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

Use 'float' explicitly for OpenAI's embedding "encoding_format" (#9838)

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

The default value for OpenAI '/v1/embeddings' parameter
'encoding_format' is 'base64'. Use 'float' explicitly to avoid base64
encoding & decoding, larger data size.


https://github.com/openai/openai-python/blob/main/src/openai/resources/embeddings.py
        if not is_given(encoding_format):
            params["encoding_format"] = "base64"

### Type of change

- [x] Performance Improvement
This commit is contained in:
Haiyue Wang
2025-09-02 10:31:51 +08:00
committed by GitHub
parent 0b456a18a3
commit 2e00d8d3d4
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/llm/embedding_model.py
View File

@ -145,7 +145,7 @@ class OpenAIEmbed(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 = self.client.embeddings.create(input=texts[i : i + batch_size], model=self.model_name, encoding_format="float")
try: try:
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)
@ -154,7 +154,7 @@ class OpenAIEmbed(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=[truncate(text, 8191)], model=self.model_name) res = self.client.embeddings.create(input=[truncate(text, 8191)], model=self.model_name, encoding_format="float")
return np.array(res.data[0].embedding), self.total_token_count(res) return np.array(res.data[0].embedding), self.total_token_count(res)