Thomas Ashish Cherian
Thomas Ashish Cherian
I converted the div into a canvas and exported it to a URL https://stackoverflow.com/a/50253915/7690738
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[512] [[Node: dense_1/bias/Assign = Assign[T=DT_FLOAT, _class=["loc:@dense_1/bias"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](dense_1/bias, dense_1/Const)]]
Yes, Im sure
Yes it still does
you can visit my blog ashish.ch to check it out
Python 3.6
looks like it @elpablete
The request timeout was added 5 months ago to openAI anyone having openai client version before might face issue cause this param didnt exist before that. https://github.com/openai/openai-python/pull/116 The issue is...
we are trying to maintain a fork here - https://github.com/pythonutilities/jinjasql for our personal and company projects
You can probably log the full prompt args after it has been formatted by langchain https://github.com/jerryjliu/gpt_index/blob/aa0092a14420a75e2e4251a2bd8aa1d5f9c28e29/gpt_index/langchain_helpers/chain_wrapper.py#L97