From 76ebf08bcc9ef19e7086a69f1351c084861da20a Mon Sep 17 00:00:00 2001 From: kdziedzic68 Date: Thu, 28 Nov 2024 13:23:46 +0100 Subject: [PATCH] warn not embedded images individually --- .../src/ragbits/document_search/_main.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/packages/ragbits-document-search/src/ragbits/document_search/_main.py b/packages/ragbits-document-search/src/ragbits/document_search/_main.py index 15e40aa1..302a211c 100644 --- a/packages/ragbits-document-search/src/ragbits/document_search/_main.py +++ b/packages/ragbits-document-search/src/ragbits/document_search/_main.py @@ -167,7 +167,9 @@ async def insert_elements(self, elements: list[Element]) -> None: element.to_vector_db_entry(vector, EmbeddingTypes.TEXT) for element, vector in zip(elements_with_text, vectors, strict=False) ] - num_embedded_images = len(images_with_text) + not_embedded_image_elements = [ + image_element for image_element in image_elements if image_element not in images_with_text + ] if image_elements and self.embedder.image_support(): image_vectors = await self.embedder.embed_image([element.image_bytes for element in image_elements]) @@ -177,16 +179,14 @@ async def insert_elements(self, elements: list[Element]) -> None: for element, vector in zip(image_elements, image_vectors, strict=False) ] ) - num_embedded_images = len(image_elements) + not_embedded_image_elements = [] elif image_elements: warnings.warn( f"Image elements are not supported by the embedder {self.embedder}. " f"Skipping {len(image_elements)} image elements." ) - if len(image_elements) > num_embedded_images: - warnings.warn( - f"{len(image_elements) - num_embedded_images} of {len(image_elements)} have not been embedded" - ) + for image_element in not_embedded_image_elements: + warnings.warn(f"Image: {image_element.id} could not be embedded") await self.vector_store.store(entries)