haiku.rag 0.7.3__py3-none-any.whl → 0.7.5__py3-none-any.whl

haiku/rag/app.py

@@ -50,8 +50,13 @@ class HaikuRAGApp:
 
     async def delete_document(self, doc_id: str):
         async with HaikuRAG(db_path=self.db_path) as self.client:
-            await self.client.delete_document(doc_id)
-            self.console.print(f"[b]Document {doc_id} deleted successfully.[/b]")
+            deleted = await self.client.delete_document(doc_id)
+            if deleted:
+                self.console.print(f"[b]Document {doc_id} deleted successfully.[/b]")
+            else:
+                self.console.print(
+                    f"[yellow]Document with id {doc_id} not found.[/yellow]"
+                )
 
     async def search(self, query: str, limit: int = 5):
         async with HaikuRAG(db_path=self.db_path) as self.client:

haiku/rag/cli.py

@@ -8,6 +8,7 @@ from rich.console import Console
 
 from haiku.rag.app import HaikuRAGApp
 from haiku.rag.config import Config
+from haiku.rag.logging import configure_cli_logging
 from haiku.rag.migration import migrate_sqlite_to_lancedb
 from haiku.rag.utils import is_up_to_date
 
@@ -21,6 +22,65 @@ cli = typer.Typer(
 console = Console()
 
 
+def complete_document_ids(ctx: typer.Context, incomplete: str):
+    """Autocomplete document IDs from the selected DB."""
+    db_path = ctx.params.get("db") or (Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb")
+
+    try:
+        from haiku.rag.client import HaikuRAG
+
+        async def _list_ids():
+            async with HaikuRAG(db_path) as client:
+                docs = await client.list_documents()
+                return [d.id for d in docs if d.id]
+
+        ids = asyncio.run(_list_ids())
+    except Exception:
+        return []
+
+    return [i for i in ids if i and i.startswith(incomplete)]
+
+
+def complete_local_paths(ctx: typer.Context, incomplete: str) -> list[str]:
+    """Autocomplete local filesystem paths.
+
+    Provides directory/file suggestions based on the current incomplete input.
+    Does not validate or restrict to specific extensions to keep it flexible
+    (URLs are still allowed to be typed manually).
+    """
+    try:
+        text = incomplete or ""
+
+        # Expand user home
+        from os.path import expanduser
+
+        expanded = expanduser(text)
+        p = Path(expanded)
+
+        # Choose directory to list and prefix to filter
+        if text == "" or text.endswith(("/", "\\")):
+            directory = p
+            prefix = ""
+        else:
+            directory = p.parent
+            prefix = p.name
+
+        if not directory.exists():
+            return []
+
+        suggestions: list[str] = []
+        for entry in directory.iterdir():
+            name = entry.name
+            if not prefix or name.startswith(prefix):
+                suggestion = str(directory / name)
+                if entry.is_dir():
+                    suggestion += "/"
+                suggestions.append(suggestion)
+        return suggestions
+    except Exception:
+        return []
+
+
 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()
@@ -49,6 +109,8 @@ def main(
     ),
 ):
     """haiku.rag CLI - Vector database RAG system"""
+    # Ensure only haiku.rag logs are emitted in CLI context
+    configure_cli_logging()
     # Run version check before any command
     asyncio.run(check_version())
 
@@ -84,6 +146,7 @@ def add_document_text(
 def add_document_src(
     source: str = typer.Argument(
         help="The file path or URL of the document to add",
+        autocompletion=complete_local_paths,
     ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
@@ -99,6 +162,7 @@ def add_document_src(
 def get_document(
     doc_id: str = typer.Argument(
         help="The ID of the document to get",
+        autocompletion=complete_document_ids,
     ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
@@ -114,6 +178,7 @@ def get_document(
 def delete_document(
     doc_id: str = typer.Argument(
         help="The ID of the document to delete",
+        autocompletion=complete_document_ids,
     ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
@@ -125,6 +190,10 @@ def delete_document(
     asyncio.run(app.delete_document(doc_id=doc_id))
 
