Naresh

Yeah I also faced the same issue. If you are using the data for training in tensorflow, you can use `tf.feature_column` to map column names to specific input nodes. But...

I am not able to locate the file that is generated as well. I think it is in distributed mode. How can I delete files created in distributed mode? I...

I would create a observe on the cells that I expect the change and would create a dataframe from the sheet before and after the change and do a outer...

If someone has not already started to work on this, I can give it a shot this week. Kindly let know

I am also thinking of the same. Flattening the metadata. Add all metadata fields to the index so that it can be filtered. I have a dirty implementation of that...

Sure. Will do it. Its night now. Will do it tonight or early tomorrow.

Created a PR: https://github.com/langchain-ai/langchain/pull/8464 I have done one round of testing. It looked fine.

Also I saw that we are filtering the documents based on `score_threshold` in python. Its possible to do in redis itself. Should we adding the threshold to be part of...

Ill also work on this. Guessing you can comment there as well. Let know otherwise.

I have implemented the changes to accommodate TEXT, TAG and NUMERIC in the above mentioned PR. Let know your suggestions