echo-vector 1.0.3__tar.gz → 1.0.4__tar.gz

{echo_vector-1.0.3 → echo_vector-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: echo_vector
-Version: 1.0.3
+Version: 1.0.4
 Summary: Semantic text search over audio files without full transcription
 Project-URL: Homepage, https://github.com/ahron-maslin/echo_vector
 Project-URL: Documentation, https://github.com/ahron-maslin/echo_vector#readme

echo_vector-1.0.4/echovector/__init__.py

@@ -0,0 +1,18 @@
+"""EchoVector: Audio vector embedding and processing library."""
+
+import warnings
+
+from echovector.core import EchoVector
+
+# librosa falls back to its deprecated audioread loader for formats libsndfile
+# can't decode natively (e.g. m4a/aac), emitting a noisy FutureWarning we can't
+# act on from here.
+warnings.filterwarnings(
+    "ignore",
+    message="librosa.core.audio.__audioread_load",
+    category=FutureWarning,
+)
+
+__version__ = "0.1.0"
+
+__all__ = ["EchoVector"]

{echo_vector-1.0.3 → echo_vector-1.0.4}/echovector/cli/main.py

@@ -5,6 +5,7 @@ from typing import Annotated
 
 import typer
 from rich.console import Console
+from rich.progress import Progress
 from rich.table import Table
 
 from echovector import EchoVector
@@ -74,7 +75,16 @@ def index(
             )
         if reset:
             engine.reset()
-        count = engine.index(files, recursive=recursive)
+
+        with Progress(console=console) as progress:
+            task = progress.add_task("Indexing files...", total=None)
+
+            def _on_file_indexed(done: int, total: int, file_path: Path) -> None:
+                progress.update(
+                    task, total=total, completed=done, description=f"Indexed {file_path.name}"
+                )
+
+            count = engine.index(files, recursive=recursive, on_file_indexed=_on_file_indexed)
     except Exception as exc:
         console.print(f"[bold red]Indexing failed:[/bold red] {exc}")
         raise typer.Exit(code=1) from exc

{echo_vector-1.0.3 → echo_vector-1.0.4}/echovector/core.py

@@ -1,6 +1,6 @@
 """Core public API for EchoVector."""
 
-from collections.abc import Sequence
+from collections.abc import Callable, Sequence
 from pathlib import Path
 from tempfile import TemporaryDirectory
 from typing import Any, cast
@@ -67,6 +67,7 @@ class EchoVector:
         recursive: bool | None = None,
         batch_size: int = 16,
         force: bool = False,
+        on_file_indexed: Callable[[int, int, Path], None] | None = None,
     ) -> int:
         """Index audio chunks from paths or directories.
 
@@ -76,6 +77,9 @@ class EchoVector:
             batch_size: Number of chunks to embed per batch.
             force: If True, remove and re-index files that are already stored.
                    If False (default), already-indexed files are skipped.
+            on_file_indexed: Optional callback invoked after each file is
+                processed, with (files_done, total_files, file_path). Useful
+                for reporting progress.
 
         Returns:
             Number of new chunks added to the index.
@@ -103,7 +107,7 @@ class EchoVector:
             chunk_ids: list[str] = []
             chunk_metadata: list[dict[str, Any]] = []
 
-            for file_path in files:
+            for file_number, file_path in enumerate(files, start=1):
                 audio = self.audio_processor.load_audio(str(file_path))
                 for (
                     chunk_number,
@@ -131,6 +135,9 @@ class EchoVector:
                         chunk_ids = []
                         chunk_metadata = []
 
+                if on_file_indexed is not None:
+                    on_file_indexed(file_number, len(files), file_path)
+
             if chunk_paths:
                 self._add_chunk_batch(chunk_paths, chunk_ids, chunk_metadata)
 

echo_vector-1.0.3/echovector/__init__.py

@@ -1,7 +0,0 @@
-"""EchoVector: Audio vector embedding and processing library."""
-
-from echovector.core import EchoVector
-
-__version__ = "0.1.0"
-
-__all__ = ["EchoVector"]