mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-07-12 06:42:11 +02:00
2f23efc269
The OpenAI API deprecated `max_tokens` in favor of `max_completion_tokens` for chat completion endpoints. Newer models (gpt-4o, o1, o3, gpt-5.x) reject `max_tokens` with: "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead." This updates both the OpenAI and Azure OpenAI text completion providers to use the new parameter name. Fixes both streaming and non-streaming code paths. |
||
|---|---|---|
| .. | ||
| trustgraph | ||
| pyproject.toml | ||
| README.md | ||