 
+# Add alias `rm` for delete
+cli.command("rm", help="Alias for delete: remove a document by its ID")(delete_document)
+
+
 @cli.command("search", help="Search for documents by a query")
 def search(
     query: str = typer.Argument(

haiku/rag/logging.py

@@ -3,13 +3,9 @@ import logging
 from rich.console import Console
 from rich.logging import RichHandler
 
-logging.basicConfig(level=logging.DEBUG)
-logging.getLogger("httpx").setLevel(logging.WARNING)
-logging.getLogger("httpcore").setLevel(logging.WARNING)
-logging.getLogger("docling").setLevel(logging.WARNING)
-
 
 def get_logger() -> logging.Logger:
+    """Return the library logger configured with a Rich handler."""
     logger = logging.getLogger("haiku.rag")
 
     handler = RichHandler(
@@ -19,11 +15,39 @@ def get_logger() -> logging.Logger:
     formatter = logging.Formatter("%(message)s")
     handler.setFormatter(formatter)
 
-    logger.setLevel("INFO")
+    logger.setLevel(logging.INFO)
 
     # Remove any existing handlers to avoid duplicates on reconfiguration
     for hdlr in logger.handlers[:]:
         logger.removeHandler(hdlr)
 
     logger.addHandler(handler)
+    # Do not let messages propagate to the root logger
+    logger.propagate = False
+    return logger
+
+
+def configure_cli_logging(level: int = logging.INFO) -> logging.Logger:
+    """Configure logging for CLI runs.
+
+    - Silence ALL non-haiku.rag loggers by detaching root handlers and setting
+      their level to ERROR.
+    - Attach a Rich handler only to the "haiku.rag" logger.
+    - Prevent propagation so only our logger prints in the CLI.
+    """
+    # Silence root logger completely
+    root = logging.getLogger()
+    for hdlr in root.handlers[:]:
+        root.removeHandler(hdlr)
+    root.setLevel(logging.ERROR)
+
+    # Optionally silence some commonly noisy libraries explicitly as a safeguard
+    for noisy in ("httpx", "httpcore", "docling", "urllib3", "asyncio"):
+        logging.getLogger(noisy).setLevel(logging.ERROR)
+        logging.getLogger(noisy).propagate = False
+
+    # Configure and return our app logger
+    logger = get_logger()
+    logger.setLevel(level)
+    logger.propagate = False
     return logger

haiku/rag/migration.py

@@ -1,13 +1,3 @@
-#!/usr/bin/env python3
-"""
-Migration script to migrate from SQLite to LanceDB.
-
-This script will:
-1. Read data from an existing SQLite database
-2. Create a new LanceDB database with the same data
-3. Preserve all documents, chunks, embeddings, and settings
-"""
-
 import json
 import sqlite3
 import struct
@@ -55,6 +45,22 @@ class SQLiteToLanceDBMigrator:
             sqlite_conn = sqlite3.connect(self.sqlite_path)
             sqlite_conn.row_factory = sqlite3.Row
 
+            # Load the sqlite-vec extension
+            try:
+                import sqlite_vec
+
+                sqlite_conn.enable_load_extension(True)
+                sqlite_vec.load(sqlite_conn)
+                self.console.print("[blue]Loaded sqlite-vec extension[/blue]")
+            except Exception as e:
+                self.console.print(
+                    f"[yellow]Warning: Could not load sqlite-vec extension: {e}[/yellow]"
+                )
+                self.console.print(
+                    "[yellow]Install sqlite-vec with[/yellow]\n[green]uv pip install sqlite-vec [/green]"
+                )
+                exit(1)
+
             # Create LanceDB store
             lance_store = Store(self.lancedb_path, skip_validation=True)
 
@@ -180,30 +186,24 @@ class SQLiteToLanceDBMigrator:
 
         chunks_data = cursor.fetchall()
 
