Doc().query method returns relevant answer from relevant papers but returns unrelevant pages

[Snikch63200]

Hi,

Whan i use Doc().query method on a doc collection, answer returns relevant answer from relevant papers but citation pages seems random.

The answer seems refers to different pages from documents. Maybe it is related to PDF parsing...

Any solution for this ?

Best regards.

@dosu.

[dosubot]

The issue you're experiencing with the Doc().query method returning seemingly random citation pages might be related to the PDF parsing approach or the logic used to associate answers with specific pages. Unfortunately, the specific logic or algorithm used by the Doc().query method to select citation pages is not detailed in the available information. However, there are known limitations with the PDF parsing approach that could potentially affect the results:

1. Corrupt PDF Files: If a PDF file is corrupt, it might not be parsed correctly, leading to incorrect page references ^[1].

2. Page Size Limit Exceeded: If the text on a page exceeds a certain limit, it might not be processed correctly, which could also affect page references ^[1].

To address this, you might want to check the integrity of your PDF files and ensure they are not exceeding any size limits during parsing. Additionally, reviewing the parsing logic in the parse_pdf_to_pages function might provide further insights into potential issues.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}