Fix: debug pipeline... (#10311)

### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-09-26 19:11:30 +08:00
committed by GitHub
parent 771a38434f
commit 76b1ee2a00
18 changed files with 116 additions and 474 deletions

View File

@ -59,6 +59,7 @@ class Splitter(ProcessBase):
else:
deli += d
self.set_output("output_format", "chunks")
self.callback(random.randint(1, 5) / 100.0, "Start to split into chunks.")
if from_upstream.output_format in ["markdown", "text", "html"]:
if from_upstream.output_format == "markdown":
@ -99,7 +100,7 @@ class Splitter(ProcessBase):
{
"text": RAGFlowPdfParser.remove_tag(c),
"image": img,
"positions": [[pos[0][-1]+1, *pos[1:]] for pos in RAGFlowPdfParser.extract_positions(c)],
"positions": [[pos[0][-1], *pos[1:]] for pos in RAGFlowPdfParser.extract_positions(c)],
}
for c, img in zip(chunks, images)
]