haiku.rag 0.10.1__py3-none-any.whl → 0.10.2__py3-none-any.whl

haiku/rag/app.py

@@ -1,4 +1,6 @@
 import asyncio
+import json
+from importlib.metadata import version as pkg_version
 from pathlib import Path
 
 from rich.console import Console
@@ -25,26 +27,141 @@ class HaikuRAGApp:
         self.db_path = db_path
         self.console = Console()
 
+    async def info(self):
+        """Display read-only information about the database without modifying it."""
+
+        import lancedb
+
+        # Basic: show path
+        self.console.print("[bold]haiku.rag database info[/bold]")
+        self.console.print(
+            f"  [repr.attrib_name]path[/repr.attrib_name]: {self.db_path}"
+        )
+
+        if not self.db_path.exists():
+            self.console.print("[red]Database path does not exist.[/red]")
+            return
+
+        # Connect without going through Store to avoid upgrades/validation writes
+        try:
+            db = lancedb.connect(self.db_path)
+            table_names = set(db.table_names())
+        except Exception as e:
+            self.console.print(f"[red]Failed to open database: {e}[/red]")
+            return
+
+        try:
+            ldb_version = pkg_version("lancedb")
+        except Exception:
+            ldb_version = "unknown"
+        try:
+            hr_version = pkg_version("haiku.rag")
+        except Exception:
+            hr_version = "unknown"
+        try:
+            docling_version = pkg_version("docling")
+        except Exception:
+            docling_version = "unknown"
+
+        # Read settings (if present) to find stored haiku.rag version and embedding config
+        stored_version = "unknown"
+        embed_provider: str | None = None
+        embed_model: str | None = None
+        vector_dim: int | None = None
+
+        if "settings" in table_names:
+            settings_tbl = db.open_table("settings")
+            arrow = settings_tbl.search().where("id = 'settings'").limit(1).to_arrow()
+            rows = arrow.to_pylist() if arrow is not None else []
+            if rows:
+                raw = rows[0].get("settings") or "{}"
+                data = json.loads(raw) if isinstance(raw, str) else (raw or {})
+                stored_version = str(data.get("version", stored_version))
+                embed_provider = data.get("EMBEDDINGS_PROVIDER")
+                embed_model = data.get("EMBEDDINGS_MODEL")
+                vector_dim = (
+                    int(data.get("EMBEDDINGS_VECTOR_DIM"))  # pyright: ignore[reportArgumentType]
+                    if data.get("EMBEDDINGS_VECTOR_DIM") is not None
+                    else None
+                )
+
+        num_docs = 0
+        if "documents" in table_names:
+            docs_tbl = db.open_table("documents")
+            num_docs = int(docs_tbl.count_rows())  # type: ignore[attr-defined]
+
+        # Table versions per table (direct API)
+        doc_versions = (
+            len(list(db.open_table("documents").list_versions()))
+            if "documents" in table_names
+            else 0
+        )
+        chunk_versions = (
+            len(list(db.open_table("chunks").list_versions()))
+            if "chunks" in table_names
+            else 0
+        )
+
+        self.console.print(
+            f"  [repr.attrib_name]haiku.rag version (db)[/repr.attrib_name]: {stored_version}"
+        )
+        if embed_provider or embed_model or vector_dim:
+            provider_part = embed_provider or "unknown"
+            model_part = embed_model or "unknown"
+            dim_part = f"{vector_dim}" if vector_dim is not None else "unknown"
+            self.console.print(
+                "  [repr.attrib_name]embeddings[/repr.attrib_name]: "
+                f"{provider_part}/{model_part} (dim: {dim_part})"
+            )
+        else:
+            self.console.print(
+                "  [repr.attrib_name]embeddings[/repr.attrib_name]: unknown"
+            )
+        self.console.print(
+            f"  [repr.attrib_name]documents[/repr.attrib_name]: {num_docs}"
+        )
+        self.console.print(
+            f"  [repr.attrib_name]versions (documents)[/repr.attrib_name]: {doc_versions}"
+        )
+        self.console.print(
+            f"  [repr.attrib_name]versions (chunks)[/repr.attrib_name]: {chunk_versions}"
+        )
+        self.console.rule()
+        self.console.print("[bold]Versions[/bold]")
+        self.console.print(
+            f"  [repr.attrib_name]haiku.rag[/repr.attrib_name]: {hr_version}"
+        )
+        self.console.print(
+            f"  [repr.attrib_name]lancedb[/repr.attrib_name]: {ldb_version}"
+        )
+        self.console.print(
+            f"  [repr.attrib_name]docling[/repr.attrib_name]: {docling_version}"
+        )
+
     async def list_documents(self):
         async with HaikuRAG(db_path=self.db_path) as self.client:
             documents = await self.client.list_documents()
             for doc in documents:
                 self._rich_print_document(doc, truncate=True)
 
-    async def add_document_from_text(self, text: str):
+    async def add_document_from_text(self, text: str, metadata: dict | None = None):
         async with HaikuRAG(db_path=self.db_path) as self.client:
-            doc = await self.client.create_document(text)
+            doc = await self.client.create_document(text, metadata=metadata)
             self._rich_print_document(doc, truncate=True)
             self.console.print(
-                f"[b]Document with id [cyan]{doc.id}[/cyan] added successfully.[/b]"
+                f"[bold green]Document {doc.id} added successfully.[/bold green]"
             )
 
-    async def add_document_from_source(self, source: str, title: str | None = None):
+    async def add_document_from_source(
+        self, source: str, title: str | None = None, metadata: dict | None = None
+    ):
         async with HaikuRAG(db_path=self.db_path) as self.client:
-            doc = await self.client.create_document_from_source(source, title=title)
+            doc = await self.client.create_document_from_source(
+                source, title=title, metadata=metadata
+            )
             self._rich_print_document(doc, truncate=True)
             self.console.print(
-                f"[b]Document with id [cyan]{doc.id}[/cyan] added successfully.[/b]"
+                f"[bold green]Document {doc.id} added successfully.[/bold green]"
             )
 
     async def get_document(self, doc_id: str):
@@ -59,7 +176,9 @@ class HaikuRAGApp:
         async with HaikuRAG(db_path=self.db_path) as self.client:
             deleted = await self.client.delete_document(doc_id)
             if deleted:
-                self.console.print(f"[b]Document {doc_id} deleted successfully.[/b]")
+                self.console.print(
+                    f"[bold green]Document {doc_id} deleted successfully.[/bold green]"
+                )
             else:
                 self.console.print(
                     f"[yellow]Document with id {doc_id} not found.[/yellow]"
@@ -69,7 +188,7 @@ class HaikuRAGApp:
         async with HaikuRAG(db_path=self.db_path) as self.client:
             results = await self.client.search(query, limit=limit)
             if not results:
-                self.console.print("[red]No results found.[/red]")
+                self.console.print("[yellow]No results found.[/yellow]")
                 return
             for chunk, score in results:
                 self._rich_print_search_result(chunk, score)
@@ -202,14 +321,16 @@ class HaikuRAGApp:
                     return
 
                 self.console.print(
-                    f"[b]Rebuilding database with {total_docs} documents...[/b]"
+                    f"[bold cyan]Rebuilding database with {total_docs} documents...[/bold cyan]"
                 )
                 with Progress() as progress:
                     task = progress.add_task("Rebuilding...", total=total_docs)
                     async for _ in client.rebuild_database():
                         progress.update(task, advance=1)
 
-                self.console.print("[b]Database rebuild completed successfully.[/b]")
+                self.console.print(
+                    "[bold green]Database rebuild completed successfully.[/bold green]"
+                )
             except Exception as e:
                 self.console.print(f"[red]Error rebuilding database: {e}[/red]")
 
@@ -218,7 +339,9 @@ class HaikuRAGApp:
         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]")
+            self.console.print(
+                "[bold green]Vacuum completed successfully.[/bold green]"
+            )
         except Exception as e:
             self.console.print(f"[red]Error during vacuum: {e}[/red]")
 
@@ -240,7 +363,9 @@ class HaikuRAGApp:
             else:
                 display_value = field_value
 
-            self.console.print(f"  [cyan]{field_name}[/cyan]: {display_value}")
+            self.console.print(
+                f"  [repr.attrib_name]{field_name}[/repr.attrib_name]: {display_value}"
+            )
 
     def _rich_print_document(self, doc: Document, truncate: bool = False):
         """Format a document for display."""

