pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: correctly update parser method & correct vllm pdf parser (#10441)

Browse Source 
### What problem does this PR solve?

Fix: correctly update parser method

### Type of change

- [X] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Billy Bao
2025-10-09 19:03:12 +08:00
committed by GitHub
parent 1fc2889f98
commit f04c9e2937
2 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/apps/document_app.py
View File

@ -557,8 +557,8 @@ def get(doc_id):
@login_required @login_required
@validate_request("doc_id") @validate_request("doc_id")
def change_parser(): def change_parser():
req = request.json
req = request.json
if not DocumentService.accessible(req["doc_id"], current_user.id): if not DocumentService.accessible(req["doc_id"], current_user.id):
return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR) return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
@ -582,7 +582,7 @@ def change_parser():
settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id) settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id)
try: try:
if "pipeline_id" in req: if "pipeline_id" in req and req["pipeline_id"] != "":
if doc.pipeline_id == req["pipeline_id"]: if doc.pipeline_id == req["pipeline_id"]:
return get_json_result(data=True) return get_json_result(data=True)
DocumentService.update_by_id(doc.id, {"pipeline_id": req["pipeline_id"]}) DocumentService.update_by_id(doc.id, {"pipeline_id": req["pipeline_id"]})

6
deepdoc/parser/pdf_parser.py
View File

@ -1274,12 +1274,16 @@ class VisionParser(RAGFlowPdfParser):
prompt=vision_llm_describe_prompt(page=pdf_page_num + 1), prompt=vision_llm_describe_prompt(page=pdf_page_num + 1),
callback=callback, callback=callback,
) )
if kwargs.get("callback"): if kwargs.get("callback"):
kwargs["callback"](idx * 1.0 / len(self.page_images), f"Processed: {idx + 1}/{len(self.page_images)}") kwargs["callback"](idx * 1.0 / len(self.page_images), f"Processed: {idx + 1}/{len(self.page_images)}")
if text: if text:
width, height = self.page_images[idx].size width, height = self.page_images[idx].size
all_docs.append((text, f"{pdf_page_num + 1} 0 {width / zoomin} 0 {height / zoomin}")) all_docs.append((
text,
f"@@{pdf_page_num + 1}\t{0.0:.1f}\t{width / zoomin:.1f}\t{0.0:.1f}\t{height / zoomin:.1f}##"
))
return all_docs, [] return all_docs, []