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

refine presentation parser (#110)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-07 17:21:38 +08:00
committed by GitHub
parent 2d7c9080f4
commit 436c52bbc5
3 changed files with 15 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/nlp/search.py
View File

@ -243,7 +243,7 @@ class Dealer:
res += f" ##{c}$$"
seted.add(c)
return res
return res, seted
def rerank(self, sres, query, tkweight=0.3,
vtweight=0.7, cfield="content_ltks"):
@ -290,7 +290,7 @@ class Dealer:
start_idx -= 1
if start_idx >= 0:
continue
if len(ranks["chunks"]) == page_size:
if len(ranks["chunks"]) >= page_size:
if aggs:
continue
break
@ -322,7 +322,7 @@ class Dealer:
if dnm not in ranks["doc_aggs"]:
ranks["doc_aggs"][dnm] = {"doc_id": did, "count": 0}
ranks["doc_aggs"][dnm]["count"] += 1
ranks["doc_aggs"] = []#[{"doc_name": k, "doc_id": v["doc_id"], "count": v["count"]} for k,v in sorted(ranks["doc_aggs"].items(), key=lambda x:x[1]["count"]*-1)]
ranks["doc_aggs"] = [{"doc_name": k, "doc_id": v["doc_id"], "count": v["count"]} for k,v in sorted(ranks["doc_aggs"].items(), key=lambda x:x[1]["count"]*-1)]
return ranks