The community member is trying to run a multimodal model using ollama (minicpm-v) in parallel to process the same query over multiple images at the same time, but they are encountering an error that indicates ollama does not support async completion. The comments suggest that async has not been implemented yet for the multimodal ollama class, and the community members discuss potential solutions, such as modifying the ollama LLM class to include async implementation, or exploring alternative models with async implementation outside of ollama. One community member suggests creating a pull request to update the ollama client to include the async implementation, and another community member indicates they have created a pull request for this purpose.
Hello I am trying to run a multimodal model using ollama (minicpm-v) I want to run this model in parallel to process the same query over multiple images at the same time, is this possible? I know that ollama has some concurrency parameters to run multiple models but I couldn't get it to work, I tried the "Parallel Execution of Same Event Example" cookbook workflow but I failed and got this error. Error during frame analysis: Ollama does not support async completion.
It looks like its already using the official ollama client, and I know they have an async client, so would be a straightforward PR if you want to give it a shot ❤️
