Is your feature request related to a problem? Please describe.
In a similar way to how the embedding pipeline was integrated, integrate the onnx gen AI runtime so LLMs can be run locally.
Describe the solution you'd like
Integration of onnx gen AI runtime so LLMs can be run and invoked locally.
Is your feature request related to a problem? Please describe.
In a similar way to how the embedding pipeline was integrated, integrate the onnx gen AI runtime so LLMs can be run locally.
Describe the solution you'd like
Integration of onnx gen AI runtime so LLMs can be run and invoked locally.