanup_older_than=timedelta(0))
+
     def _connect_to_lancedb(self, db_path: Path):
         """Establish connection to LanceDB (local, cloud, or object storage)."""
         # Check if we have cloud configuration
@@ -159,16 +169,18 @@ class Store:
             self.settings_table.search().limit(1).to_pydantic(SettingsRecord)
         )
         if settings_records:
-            settings = (
+            # Only write if version actually changes to avoid creating new table versions
+            current = (
                 json.loads(settings_records[0].settings)
                 if settings_records[0].settings
                 else {}
             )
-            settings["version"] = version
-            # Update the record
-            self.settings_table.update(
-                where="id = 'settings'", values={"settings": json.dumps(settings)}
-            )
+            if current.get("version") != version:
+                current["version"] = version
+                self.settings_table.update(
+                    where="id = 'settings'",
+                    values={"settings": json.dumps(current)},
+                )
         else:
             # Create new settings record
             settings_data = Config.model_dump(mode="json")

haiku/rag/store/repositories/settings.py

@@ -84,10 +84,15 @@ class SettingsRepository:
         )
 
         if existing:
-            # Update existing settings
-            self.store.settings_table.update(
-                where="id = 'settings'", values={"settings": json.dumps(current_config)}
+            # Only update when configuration actually changed to avoid needless new versions
+            existing_payload = (
+                json.loads(existing[0].settings) if existing[0].settings else {}
             )
+            if existing_payload != current_config:
+                self.store.settings_table.update(
+                    where="id = 'settings'",
+                    values={"settings": json.dumps(current_config)},
+                )
         else:
             # Create new settings
             settings_record = SettingsRecord(

{haiku_rag-0.7.6.dist-info → haiku_rag-0.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.7.6
+Version: 0.8.0
 Summary: Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT

