run-llama / llama_parse

Parse files for optimal RAG
https://www.llamaindex.ai
MIT License
2.72k stars 263 forks source link

markdown output for table in pdf is incorrect #167

Open blackwhites opened 5 months ago

blackwhites commented 5 months ago

I use the pdf from sample https://policyholder.gov.in/documents/37343/931203/NBHTGBP22011V012223.pdf/c392bcc1-f6a8-cadd-ab84-495b3273d2c3?version=1.0&t=1669350459879&download=true

I use python convert into a markdown format and it is successful,but when I use markdown to check the output I found below output in pdf 51 page

image

You can see the markdown table the order Deductible at the final order which is incorrect,can u fix that issue?

Annexure V – Policy Benefit Table

Sr. No. Benefits Covered Indemnity/Fixed Benefit International Sum Insured SI Options Deductible
1.1 Emergency in-patient Medical Treatment Indemnity USD 25K, 50K, 75K, 100K, 150K, 200K 250K, 3Lac, 5Lac Nil/50/100 Independent SI
1.2 Medical Treatment with OPD Indemnity With sublimit of 25% max up to 10K Nil/50/100 Independent SI
2 Maternity Indemnity USD 2500, 5000, 10000 (Waiting period 10m, 24m) Part of Base Sum Insured
3 New Born Baby Cover Indemnity USD 2500, 5000, 10000 Nil/50/100 Part of Maternity SI
4 Emergency Outpatient Treatment (OPD) Indemnity USD 500, 1K, 2K, 3K, 4K, 5K, 6K, 7K, 8K, 9K, 10K Nil/50/100 Independent SI
5 Road Ambulance Cover Indemnity USD 500, 1K, 2K, 3K, 4K, 5K, 6K, 7K, 8K, 9K, 10K Nil Part of Base Sum Insured
6 Hospital Daily Cash Benefit USD 25, 50, 75, 100, 200, 250 per day Max 5 to 30 days in multiple of 5 days Nil Independent SI
7 Emergency Dental Treatment Indemnity USD 200 to 1000 in multiples of 100 Nil/50/100/200 Part of Base Sum Insured