Fix dify retrieval issue. (#4473)

### What problem does this PR solve?

#4464
#4469 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu 2025-01-14 13:16:05 +08:00 committed by GitHub
parent f318342c8e
commit f556f0239c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions

View File

@ -62,7 +62,7 @@ def retrieval(tenant_id):
for c in ranks["chunks"]:
c.pop("vector", None)
records.append({
"content": c["content_ltks"],
"content": c["content_with_weight"],
"score": c["similarity"],
"title": c["docnm_kwd"],
"metadata": {}

View File

@ -70,7 +70,7 @@ class Pdf(PdfParser):
for b in self.boxes:
b["text"] = re.sub(r"([\t  ]|\u3000){2,}", " ", b["text"].strip())
return [(b["text"], b.get("layout_no", ""), self.get_position(b, zoomin))
return [(b["text"], b.get("layoutno", ""), self.get_position(b, zoomin))
for i, b in enumerate(self.boxes)], tbls