{haiku_rag-0.7.6.dist-info → haiku_rag-0.8.0.dist-info}/RECORD

@@ -1,16 +1,16 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haiku/rag/app.py,sha256=n9Y-4wHnxGeatCE-scqbv5JBnPo-5WOJ6URdfZveHC8,7837
+haiku/rag/app.py,sha256=XlL6PNPSqeBKF6bemvdSfXEnQghywudwZv-C116NuZU,8254
 haiku/rag/chunker.py,sha256=PVe6ysv8UlacUd4Zb3_8RFWIaWDXnzBAy2VDJ4TaUsE,1555
-haiku/rag/cli.py,sha256=HqFHU9x2tR1yTR74V3NPndqE4R2Yn-ohASyHp334pAg,8597
-haiku/rag/client.py,sha256=N4zkWjE9Rsw9YgPvNo83xptHUQR2ognfOnjkoV_w6hc,20999
+haiku/rag/cli.py,sha256=houkHTeVc89BA3zPksCjUooEnScSg1Ez_BIHBH6cmJQ,8920
+haiku/rag/client.py,sha256=NJVGXzVzpoVy1sttz_xEU7mXWtObKT8pGpvo5pZyzwc,21288
 haiku/rag/config.py,sha256=3H41da9BU1R1y2JJHD0cOSErX_VSM1UXA7M2JSOxFXE,1795
-haiku/rag/logging.py,sha256=a0ELyeMqb85ebeOTN8OQCTL1PiMWiiV9R_OOH-VZoA8,1665
+haiku/rag/logging.py,sha256=dm65AwADpcQsH5OAPtRA-4hsw0w5DK-sGOvzYkj6jzw,1720
 haiku/rag/mcp.py,sha256=bR9Y-Nz-hvjiql20Y0KE0hwNGwyjmPGX8K9d-qmXptY,4683
-haiku/rag/migration.py,sha256=n5G6SDhTo8wTf0uCYbWGegq1LqIgILDLNjWcGvSj-SQ,11053
+haiku/rag/migration.py,sha256=M--KnSF3lxgKjxmokb4vuzGH-pV8eg0C_8e7jvPqW8Y,11058
 haiku/rag/monitor.py,sha256=r386nkhdlsU8UECwIuVwnrSlgMk3vNIuUZGNIzkZuec,2770
 haiku/rag/reader.py,sha256=qkPTMJuQ_o4sK-8zpDl9WFYe_MJ7aL_gUw6rczIpW-g,3274
 haiku/rag/utils.py,sha256=c8F0ECsFSqvQxzxINAOAnvShoOnJPLsOaNE3JEY2JSc,3230
-haiku/rag/embeddings/__init__.py,sha256=n7aHW3BxHlpGxU4ze4YYDOsljzFpEep8dwVE2n45JoE,1218
+haiku/rag/embeddings/__init__.py,sha256=44IfDITGIFTflGT6UEmiYOwpWFVbYv5smLY59D0YeCs,1419
 haiku/rag/embeddings/base.py,sha256=BnSviKrlzjv3L0sZJs_T-pxfawd-bcTak-rsX-D2f3A,497
 haiku/rag/embeddings/ollama.py,sha256=LuLlHH6RGoO9_gFCIlbmesuXOj017gTw6z-p8Ez0CfE,595
 haiku/rag/embeddings/openai.py,sha256=fIFCk-jpUtaW0xsnrQnJ824O0UCjaGG2sgvBzREhilc,503
@@ -25,17 +25,17 @@ haiku/rag/reranking/cohere.py,sha256=1iTdiaa8vvb6oHVB2qpWzUOVkyfUcimVSZp6Qr4aq4c
 haiku/rag/reranking/mxbai.py,sha256=46sVTsTIkzIX9THgM3u8HaEmgY7evvEyB-N54JTHvK8,867
 haiku/rag/reranking/vllm.py,sha256=xVGH9ss-ISWdJ5SKUUHUbTqBo7PIEmA_SQv0ScdJ6XA,1479
 haiku/rag/store/__init__.py,sha256=hq0W0DAC7ysqhWSP2M2uHX8cbG6kbr-sWHxhq6qQcY0,103
-haiku/rag/store/engine.py,sha256=XHGo5Xl-dCFdQHrOdMo64xVK5n0k8-LoUl5V-tlA0HI,7131
+haiku/rag/store/engine.py,sha256=uzw09IOebaKo8b_FyvVHMUQMDVKfBpN7WGfuY3fKiEE,7757
 haiku/rag/store/models/__init__.py,sha256=s0E72zneGlowvZrFWaNxHYjOAUjgWdLxzdYsnvNRVlY,88
 haiku/rag/store/models/chunk.py,sha256=ZNyTfO6lh3rXWLVYO3TZcitbL4LSUGr42fR6jQQ5iQc,364
 haiku/rag/store/models/document.py,sha256=zSSpt6pyrMJAIXGQvIcqojcqUzwZnhp3WxVokaWxNRc,396
 haiku/rag/store/repositories/__init__.py,sha256=Olv5dLfBQINRV3HrsfUpjzkZ7Qm7goEYyMNykgo_DaY,291
 haiku/rag/store/repositories/chunk.py,sha256=v4y4eh4yIf6zJaWfHxljvnmb12dmvwdinzmxQt8Lvhs,13343
 haiku/rag/store/repositories/document.py,sha256=lP8Lo82KTP-qwXFRpYZ46WjeAdAsHwZ5pJcrXdz4g0U,6988
-haiku/rag/store/repositories/settings.py,sha256=dqnAvm-98nQrWpLBbf9QghJw673QD80-iqQhRMP5t0c,5025
+haiku/rag/store/repositories/settings.py,sha256=wx3fuP_5CpPflZHRrIkeoer6ml-iD0qXERh5k6MQRzI,5291
 haiku/rag/store/upgrades/__init__.py,sha256=wUiEoSiHTahvuagx93E4FB07v123AhdbOjwUkPusiIg,14
-haiku_rag-0.7.6.dist-info/METADATA,sha256=lJ64GebtYSRr0ld0jXF-jvnpraumPOde2A0w8JVpXsc,4610
-haiku_rag-0.7.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.7.6.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.7.6.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.7.6.dist-info/RECORD,,
+haiku_rag-0.8.0.dist-info/METADATA,sha256=OZfvP7S7MBndpjjTg59UaD9JgB_W39pXpYAjyULjn8A,4610
+haiku_rag-0.8.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.8.0.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.8.0.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.8.0.dist-info/RECORD,,