AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-06-04 11:24:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine rerank (#1056)

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


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
KevinHuSh 2024-06-04 17:27:00 +08:00 committed by GitHub
parent 8295979bb2
commit b8eedbdd86
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
rag/llm/rerank_model.py
View File

@ -67,12 +67,12 @@ class DefaultRerank(Base):
token_count = 0 token_count = 0
for _, t in pairs: for _, t in pairs:
token_count += num_tokens_from_string(t) token_count += num_tokens_from_string(t)
batch_size = 32 batch_size = 4096
res = [] res = []
for i in range(0, len(pairs), batch_size): for i in range(0, len(pairs), batch_size):
scores = self._model.compute_score(pairs[i:i + batch_size], max_length=2048) scores = self._model.compute_score(pairs[i:i + batch_size], max_length=2048)
scores = sigmoid(np.array(scores)).tolist() if isinstance(scores, float): res.append(scores)
res.extend(scores) else: res.extend(scores)
return np.array(res), token_count return np.array(res), token_count
@ -124,7 +124,9 @@ class YoudaoRerank(DefaultRerank):
for i in range(0, len(pairs), batch_size): for i in range(0, len(pairs), batch_size):
scores = self._model.compute_score(pairs[i:i + batch_size], max_length=self._model.max_length) scores = self._model.compute_score(pairs[i:i + batch_size], max_length=self._model.max_length)
scores = sigmoid(np.array(scores)).tolist() scores = sigmoid(np.array(scores)).tolist()
if isinstance(scores, float): res.append(scores)
res.extend(scores) res.extend(scores)
return np.array(res), token_count return np.array(res), token_count