NVIDIA / NVIDIA/NeMo-Retriever
[BUG]: Doesn't recognize charts in files other than PDF
Open
Nobody has claimed this yet.
bug
- Dominant language
- Python
- Stars
- 3k
- Forks
- 349
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
Version
24.12
Which installation method(s) does this occur on?
Source
Describe the bug.
Ingestion of pdf files extracts charts as structured document_types but it doesn't extract charts from pptx and docx files.
Minimum reproducible example
`
ingestor = (
Ingestor(message_client_hostname=HTTP_HOST, message_client_port=HTTP_PORT)
.files('sample-test.pptx')
.extract(
extract_text=True,
extract_tables=True,
extract_charts=True,
extract_images=True,
text_depth="document",
).dedup(
content_type="image",
filter=True,
).store(
structured=True,
images=True,
store_method="minio",
params={
"access_key": MINIO_ACCESS_KEY,
"secret_key": MINIO_SECRET_KEY,
}
)
)
generated_metadata = ingestor.ingest()[0]
`
Relevant log output
`
for i in range(len(generated_metadata)):
print(generated_metadata[i]['document_type'])
`
image
structured
structured
structured
text
Other/Misc.
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the provided Python Ingestor reproduction using the sample PPTX, then compare chart extraction for PDF, PPTX, and DOCX inputs. Confirm that PPTX and DOCX charts are emitted as structured document types alongside the existing PDF behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100