gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Refactor:remove use less convert for FastEmbed (#8984)

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

remove use less convert for FastEmbed

### Type of change

- [x] Refactoring
This commit is contained in:
Stephen Hu 2025-07-23 10:51:48 +08:00 • committed by GitHub
parent 0d7244e4a4
commit ec21d9a98f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
rag/llm/embedding_model.py
View file

@ -352,8 +352,7 @@ class FastEmbed(DefaultEmbedding):
# Using the internal tokenizer to encode the texts and get the total # Using the internal tokenizer to encode the texts and get the total
# number of tokens # number of tokens
encoding = self._model.model.tokenizer.encode(text) encoding = self._model.model.tokenizer.encode(text)
embedding = next(self._model.query_embed(text)).tolist() embedding = next(self._model.query_embed(text))
return np.array(embedding), len(encoding.ids) return np.array(embedding), len(encoding.ids)