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

Feat: add splitter (#10161)

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


### Type of change
- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
This commit is contained in:
Kevin Hu
2025-09-19 10:15:19 +08:00
committed by GitHub
parent f9c7404bee
commit a1b947ffd6
81 changed files with 3083 additions and 799 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
api/apps/document_app.py
View File

@ -182,6 +182,7 @@ def create():
"id": get_uuid(),
"kb_id": kb.id,
"parser_id": kb.parser_id,
"pipeline_id": kb.pipeline_id,
"parser_config": kb.parser_config,
"created_by": current_user.id,
"type": FileType.VIRTUAL,
@ -546,31 +547,22 @@ def get(doc_id):
@manager.route("/change_parser", methods=["POST"]) # noqa: F821
@login_required
@validate_request("doc_id", "parser_id")
@validate_request("doc_id")
def change_parser():
req = request.json
if not DocumentService.accessible(req["doc_id"], current_user.id):
return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
try:
e, doc = DocumentService.get_by_id(req["doc_id"])
if not e:
return get_data_error_result(message="Document not found!")
if doc.parser_id.lower() == req["parser_id"].lower():
if "parser_config" in req:
if req["parser_config"] == doc.parser_config:
return get_json_result(data=True)
else:
return get_json_result(data=True)
if (doc.type == FileType.VISUAL and req["parser_id"] != "picture") or (re.search(r"\.(ppt|pptx|pages)$", doc.name) and req["parser_id"] != "presentation"):
return get_data_error_result(message="Not supported yet!")
e, doc = DocumentService.get_by_id(req["doc_id"])
if not e:
return get_data_error_result(message="Document not found!")
def reset_doc():
nonlocal doc
e = DocumentService.update_by_id(doc.id, {"parser_id": req["parser_id"], "progress": 0, "progress_msg": "", "run": TaskStatus.UNSTART.value})
if not e:
return get_data_error_result(message="Document not found!")
if "parser_config" in req:
DocumentService.update_parser_config(doc.id, req["parser_config"])
if doc.token_num > 0:
e = DocumentService.increment_chunk_num(doc.id, doc.kb_id, doc.token_num * -1, doc.chunk_num * -1, doc.process_duration * -1)
if not e:
@ -581,6 +573,26 @@ def change_parser():
if settings.docStoreConn.indexExist(search.index_name(tenant_id), doc.kb_id):
settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id)
try:
if req.get("pipeline_id"):
if doc.pipeline_id == req["pipeline_id"]:
return get_json_result(data=True)
DocumentService.update_by_id(doc.id, {"pipeline_id": req["pipeline_id"]})
reset_doc()
return get_json_result(data=True)
if doc.parser_id.lower() == req["parser_id"].lower():
if "parser_config" in req:
if req["parser_config"] == doc.parser_config:
return get_json_result(data=True)
else:
return get_json_result(data=True)
if (doc.type == FileType.VISUAL and req["parser_id"] != "picture") or (re.search(r"\.(ppt|pptx|pages)$", doc.name) and req["parser_id"] != "presentation"):
return get_data_error_result(message="Not supported yet!")
if "parser_config" in req:
DocumentService.update_parser_config(doc.id, req["parser_config"])
reset_doc()
return get_json_result(data=True)
except Exception as e:
return server_error_response(e)