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

Refactor function name (#11210)

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

As title

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2025-11-12 19:00:15 +08:00
committed by GitHub
parent a36a0fe71c
commit 296476ab89
20 changed files with 105 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
rag/nlp/search.py
View File

@ -102,7 +102,7 @@ class Dealer:
orderBy.asc("top_int")
orderBy.desc("create_timestamp_flt")
res = self.dataStore.search(src, [], filters, [], orderBy, offset, limit, idx_names, kb_ids)
total = self.dataStore.getTotal(res)
total = self.dataStore.get_total(res)
logging.debug("Dealer.search TOTAL: {}".format(total))
else:
highlightFields = ["content_ltks", "title_tks"]
@ -115,7 +115,7 @@ class Dealer:
matchExprs = [matchText]
res = self.dataStore.search(src, highlightFields, filters, matchExprs, orderBy, offset, limit,
idx_names, kb_ids, rank_feature=rank_feature)
total = self.dataStore.getTotal(res)
total = self.dataStore.get_total(res)
logging.debug("Dealer.search TOTAL: {}".format(total))
else:
matchDense = self.get_vector(qst, emb_mdl, topk, req.get("similarity", 0.1))
@ -127,20 +127,20 @@ class Dealer:
res = self.dataStore.search(src, highlightFields, filters, matchExprs, orderBy, offset, limit,
idx_names, kb_ids, rank_feature=rank_feature)
total = self.dataStore.getTotal(res)
total = self.dataStore.get_total(res)
logging.debug("Dealer.search TOTAL: {}".format(total))
# If result is empty, try again with lower min_match
if total == 0:
if filters.get("doc_id"):
res = self.dataStore.search(src, [], filters, [], orderBy, offset, limit, idx_names, kb_ids)
total = self.dataStore.getTotal(res)
total = self.dataStore.get_total(res)
else:
matchText, _ = self.qryr.question(qst, min_match=0.1)
matchDense.extra_options["similarity"] = 0.17
res = self.dataStore.search(src, highlightFields, filters, [matchText, matchDense, fusionExpr],
orderBy, offset, limit, idx_names, kb_ids, rank_feature=rank_feature)
total = self.dataStore.getTotal(res)
total = self.dataStore.get_total(res)
logging.debug("Dealer.search 2 TOTAL: {}".format(total))
for k in keywords:
@ -153,17 +153,17 @@ class Dealer:
kwds.add(kk)
logging.debug(f"TOTAL: {total}")
ids = self.dataStore.getChunkIds(res)
ids = self.dataStore.get_chunk_ids(res)
keywords = list(kwds)
highlight = self.dataStore.getHighlight(res, keywords, "content_with_weight")
aggs = self.dataStore.getAggregation(res, "docnm_kwd")
highlight = self.dataStore.get_highlight(res, keywords, "content_with_weight")
aggs = self.dataStore.get_aggregation(res, "docnm_kwd")
return self.SearchResult(
total=total,
ids=ids,
query_vector=q_vec,
aggregation=aggs,
highlight=highlight,
field=self.dataStore.getFields(res, src + ["_score"]),
field=self.dataStore.get_fields(res, src + ["_score"]),
keywords=keywords
)
@ -488,7 +488,7 @@ class Dealer:
for p in range(offset, max_count, bs):
es_res = self.dataStore.search(fields, [], condition, [], orderBy, p, bs, index_name(tenant_id),
kb_ids)
dict_chunks = self.dataStore.getFields(es_res, fields)
dict_chunks = self.dataStore.get_fields(es_res, fields)
for id, doc in dict_chunks.items():
doc["id"] = id
if dict_chunks:
@ -501,11 +501,11 @@ class Dealer:
if not self.dataStore.indexExist(index_name(tenant_id), kb_ids[0]):
return []
res = self.dataStore.search([], [], {}, [], OrderByExpr(), 0, 0, index_name(tenant_id), kb_ids, ["tag_kwd"])
return self.dataStore.getAggregation(res, "tag_kwd")
return self.dataStore.get_aggregation(res, "tag_kwd")
def all_tags_in_portion(self, tenant_id: str, kb_ids: list[str], S=1000):
res = self.dataStore.search([], [], {}, [], OrderByExpr(), 0, 0, index_name(tenant_id), kb_ids, ["tag_kwd"])
res = self.dataStore.getAggregation(res, "tag_kwd")
res = self.dataStore.get_aggregation(res, "tag_kwd")
total = np.sum([c for _, c in res])
return {t: (c + 1) / (total + S) for t, c in res}
@ -513,7 +513,7 @@ class Dealer:
idx_nm = index_name(tenant_id)
match_txt = self.qryr.paragraph(doc["title_tks"] + " " + doc["content_ltks"], doc.get("important_kwd", []), keywords_topn)
res = self.dataStore.search([], [], {}, [match_txt], OrderByExpr(), 0, 0, idx_nm, kb_ids, ["tag_kwd"])
aggs = self.dataStore.getAggregation(res, "tag_kwd")
aggs = self.dataStore.get_aggregation(res, "tag_kwd")
if not aggs:
return False
cnt = np.sum([c for _, c in aggs])
@ -529,7 +529,7 @@ class Dealer:
idx_nms = [index_name(tid) for tid in tenant_ids]
match_txt, _ = self.qryr.question(question, min_match=0.0)
res = self.dataStore.search([], [], {}, [match_txt], OrderByExpr(), 0, 0, idx_nms, kb_ids, ["tag_kwd"])
aggs = self.dataStore.getAggregation(res, "tag_kwd")
aggs = self.dataStore.get_aggregation(res, "tag_kwd")
if not aggs:
return {}
cnt = np.sum([c for _, c in aggs])
@ -552,7 +552,7 @@ class Dealer:
es_res = self.dataStore.search(["content_with_weight"], [], {"doc_id": doc_id, "toc_kwd": "toc"}, [], OrderByExpr(), 0, 128, idx_nms,
kb_ids)
toc = []
dict_chunks = self.dataStore.getFields(es_res, ["content_with_weight"])
dict_chunks = self.dataStore.get_fields(es_res, ["content_with_weight"])
for _, doc in dict_chunks.items():
try:
toc.extend(json.loads(doc["content_with_weight"]))