haiku/rag/cli.py

@@ -1,7 +1,9 @@
 import asyncio
+import json
 import warnings
 from importlib.metadata import version
 from pathlib import Path
+from typing import Any
 
 import typer
 
@@ -137,11 +139,41 @@ def list_documents(
     asyncio.run(app.list_documents())
 
 
+def _parse_meta_options(meta: list[str] | None) -> dict[str, Any]:
+    """Parse repeated --meta KEY=VALUE options into a dictionary.
+
+    Raises a Typer error if any entry is malformed.
+    """
+    result: dict[str, Any] = {}
+    if not meta:
+        return result
+    for item in meta:
+        if "=" not in item:
+            raise typer.BadParameter("--meta must be in KEY=VALUE format")
+        key, value = item.split("=", 1)
+        if not key:
+            raise typer.BadParameter("--meta key cannot be empty")
+        # Best-effort JSON coercion: numbers, booleans, null, arrays/objects
+        try:
+            parsed = json.loads(value)
+            result[key] = parsed
+        except Exception:
+            # Leave as string if not valid JSON literal
+            result[key] = value
+    return result
+
+
 @cli.command("add", help="Add a document from text input")
 def add_document_text(
     text: str = typer.Argument(
         help="The text content of the document to add",
     ),
+    meta: list[str] | None = typer.Option(
+        None,
+        "--meta",
+        help="Metadata entries as KEY=VALUE (repeatable)",
+        metavar="KEY=VALUE",
+    ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
         "--db",
@@ -151,7 +183,8 @@ def add_document_text(
     from haiku.rag.app import HaikuRAGApp
 
     app = HaikuRAGApp(db_path=db)
-    asyncio.run(app.add_document_from_text(text=text))
+    metadata = _parse_meta_options(meta)
+    asyncio.run(app.add_document_from_text(text=text, metadata=metadata or None))
 
 
 @cli.command("add-src", help="Add a document from a file path or URL")
@@ -165,6 +198,12 @@ def add_document_src(
         "--title",
         help="Optional human-readable title to store with the document",
     ),
+    meta: list[str] | None = typer.Option(
+        None,
+        "--meta",
+        help="Metadata entries as KEY=VALUE (repeatable)",
+        metavar="KEY=VALUE",
+    ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
         "--db",
@@ -174,7 +213,12 @@ def add_document_src(
     from haiku.rag.app import HaikuRAGApp
 
     app = HaikuRAGApp(db_path=db)
-    asyncio.run(app.add_document_from_source(source=source, title=title))
+    metadata = _parse_meta_options(meta)
+    asyncio.run(
+        app.add_document_from_source(
+            source=source, title=title, metadata=metadata or None
+        )
+    )
 
 
 @cli.command("get", help="Get and display a document by its ID")
@@ -347,6 +391,32 @@ def vacuum(
     asyncio.run(app.vacuum())
 
 
+@cli.command("info", help="Show read-only database info (no upgrades or writes)")
+def info(
+    db: Path = typer.Option(
+        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        "--db",
+        help="Path to the LanceDB database file",
+    ),
+):
+    from haiku.rag.app import HaikuRAGApp
+
+    app = HaikuRAGApp(db_path=db)
+    asyncio.run(app.info())
+
+
+@cli.command("download-models", help="Download Docling and Ollama models per config")
+def download_models_cmd():
+    from haiku.rag.utils import prefetch_models
+
+    try:
+        prefetch_models()
+        typer.echo("Models downloaded successfully.")
+    except Exception as e:
+        typer.echo(f"Error downloading models: {e}")
+        raise typer.Exit(1)
+
+
 @cli.command(
     "serve", help="Start the haiku.rag MCP server (by default in streamable HTTP mode)"
 )

haiku/rag/migration.py

@@ -51,7 +51,7 @@ class SQLiteToLanceDBMigrator:
 
                 sqlite_conn.enable_load_extension(True)
                 sqlite_vec.load(sqlite_conn)
-                self.console.print("[blue]Loaded sqlite-vec extension[/blue]")
+                self.console.print("[cyan]Loaded sqlite-vec extension[/cyan]")
             except Exception as e:
                 self.console.print(
                     f"[yellow]Warning: Could not load sqlite-vec extension: {e}[/yellow]"
@@ -92,7 +92,7 @@ class SQLiteToLanceDBMigrator:
             sqlite_conn.close()
 
