PAIR-code / PAIR-code/lumi

【Error】Raise ValueError(f"Document is too long") ValueError: Document is too long

Open
#130 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
207
Forks
31
Avg merge
3h 33m
Merged PRs (30d)
1

Description

many times error!!

❌ Failed to import 2108.07258v1.
Stdout: 🍭 Running import pipeline locally...

fetch_arxiv_metadata took: 1.15s
Calling Gemini with schema, prompt: 'You are an expert academic assistant tasked with extracting key concepts and terms
from research paper abstracts. For each concept, provide its name and two content items:
1. A general definit...'
Gemini with schema call took: 7.81s
extract_concepts took: 7.88s

Stderr: Traceback (most recent call last):
File "/Users/xxxxx/depoly/lumi/scripts/../functions/script_local_import.py", line 77, in
lumi_doc, _ = import_pipeline.import_arxiv_latex_and_pdf(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/xxxxx/depoly/lumi/functions/import_pipeline/import_pipeline.py", line 106, in import_arxiv_latex_and_pdf
raise ValueError(f"Document is too long")
ValueError: Document is too long


Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with functions/import_pipeline/import_pipeline.py at the ValueError on line 106 and reproduce the failure using arXiv paper 2108.07258v1 through scripts/script_local_import.py. Trace how the document length is determined and establish the intended behavior for oversized documents before defining what a successful import should look like.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.