PageIndex

PageIndex copied to clipboard

Issue: Token limit not enforced → `tokens_limit_reached` + unpacking crash

2

**Test setup:** - `PageIndex` CLI (main branch, April 27) - Model: `gpt-4o-mini` (context ~8k tokens) - Python 3.10 on Ubuntu 22.04 - PDF: 22 pages (14k tokens) - Command: ```bash...

Chebil-Ilef

How to get the contents of the nodes

1

Does Pageindex get the contents of the nodes as well or should it be done using some other framework? In the [examples](https://github.com/VectifyAI/PageIndex/blob/main/results/2023-annual-report_structure.json), the node content is not present in the...

sacsac944

If the file name has Spaces, it will simply fail

3

(.venv) skype@192 PageIndex % python3 run_pageindex.py --pdf_path /Users/skype/Documents/GitHub/PageIndex/docs/Websocket vs SSE- OpenAI.pdf usage: run_pageindex.py [-h] [--pdf_path PDF_PATH] [--model MODEL] [--toc-check-pages TOC_CHECK_PAGES] [--max-pages-per-node MAX_PAGES_PER_NODE] [--max-tokens-per-node MAX_TOKENS_PER_NODE] [--if-add-node-id IF_ADD_NODE_ID] [--if-add-node-summary IF_ADD_NODE_SUMMARY] [--if-add-doc-description IF_ADD_DOC_DESCRIPTION]...

sliderss

initial run, key error

7

Hi, I tried downloading the repo and following the usage instructions. I get: File "/home/bsenftner/PageIndex/utils.py", line 498, in convert_physical_index_to_int if isinstance(data[i]['physical_index'], str): KeyError: 'physical_index' after this output: Parsing PDF... start...

bsenftner

Hi, this is interesting. I have a question: is it necessary to have an API key to run everything locally, that is, both converting documents and performing the search? I...

cguilarte

This is an interesting approach. Could you please provide me more information about features in open-source version and Enterprise version. I would like to know what are the differences in...

VimukthiRandika1997

PAGEINDEX_API_KEY

3

Can I use pageindex without PAGEINDEX_API_KEY in my local?

yunusozpolat