Gengliang Wang

@FahimMohd This should be fixed in https://github.com/databrickslabs/pyspark-ai/pull/67. Please try upgrade the package and see if it still happens.

@FahimMohd Could you post the whole python code? It didn't looks like you have executed `spark_ai.activate()`

@FahimMohd `df` must be a Spark DataFrame. In your code, it is a pandas DataFrame.

@neox2811 Thanks for the input. Yes, this makes sense. We will support customized temp view names.

@neox2811 this should be fixed in https://github.com/databrickslabs/pyspark-ai/pull/80 I verified with: ``` spark_ai.create_df("https://www.procontra-online.de/sach-privat/artikel/softfair-ermittelt-die-besten-wohngebaeude-tarife") ``` output: ``` CREATE OR REPLACE TEMP VIEW temp_view_8cf30c AS SELECT * FROM VALUES ('Alte Leipziger', 'comfort mit...

@grundprinzip We have thought about this. Using SQL is safer. With proper permission settings, the SDK can only perform `SELECT` for the transform. Running arbitrary python code from LLM may...

I will evaluate and try supporting Python code generation.

As of July 2023, we have found that the GPT-4 works optimally with the English SDK. This superior AI model is readily accessible to all developers through the OpenAI API....

@Sassun Not yet. We are focusing on new APIs and better users experience based on GPT-4.

I am marking this one as resolved. Feel free to reopen this one if you have any more comments.