             # Optimize and cleanup using centralized vacuum
-            self.console.print("[blue]Optimizing LanceDB...[/blue]")
+            self.console.print("[cyan]Optimizing LanceDB...[/cyan]")
             try:
                 lance_store.vacuum()
                 self.console.print("[green]✅ Optimization completed[/green]")

haiku/rag/store/__init__.py

@@ -1,4 +1,4 @@
 from .engine import Store
 from .models import Chunk, Document
 
-__all__ = ["Store", "Chunk", "Document"]
+__all__ = ["Store", "Chunk", "Document"]

haiku/rag/store/models/__init__.py

@@ -1,4 +1,4 @@
 from .chunk import Chunk
 from .document import Document
 
-__all__ = ["Chunk", "Document"]
+__all__ = ["Chunk", "Document"]

haiku/rag/utils.py

@@ -163,3 +163,37 @@ def load_callable(path: str):
             f"Attribute '{func_name}' in module '{module_part}' is not callable"
         )
     return func
+
+
+def prefetch_models():
+    """Prefetch runtime models (Docling + Ollama as configured)."""
+    import httpx
+    from docling.utils.model_downloader import download_models
+
+    from haiku.rag.config import Config
+
+    download_models()
+
+    # Collect Ollama models from config
+    required_models: set[str] = set()
+    if Config.EMBEDDINGS_PROVIDER == "ollama":
+        required_models.add(Config.EMBEDDINGS_MODEL)
+    if Config.QA_PROVIDER == "ollama":
+        required_models.add(Config.QA_MODEL)
+    if Config.RESEARCH_PROVIDER == "ollama":
+        required_models.add(Config.RESEARCH_MODEL)
+    if Config.RERANK_PROVIDER == "ollama":
+        required_models.add(Config.RERANK_MODEL)
+
+    if not required_models:
+        return
+
+    base_url = Config.OLLAMA_BASE_URL
+
+    with httpx.Client(timeout=None) as client:
+        for model in sorted(required_models):
+            with client.stream(
+                "POST", f"{base_url}/api/pull", json={"model": model}
+            ) as r:
+                for _ in r.iter_lines():
+                    pass

{haiku_rag-0.10.1.dist-info → haiku_rag-0.10.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.10.1
+Version: 0.10.2
 Summary: Agentic Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -66,7 +66,8 @@ uv pip install haiku.rag
 
 # Add documents
 haiku-rag add "Your content here"
-haiku-rag add-src document.pdf
+haiku-rag add "Your content here" --meta author=alice --meta topic=notes
+haiku-rag add-src document.pdf --meta source=manual
 
