dale_yxc/ragflow_python
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix too long query exception (#1195)

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

#1161 
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
KevinHuSh
2024-06-18 09:50:59 +08:00
committed by GitHub
parent 7920a5c78d
commit e35f7610e7
4 changed files with 19 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
rag/app/qa.py
View File

@@ -145,6 +145,7 @@ def beAdoc(d, q, a, eng):
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
return d
def mdQuestionLevel(s):
match = re.match(r'#*', s)
return (len(match.group(0)), s.lstrip('#').lstrip()) if match else (0, s)
@@ -244,7 +245,6 @@ def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
break
txt += l
lines = txt.split("\n")
comma, tab = 0, 0
last_question, last_answer = "", ""
question_stack, level_stack = [], []
code_block = False
@@ -262,7 +262,7 @@ def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
last_answer = f'{last_answer}\n{l}'
else: # is a question
if last_answer:
sum_question = ('\n').join(question_stack)
sum_question = '\n'.join(question_stack)
if sum_question:
res.append(beAdoc(deepcopy(doc), sum_question, last_answer, eng))
last_answer = ''
@@ -274,12 +274,11 @@ def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
question_stack.append(question)
level_stack.append(question_level)
if last_answer:
sum_question = ('\n').join(question_stack)
sum_question = '\n'.join(question_stack)
if sum_question:
res.append(beAdoc(deepcopy(doc), sum_question, last_answer, eng))
return res
raise NotImplementedError(
"Excel, csv(txt), pdf and markdown format files are supported.")

1
rag/nlp/query.py
View File

@@ -110,6 +110,7 @@ class EsQueryer:
sm = []
keywords.append(re.sub(r"[ \\\"']+", "", tk))
if len(keywords) >= 12: break
tk_syns = self.syn.lookup(tk)
tk = EsQueryer.subSpecialChar(tk)

4
rag/nlp/search.py
View File

@@ -98,7 +98,7 @@ class Dealer:
if not qst:
if not req.get("sort"):
s = s.sort(
{"create_time": {"order": "desc", "unmapped_type": "date"}},
#{"create_time": {"order": "desc", "unmapped_type": "date"}},
{"create_timestamp_flt": {
"order": "desc", "unmapped_type": "float"}}
)
@@ -108,7 +108,7 @@ class Dealer:
"mode": "avg", "numeric_type": "double"}},
{"top_int": {"order": "asc", "unmapped_type": "float",
"mode": "avg", "numeric_type": "double"}},
{"create_time": {"order": "desc", "unmapped_type": "date"}},
#{"create_time": {"order": "desc", "unmapped_type": "date"}},
{"create_timestamp_flt": {
"order": "desc", "unmapped_type": "float"}}
)