add multi-file import support

chromy/cli.py

@@ -6,7 +6,6 @@ import typer
 from chromadb.errors import InternalError, NotFoundError
 from rich import print
 
-from chromy.errors import UnsupportedTextFileError
 from chromy.handlers.count_collection import handle_count_collection
 from chromy.handlers.create_collection import handle_create_collection
 from chromy.handlers.delete_collection import (
@@ -106,26 +105,27 @@ def count(
 # ------------------------------------------------------------------------------
 @app.command(
     "import",
-    help="Chunk, embed, and add a file to a collection in the local Chroma database.",
+    help=(
+        "Chunk, embed, and add one or more files to a collection in the "
+        "local Chroma database."
+    ),
 )
 def import_data(
     collection: Annotated[
         str,
         typer.Argument(help="Name of the target collection."),
     ],
-    file: Annotated[
-        str,
-        typer.Argument(help="Path to the file to chunk and add to the collection."),
+    files: Annotated[
+        list[str],
+        typer.Argument(
+            help="Path(s) to the file(s) to chunk and add to the collection."
+        ),
     ],
 ) -> None:
     try:
-        _run(lambda: handle_import(collection, file))
+        _run(lambda: handle_import(collection, files))
     except NotFoundError:
         _fail(f"Collection '{collection}' does not exist.")
-    except FileNotFoundError:
-        _fail(f"The file '{file}' was not found.")
-    except UnsupportedTextFileError:
-        _fail(f"The file '{file}' is not a text file.")
 
 
 # ------------------------------------------------------------------------------

chromy/handlers/import_data.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import os
 from pathlib import Path
+from typing import Final
 
 from rich import print
 
@@ -10,6 +11,9 @@ from chromy.utilities import ingest_file
 
 from ..utilities import is_probably_text_file
 
+SUCCESS_EXIT_CODE: Final = 0
+FAILURE_EXIT_CODE: Final = 1
+
 
 def _get_absolute_path(file: str) -> str:
     """
@@ -29,12 +33,49 @@ def _get_absolute_path(file: str) -> str:
     return str(file_path.resolve())
 
 
-def handle_import(collection: str, file: str) -> int:
+def _import_one(collection: str, file: str) -> int:
     absolute_path = _get_absolute_path(file)
 
+    if not Path(absolute_path).is_file():
+        raise FileNotFoundError()
+
     if not is_probably_text_file(absolute_path):
         raise UnsupportedTextFileError()
 
     records_added = ingest_file(collection, absolute_path)
-    print(f"[bold green]Added[/] {records_added} records to collection '{collection}'.")
-    return 0
+    print(
+        "[bold green]Added[/] "
+        f"{records_added} records from '{file}' to collection '{collection}'."
+    )
+    return SUCCESS_EXIT_CODE
+
+
+def handle_import(collection: str, files: list[str]) -> int:
+    successful_imports = 0
+    failed_imports = 0
+    seen_paths: set[str] = set()
+
+    for file in files:
+        try:
+            absolute_path = _get_absolute_path(file)
+            if absolute_path in seen_paths:
+                continue
+
+            seen_paths.add(absolute_path)
+            _import_one(collection, file)
+            successful_imports += 1
+        except FileNotFoundError:
+            failed_imports += 1
+            print(f"[bold red]Error[/]: The file '{file}' was not found.")
+        except UnsupportedTextFileError:
+            failed_imports += 1
+            print(f"[bold red]Error[/]: The file '{file}' is not a text file.")
+
+    print(
+        f"Imported {successful_imports} file(s) successfully; {failed_imports} failed."
+    )
+
+    if failed_imports:
+        return FAILURE_EXIT_CODE
+
+    return SUCCESS_EXIT_CODE