 # Search
 haiku-rag search "query"

{haiku_rag-0.10.1.dist-info → haiku_rag-0.10.2.dist-info}/RECORD

@@ -1,15 +1,15 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haiku/rag/app.py,sha256=06nsdjrljPNqZew4gsLFIA0BSwv-CxPovJaAYSFzm-w,13265
+haiku/rag/app.py,sha256=-nhri6MLIZvp8DEndfeixTCVj6kutWwfLguyAcNe9S4,18023
 haiku/rag/chunker.py,sha256=PVe6ysv8UlacUd4Zb3_8RFWIaWDXnzBAy2VDJ4TaUsE,1555
-haiku/rag/cli.py,sha256=4aYUXPr54q-7U2-cySNpSnW1ntvD0Jck6oj8vvA6IoI,10830
+haiku/rag/cli.py,sha256=wreAxyXSRnn7f09t9SGe4uAXQjlieUQIpNpOapJT7y8,12910
 haiku/rag/client.py,sha256=iUaa6YUac3CXFniIm8DsaaNsiyHsi4cp8-fPhF5XuVU,22925
 haiku/rag/config.py,sha256=SEV2OzaKavYwHZ0LmRzBj-0dbI6YFIRuNiTw9el7SO0,2307
 haiku/rag/logging.py,sha256=dm65AwADpcQsH5OAPtRA-4hsw0w5DK-sGOvzYkj6jzw,1720
 haiku/rag/mcp.py,sha256=H7XibtSNUviFeaJVsXzHiRqUm0nJCpA7A1QHuBv6SKQ,5057
-haiku/rag/migration.py,sha256=M--KnSF3lxgKjxmokb4vuzGH-pV8eg0C_8e7jvPqW8Y,11058
+haiku/rag/migration.py,sha256=zm0-60PiS1hIQnZz65B7qfsgM7GwZVXFqMFowjpVBs8,11058
 haiku/rag/monitor.py,sha256=r386nkhdlsU8UECwIuVwnrSlgMk3vNIuUZGNIzkZuec,2770
 haiku/rag/reader.py,sha256=qkPTMJuQ_o4sK-8zpDl9WFYe_MJ7aL_gUw6rczIpW-g,3274
-haiku/rag/utils.py,sha256=hKH8bBBbAVYlLFBOAcErvX-4cuWIaPTbrAFeeLN1HdM,5062
+haiku/rag/utils.py,sha256=dBzhKaOHI9KRiJqHErcXUnqtnXY2AgOK8PCLA3rhO0A,6115
 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
@@ -35,9 +35,9 @@ haiku/rag/research/nodes/evaluate.py,sha256=Cp2J-jXYZothiQV3zRZFaCsBLaUU0Tm_-ri-
 haiku/rag/research/nodes/plan.py,sha256=9AkTls01Q3zTLKGgIgSCX9X4VYC8IWjEWii8A_f77YQ,2439
 haiku/rag/research/nodes/search.py,sha256=2ioc5Ba3ciq2zpFxgzoGkZOvVsJ1TBX9zseURLDJpBg,3591
 haiku/rag/research/nodes/synthesize.py,sha256=4acKduqWnE11ML7elUksKLozxzWJTkBLSJ2li_YMxgY,1736
-haiku/rag/store/__init__.py,sha256=hq0W0DAC7ysqhWSP2M2uHX8cbG6kbr-sWHxhq6qQcY0,103
+haiku/rag/store/__init__.py,sha256=R2IRcxtkFDxqa2sgMirqLq3l2-FPdWr6ydYStaqm5OQ,104
 haiku/rag/store/engine.py,sha256=BceAeTpDgV92B1A3GVcjsTwlD-c0cZPPvGiXW2Gola0,10215
-haiku/rag/store/models/__init__.py,sha256=s0E72zneGlowvZrFWaNxHYjOAUjgWdLxzdYsnvNRVlY,88
+haiku/rag/store/models/__init__.py,sha256=kc7Ctf53Jr483tk4QTIrcgqBbXDz4ZoeYSkFXfPnpks,89
 haiku/rag/store/models/chunk.py,sha256=3EuZav4QekJIeHBCub48EM8SjNX8HEJ6wVDXGot4PEQ,421
 haiku/rag/store/models/document.py,sha256=cZXy_jEti-hnhq7FKhuhCfd99ccY9fIHMLovB_Thbb8,425
 haiku/rag/store/repositories/__init__.py,sha256=Olv5dLfBQINRV3HrsfUpjzkZ7Qm7goEYyMNykgo_DaY,291
@@ -47,8 +47,8 @@ haiku/rag/store/repositories/settings.py,sha256=7XMBMavU8zRgdBoQzQg0Obfa7UKjuVnB
 haiku/rag/store/upgrades/__init__.py,sha256=RQ8A6rEXBASLb5PD9vdDnEas_m_GgRzzdVu4B88Snqc,1975
 haiku/rag/store/upgrades/v0_10_1.py,sha256=qNGnxj6hoHaHJ1rKTiALfw0c9NQOi0KAK-VZCD_073A,1959
 haiku/rag/store/upgrades/v0_9_3.py,sha256=NrjNilQSgDtFWRbL3ZUtzQzJ8tf9u0dDRJtnDFwwbdw,3322
-haiku_rag-0.10.1.dist-info/METADATA,sha256=Bu1Nmz3AoD_EquvCvsbcJjGXmFsGDEwqnfaYIBgOLqQ,5879
-haiku_rag-0.10.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.10.1.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.10.1.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.10.1.dist-info/RECORD,,
+haiku_rag-0.10.2.dist-info/METADATA,sha256=Q-yJHHYbis9EtHkAW6I9IhATxh8a2XOinzLj6Z40NZY,5973
+haiku_rag-0.10.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.10.2.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.10.2.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.10.2.dist-info/RECORD,,