Akash Tyagi

This project uses pre-trained model. How can we tune it or train our own model ?

bug/Very High Memory Utilisation: 7mb Excel sheet taking more than 10gb memory space

4

**Describe the bug** When trying to parse and chunk a 7mb xls file, the Unstructured server takes exponential memory space and crashes for me beyond 10gb. **To Reproduce** Input file...

**Describe the bug** Since the [pdf_infer_table_structure](https://github.com/Unstructured-IO/unstructured/blob/9ece0b5ad2cc2ecbb24e57644c06c0b735719776/unstructured/partition/auto.py#L97C5-L97C30) is deprecated. Using the simple partition strategy should work, but it doesn't. Instead [skip_infer_table_types](https://github.com/Unstructured-IO/unstructured/blob/9ece0b5ad2cc2ecbb24e57644c06c0b735719776/unstructured/partition/auto.py#L87) has pdf mentioned in it, hence it requires to explicitly...