Skip to content

fix: prevent embedding 422 on strict OpenAI-compatible endpoints (DeepInfra, vLLM, TEI) #1430

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.

Sign up for GitHub

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

Closed
PaoloC68 wants to merge 1 commit into from
+4 −2
Closed

fix: prevent embedding 422 on strict OpenAI-compatible endpoints (DeepInfra, vLLM, TEI) #1430

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -600,7 +600,8 @@ def embed_documents(self, texts: List[str]) -> List[List[float]]:
# Apply rate limiting if configured
apply_rate_limiter_sync(self.a0_model_conf, " ".join(texts))

resp = embedding(model=self.model_name, input=texts, **self.kwargs)
embed_kwargs = {"encoding_format": "float", **self.kwargs}
resp = embedding(model=self.model_name, input=texts, **embed_kwargs)
return [
item.get("embedding") if isinstance(item, dict) else item.embedding # type: ignore
for item in resp.data # type: ignore
Expand All @@ -610,7 +611,8 @@ def embed_query(self, text: str) -> List[float]:
# Apply rate limiting if configured
apply_rate_limiter_sync(self.a0_model_conf, text)

resp = embedding(model=self.model_name, input=[text], **self.kwargs)
embed_kwargs = {"encoding_format": "float", **self.kwargs}
resp = embedding(model=self.model_name, input=[text], **embed_kwargs)
item = resp.data[0] # type: ignore
return item.get("embedding") if isinstance(item, dict) else item.embedding # type: ignore

Expand Down