Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

batch提取embedding,避免文本chunk数量过多(>1000)之后报empty response from server 错误 #338

Merged
merged 1 commit into from
Feb 23, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -101,16 +101,31 @@ def embed(self, texts: List[str], **kwargs) -> List[List[float]]:
if self.verbose:
print('payload', inp)

max_text_to_split = 200
outp = None
try:
outp = self.client(url=self.url_ep, json=inp, timeout=self.request_timeout).json()
except requests.exceptions.Timeout:
raise Exception(f'timeout in host embedding infer, url=[{self.url_ep}]')
except Exception as e:
raise Exception(f'exception in host embedding infer: [{e}]')

if outp['status_code'] != 200:
raise ValueError(f"API returned an error: {outp['status_message']}")

start_index = 0
len_text = len(texts)
while start_index < len_text:
inp_local = {
'texts':texts[start_index:min(start_index + max_text_to_split, len_text)],
'model':self.model,
'type':emb_type
}
try:
outp_single = self.client(url=self.url_ep, json=inp_local, timeout=self.request_timeout).json()
if outp is None:
outp = outp_single
else:
outp['embeddings'] += outp_single['embeddings']
except requests.exceptions.Timeout:
raise Exception(f'timeout in host embedding infer, url=[{self.url_ep}]')
except Exception as e:
raise Exception(f'exception in host embedding infer: [{e}]')

if outp_single['status_code'] != 200:
raise ValueError(f"API returned an error: {outp['status_message']}")
start_index += max_text_to_split
return outp['embeddings']

def embed_documents(self,
Expand Down