The community member is having an issue using the markdownElementNodeParser with fastEmbedding and ollama, loading files using SimpleDirectoryReader. Another community member suggests adding the nest_async piece of text at the top, as they see a mention of coroutine in the error. The community member confirms they have added import nest_asyncionest_asyncio.apply().
The issue is then resolved, but the community member encountered a problem with ollama, where they received errors related to CUDA and the llama runner process terminating. Restarting the machine fixed the issue, and another community member comments that "Restarting is the universal solution".
Hello, i have this issue when I try using the markdownElementNodeParser, i'm using fastEmbedding and ollama loading the files using SimpleDirectoryReader
It works right now, there was something wrong with ollama, i tried running the llm on my terminal and got these errors : llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_NOT_INITIALIZED current device: 1, in function cublas_handle at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda/common.cuh:653 cublasCreate_v2(&cublas_handles[device]) GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu !"CUDA error"
