Dr. Bhaskar Tripathi

I reolved the issue by doing this : Comment this: `#from pandas.stats import moments` Use this: `import statsmodels.stats as moments`

Here is the link for collab: https://colab.research.google.com/drive/1oK6sBNYxYVAm_WrbaUIw9qQtfcNFO9Oj?usp=sharing

Well to be honest my experience with this library is very bad even though the idea of combining everything in DRL is very good but they are using just too...

> At this moment, this repo is at the beginning stage. We are aiming for standarding our data processing workflow as a team…sharing the codes we use, while supporting FinRL....

Hi Guys, I understand that it Langserve doesn't provides support now. In the hindsight, I acknowledge that I shouldn't have accepted their PR. However, you can use the original code...

Please use gpt4 or text da Vinci 002 in that case. 3.5 turbo model isn't good enough

ok. I will develop this feature and push it live very soon.

Please use the original code. It works. LC-serve contributors are not active. So you will need to take the original code directly and use it. It works perfectly: https://huggingface.co/spaces/bhaskartripathi/pdfGPT_Turbo/blob/main/app.py

@deepankarm : please look into this issue

@osrussell - Do you mean you did this? It doesn't works for me: ``` import tensorflow as tf from tensorflow.keras.regularizers import l1_l2 from tensorflow.keras.regularizers import L1L2 def create_model(conv_filters, lstm_units, dense_units,...