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

deal with stop reason being length problem (#109)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-07 16:12:01 +08:00
committed by GitHub
parent b69b5dd4e5
commit 2d7c9080f4
6 changed files with 59 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
rag/nlp/search.py
View File

@ -224,12 +224,13 @@ class Dealer:
chunks_tks,
tkweight, vtweight)
mx = np.max(sim) * 0.99
if mx < 0.35:
if mx < 0.66:
continue
cites[idx[i]] = list(
set([str(ii) for ii in range(len(chunk_v)) if sim[ii] > mx]))[:4]
res = ""
seted = set([])
for i, p in enumerate(pieces):
res += p
if i not in idx:
@ -237,7 +238,10 @@ class Dealer:
if i not in cites:
continue
for c in cites[i]: assert int(c) < len(chunk_v)
for c in cites[i]: res += f" ##{c}$$"
for c in cites[i]:
if c in seted:continue
res += f" ##{c}$$"
seted.add(c)
return res
@ -318,7 +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