- Change ChatCompletionRequest.stream default from True to False per OpenAI spec — curl without "stream" now returns a single JSON object - Fix non-streaming chat completions to include usage stats (was all 0s) - Add POST /v1/responses implementing OpenAI's Responses API format: accepts input as string or typed message array, returns Response objects with output_text content, supports both streaming and non-streaming modes |
||
|---|---|---|
| .. | ||
| assets | ||
| auth | ||
| core | ||
| loggers | ||
| models | ||
| plugins | ||
| requirements | ||
| routes | ||
| state | ||
| storage | ||
| tests | ||
| utils | ||
| __init__.py | ||
| _platform_compat.py | ||
| colab.py | ||
| main.py | ||
| run.py | ||
| startup_banner.py | ||