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

Refactor: Improve the try catch logic for XinferenceEmbed (#9128)

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

Improve the try catch logic for XinferenceEmbed

### Type of change


- [x] Refactoring
This commit is contained in:
Stephen Hu
2025-07-31 12:14:50 +08:00
committed by GitHub
parent 0327fd848e
commit 20b4d88098
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/llm/embedding_model.py
View File

@ -378,8 +378,9 @@ class XinferenceEmbed(Base):
ress = [] ress = []
total_tokens = 0 total_tokens = 0
for i in range(0, len(texts), batch_size): for i in range(0, len(texts), batch_size):
res = self.client.embeddings.create(input=texts[i : i + batch_size], model=self.model_name) res = None
try: try:
res = self.client.embeddings.create(input=texts[i : i + batch_size], model=self.model_name)
ress.extend([d.embedding for d in res.data]) ress.extend([d.embedding for d in res.data])
total_tokens += self.total_token_count(res) total_tokens += self.total_token_count(res)
except Exception as _e: except Exception as _e:
@ -387,8 +388,9 @@ class XinferenceEmbed(Base):
return np.array(ress), total_tokens return np.array(ress), total_tokens
def encode_queries(self, text): def encode_queries(self, text):
res = self.client.embeddings.create(input=[text], model=self.model_name) res = None
try: try:
res = self.client.embeddings.create(input=[text], model=self.model_name)
return np.array(res.data[0].embedding), self.total_token_count(res) return np.array(res.data[0].embedding), self.total_token_count(res)
except Exception as _e: except Exception as _e:
log_exception(_e, res) log_exception(_e, res)