perf: prevent temp file leftovers, reuse core type (#487)

* chore: reuse DocumentStream from docling-core

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* update docling-core version

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* [skip ci] document  import line

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* fix: use new resolve_source_to_x functions to avoid tempfile leftovers (#490)

use new resolve_source_to_x functions

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
This commit is contained in:
Panos Vagenas
2024-12-03 10:40:28 +01:00
committed by GitHub
parent d3f84b2457
commit 051789d017
5 changed files with 103 additions and 97 deletions

View File

@@ -32,7 +32,7 @@ from docling_core.types.legacy_doc.document import (
)
from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
from docling_core.utils.file import resolve_file_source
from docling_core.utils.file import resolve_source_to_stream
from pydantic import BaseModel
from typing_extensions import deprecated
@@ -459,7 +459,7 @@ class _DocumentConversionInput(BaseModel):
self, format_options: Dict[InputFormat, "FormatOption"]
) -> Iterable[InputDocument]:
for item in self.path_or_stream_iterator:
obj = resolve_file_source(item) if isinstance(item, str) else item
obj = resolve_source_to_stream(item) if isinstance(item, str) else item
format = self._guess_format(obj)
if format not in format_options.keys():
_log.info(