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

add use layout or not option (#145)

Browse Source 
* add use layout or not option

* trival
This commit is contained in:
KevinHuSh
2024-03-22 19:21:09 +08:00
committed by GitHub
parent 2f4c71b4b4
commit f6aee7f230
18 changed files with 238 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
api/apps/conversation_app.py
View File

@ -196,7 +196,10 @@ def chat(dialog, messages, **kwargs):
for _ in range(len(questions)//2):
questions.append(questions[-1])
kbinfos = retrievaler.retrieval(" ".join(questions), embd_mdl, dialog.tenant_id, dialog.kb_ids, 1, dialog.top_n,
if "knowledge" not in [p["key"] for p in prompt_config["parameters"]]:
kbinfos = {"total":0, "chunks":[],"doc_aggs":[]}
else:
kbinfos = retrievaler.retrieval(" ".join(questions), embd_mdl, dialog.tenant_id, dialog.kb_ids, 1, dialog.top_n,
dialog.similarity_threshold,
dialog.vector_similarity_weight, top=1024, aggs=False)
knowledges = [ck["content_with_weight"] for ck in kbinfos["chunks"]]

7
api/apps/document_app.py
View File

@ -310,7 +310,10 @@ def change_parser():
if not e:
return get_data_error_result(retmsg="Document not found!")
if doc.parser_id.lower() == req["parser_id"].lower():
return get_json_result(data=True)
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 or re.search(r"\.(ppt|pptx|pages)$", doc.name):
return get_data_error_result(retmsg="Not supported yet!")
@ -319,6 +322,8 @@ def change_parser():
{"parser_id": req["parser_id"], "progress": 0, "progress_msg": "", "run": "0"})
if not e:
return get_data_error_result(retmsg="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_duation * -1)