Skip to content

Fix #249: Fix IndexError when model string has no separator #5

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

Open
gtx20060124-bot wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix #249: Fix IndexError when model string has no separator #5

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
11 changes: 8 additions & 3 deletions src/opengradient/client/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,11 @@ class _ChatParams:
x402_settlement_mode: x402SettlementMode


def _model_id(model: str) -> str:
"""Extract model ID from a TEE_LLM value, handling plain strings without separator."""
return model.split("/")[1] if "/" in model else model


class LLM:
"""
LLM inference namespace.
Expand Down Expand Up @@ -277,7 +282,7 @@ async def completion(
Raises:
RuntimeError: If the inference fails.
"""
model_id = model.split("/")[1]
model_id = _model_id(model)
payload: Dict = {
"model": model_id,
"prompt": prompt,
Expand Down Expand Up @@ -360,15 +365,15 @@ async def chat(
RuntimeError: If the inference fails.
"""
if response_format is not None and response_format.type == "json_object":
provider = model.split("/")[0]
provider = model.split("/")[0] if "/" in model else None
if provider == "anthropic":
raise ValueError(
"Anthropic models do not support response_format type 'json_object'. "
"Use ResponseFormat(type='json_schema', json_schema={...}) with an explicit schema instead."
)

params = _ChatParams(
model=model.split("/")[1],
model=_model_id(model),
max_tokens=max_tokens,
temperature=temperature,
stop_sequence=stop_sequence,
Expand Down