I've been actively working on a RAG project using Kendra and Llama 2. Everything has been functioning well until very recently, where I encountered the following error: ValueError: Error raised by the inference endpoint: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (422) from primary with message "Failed to deserialize the JSON body into the target type: inputs: invalid type: sequence, expected a string at line 1 column 11".
I also attempted to run the most recent kendra_chat_llama_2.py file, and it encountered the same error. My question is whether this issue is stemming from AWS SageMaker or if it's related to the code in the git repository? Your insights would be greatly appreciated.
MithilShah
commented
9 months ago
Hello all,
I've been actively working on a RAG project using Kendra and Llama 2. Everything has been functioning well until very recently, where I encountered the following error: ValueError: Error raised by the inference endpoint: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (422) from primary with message "Failed to deserialize the JSON body into the target type: inputs: invalid type: sequence, expected a string at line 1 column 11".
I also attempted to run the most recent kendra_chat_llama_2.py file, and it encountered the same error. My question is whether this issue is stemming from AWS SageMaker or if it's related to the code in the git repository? Your insights would be greatly appreciated.
Thank you!