AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 02:29:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

accelerate tokenize (#3244)

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


### Type of change

- [x] Performance Improvement
This commit is contained in:
Kevin Hu 2024-11-06 18:54:41 +08:00 committed by GitHub
parent d3bb5e9f3d
commit fbcc0bb408
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 38 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
rag/nlp/rag_tokenizer.py
View File

@ -281,34 +281,49 @@ class RagTokenizer:
print("[FW]", tks, s)
print("[BW]", tks1, s1)
diff = [0 for _ in range(max(len(tks1), len(tks)))]
for i in range(min(len(tks1), len(tks))):
if tks[i] != tks1[i]:
diff[i] = 1
i, j, _i, _j = 0, 0, 0, 0
same = 0
while i + same < len(tks1) and j + same < len(tks) and tks1[i + same] == tks[j + same]:
same += 1
if same > 0: res.append(" ".join(tks[j: j + same]))
_i = i + same
_j = j + same
j = _j + 1
i = _i + 1
if s1 > s:
tks = tks1
i = 0
while i < len(tks):
s = i
while s < len(tks) and diff[s] == 0:
s += 1
if s == len(tks):
res.append(" ".join(tks[i:]))
break
if s > i:
res.append(" ".join(tks[i:s]))
e = s
while e < len(tks) and e - s < 5 and diff[e] == 1:
e += 1
while i < len(tks1) and j < len(tks):
tk1, tk = "".join(tks1[_i:i]), "".join(tks[_j:j])
if tk1 != tk:
if len(tk1) > len(tk):
j += 1
else:
i += 1
continue
if tks1[i] != tks[j]:
i += 1
j += 1
continue
# backward tokens from_i to i are different from forward tokens from _j to j.
tkslist = []
self.dfs_("".join(tks[s:e + 1]), 0, [], tkslist)
self.dfs_("".join(tks[_j:j]), 0, [], tkslist)
res.append(" ".join(self.sortTks_(tkslist)[0][0]))
i = e + 1
same = 1
while i + same < len(tks1) and j + same < len(tks) and tks1[i + same] == tks[j + same]:
same += 1
res.append(" ".join(tks[j: j + same]))
_i = i + same
_j = j + same
j = _j + 1
i = _i + 1
if _i < len(tks1):
assert _j < len(tks)
assert "".join(tks1[_i:]) == "".join(tks[_j:])
tkslist = []
self.dfs_("".join(tks[_j:]), 0, [], tkslist)
res.append(" ".join(self.sortTks_(tkslist)[0][0]))
res = " ".join(self.english_normalize_(res))
if self.DEBUG: