6623928b95
A recent change meant that llm instance got cached internally, repeat calls to inference would cache data in Endpoint object leading model to failures. Both Gemini and Open AI expect a clean endpoint object cause they set data. This amends internals to make sure llm.generate will always operate on clean objects |
||
|---|---|---|
| .. | ||
| dialects | ||
| endpoints | ||
| function_call_normalizer.rb | ||
| llm.rb | ||
| prompt.rb | ||
| upload_encoder.rb | ||