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 graphrag (#1793)

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

#1594

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2024-08-02 18:51:14 +08:00
committed by GitHub
parent 80032b1fc0
commit 152072f900
74 changed files with 2522 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
rag/nlp/search.py
View File

@ -64,24 +64,25 @@ class Dealer:
"query_vector": [float(v) for v in qv]
}
def _add_filters(self, bqry, req):
if req.get("kb_ids"):
bqry.filter.append(Q("terms", kb_id=req["kb_ids"]))
if req.get("doc_ids"):
bqry.filter.append(Q("terms", doc_id=req["doc_ids"]))
if req.get("knowledge_graph_kwd"):
bqry.filter.append(Q("terms", knowledge_graph_kwd=req["knowledge_graph_kwd"]))
if "available_int" in req:
if req["available_int"] == 0:
bqry.filter.append(Q("range", available_int={"lt": 1}))
else:
bqry.filter.append(
Q("bool", must_not=Q("range", available_int={"lt": 1})))
return bqry
def search(self, req, idxnm, emb_mdl=None):
qst = req.get("question", "")
bqry, keywords = self.qryr.question(qst)
def add_filters(bqry):
nonlocal req
if req.get("kb_ids"):
bqry.filter.append(Q("terms", kb_id=req["kb_ids"]))
if req.get("doc_ids"):
bqry.filter.append(Q("terms", doc_id=req["doc_ids"]))
if "available_int" in req:
if req["available_int"] == 0:
bqry.filter.append(Q("range", available_int={"lt": 1}))
else:
bqry.filter.append(
Q("bool", must_not=Q("range", available_int={"lt": 1})))
return bqry
bqry = add_filters(bqry)
bqry = self._add_filters(bqry, req)
bqry.boost = 0.05
s = Search()
@ -89,7 +90,7 @@ class Dealer:
topk = int(req.get("topk", 1024))
ps = int(req.get("size", topk))
src = req.get("fields", ["docnm_kwd", "content_ltks", "kb_id", "img_id", "title_tks", "important_kwd",
"image_id", "doc_id", "q_512_vec", "q_768_vec", "position_int",
"image_id", "doc_id", "q_512_vec", "q_768_vec", "position_int", "knowledge_graph_kwd",
"q_1024_vec", "q_1536_vec", "available_int", "content_with_weight"])
s = s.query(bqry)[pg * ps:(pg + 1) * ps]
@ -137,7 +138,7 @@ class Dealer:
es_logger.info("TOTAL: {}".format(self.es.getTotal(res)))
if self.es.getTotal(res) == 0 and "knn" in s:
bqry, _ = self.qryr.question(qst, min_match="10%")
bqry = add_filters(bqry)
bqry = self._add_filters(bqry)
s["query"] = bqry.to_dict()
s["knn"]["filter"] = bqry.to_dict()
s["knn"]["similarity"] = 0.17