MegaParse icon indicating copy to clipboard operation
MegaParse copied to clipboard

File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

Results 26 MegaParse issues
Sort by recently updated
recently updated
newest added

When I used this model after your commit, it reminds me of this information,how can i solve it?

When running 'sudo make dev', i get the below error: ``` => => exporting layers 0.0s => => writing image sha256:70203052eb52378760709c628b60f98870d3e701267cf2f010aeb943ea9766c2 0.0s => => naming to docker.io/library/megaparse:latest 0.0s => [megaparse]...

I found this error when executing the example from the readme: **ModuleNotFoundError: No module named 'megaparse.parser'**

After `pip install megaparse` in a clean environment, I've tried the README example on a couple of .pdf files and a .xlsx, .doc file. Although I guess the `unstructured_parser` is...

Impossible to install on a Windows computer. From what I understand, there is a "winloop" version of "uvloop" and some sources seem to indicate that it should be possible to...

![image](https://github.com/user-attachments/assets/4e2beedc-7fe4-4b86-a83b-c3406f8328a5) Both code snippets Copied from README.md ```python from megaparse import MegaParse from langchain_openai import ChatOpenAI from megaparse.parser.unstructured_parser import UnstructuredParser parser = UnstructuredParser() megaparse = MegaParse(parser) response = megaparse.load("./test.pdf") print(response)...

This would allow users/developers to consume it while using Amazon Bedrock calls.

- Add a custom auto logic that is based on the proportion of images