Currently we return only the text predicted from the LLM. This was nice in that it was simple, but there may be other info we want to know from the processing. This change adds the ability to return more information from the runner than just the text predicted. |
||
|---|---|---|
| .. | ||
| llm_darwin.go | ||
| llm_linux.go | ||
| llm_windows.go | ||
| memory.go | ||
| memory_test.go | ||
| server.go | ||
| server_test.go | ||
| status.go | ||