Weight up title and keywords for chunks in terms of retrieval (#3750)

### What problem does this PR solve?


### Type of change

- [x] Performance Improvement

rag/nlp/search.py

@@ -250,7 +250,7 @@ def rerank(self, sres, query, tkweight=0.3,
             content_ltks = sres.field[i][cfield].split()
             title_tks = [t for t in sres.field[i].get("title_tks", "").split() if t]
             important_kwd = sres.field[i].get("important_kwd", [])
-            tks = content_ltks + title_tks + important_kwd
+            tks = content_ltks + title_tks*2 + important_kwd*5
             ins_tw.append(tks)
 
         sim, tksim, vtsim = self.qryr.hybrid_similarity(sres.query_vector,