-        # Get embeddings separately to avoid vec0 virtual table issues
+        # Get embeddings using the sqlite-vec virtual table
         embeddings_map = {}
         try:
-            # Try to get embeddings from the vec0 tables directly
+            # Use the virtual table to get embeddings properly
             cursor.execute("""
-                SELECT
-                    r.chunk_id,
-                    v.vectors
-                FROM chunk_embeddings_rowids r
-                JOIN chunk_embeddings_vector_chunks00 v ON r.rowid = v.rowid
+                SELECT chunk_id, embedding
+                FROM chunk_embeddings
             """)
 
             for row in cursor.fetchall():
                 chunk_id = row[0]
-                vectors_blob = row[1]
-                if vectors_blob and chunk_id not in embeddings_map:
-                    embeddings_map[chunk_id] = vectors_blob
+                embedding_blob = row[1]
+                if embedding_blob and chunk_id not in embeddings_map:
+                    embeddings_map[chunk_id] = embedding_blob
 
         except sqlite3.OperationalError as e:
             self.console.print(
-                f"[yellow]Warning: Could not extract embeddings: {e}[/yellow]"
-            )
-            self.console.print(
-                "[yellow]Continuing migration without embeddings...[/yellow]"
+                f"[yellow]Warning: Could not extract embeddings from virtual table: {e}[/yellow]"
             )
 
         chunks = []

{haiku_rag-0.7.3.dist-info → haiku_rag-0.7.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.7.3
+Version: 0.7.5
 Summary: Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT

{haiku_rag-0.7.3.dist-info → haiku_rag-0.7.5.dist-info}/RECORD

@@ -1,12 +1,12 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haiku/rag/app.py,sha256=GmuZxH7BMutWt8Mdu0RSateRBaKiqXh7Z9tV7cZX6n0,7655
+haiku/rag/app.py,sha256=S19UWA6dxl9NayL9hOZKC5D7fjNat4n0mUOw2PAF9u8,7842
 haiku/rag/chunker.py,sha256=PVe6ysv8UlacUd4Zb3_8RFWIaWDXnzBAy2VDJ4TaUsE,1555
-haiku/rag/cli.py,sha256=UY9Vh5RsIxSCV14eQbNOiwToKmbFAvqTOAnxjieaYBs,6399
+haiku/rag/cli.py,sha256=HqFHU9x2tR1yTR74V3NPndqE4R2Yn-ohASyHp334pAg,8597
 haiku/rag/client.py,sha256=N4zkWjE9Rsw9YgPvNo83xptHUQR2ognfOnjkoV_w6hc,20999
 haiku/rag/config.py,sha256=3H41da9BU1R1y2JJHD0cOSErX_VSM1UXA7M2JSOxFXE,1795
-haiku/rag/logging.py,sha256=DOQi9QMpQRl8h17Vu4nQh8HxpHdeIu29n8-HZaT3SRQ,786
+haiku/rag/logging.py,sha256=a0ELyeMqb85ebeOTN8OQCTL1PiMWiiV9R_OOH-VZoA8,1665
 haiku/rag/mcp.py,sha256=bR9Y-Nz-hvjiql20Y0KE0hwNGwyjmPGX8K9d-qmXptY,4683
-haiku/rag/migration.py,sha256=gWxQwiKo0YulRhogYz4K8N98kHN9LQXIx9FeTmT24v4,10915
+haiku/rag/migration.py,sha256=n5G6SDhTo8wTf0uCYbWGegq1LqIgILDLNjWcGvSj-SQ,11053
 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
@@ -34,8 +34,8 @@ haiku/rag/store/repositories/chunk.py,sha256=v4y4eh4yIf6zJaWfHxljvnmb12dmvwdinzm
 haiku/rag/store/repositories/document.py,sha256=lP8Lo82KTP-qwXFRpYZ46WjeAdAsHwZ5pJcrXdz4g0U,6988
 haiku/rag/store/repositories/settings.py,sha256=dqnAvm-98nQrWpLBbf9QghJw673QD80-iqQhRMP5t0c,5025
 haiku/rag/store/upgrades/__init__.py,sha256=wUiEoSiHTahvuagx93E4FB07v123AhdbOjwUkPusiIg,14
-haiku_rag-0.7.3.dist-info/METADATA,sha256=PAvA6VZuyZp9IekXhYCLWDxM1wMZMmujtntxZE2lBoE,4610
-haiku_rag-0.7.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.7.3.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.7.3.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.7.3.dist-info/RECORD,,
+haiku_rag-0.7.5.dist-info/METADATA,sha256=URf4qAZuzeL3OpTKuF6IhOeSmfRWlph-1pLboZTQUnw,4610
+haiku_rag-0.7.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.7.5.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.7.5.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.7.5.dist-info/RECORD,,