search

nlmatics / llmsherpa

Developer APIs to Accelerate LLM Projects
https://www.nlmatics.com
MIT License
1.33k stars 130 forks source link

Issue with Example Code #100

Open nickjtay opened 1 month ago

nickjtay commented 1 month ago

The below code in the jupyter notebook produces a persistent timeout error.

from llmsherpa.readers import LayoutPDFReader

llmsherpa_api_url = "https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all"
pdf_url = "https://arxiv.org/pdf/1910.13461.pdf" # also allowed is a file path e.g. /home/downloads/xyz.pdf
pdf_reader = LayoutPDFReader(llmsherpa_api_url)
doc = pdf_reader.read_pdf(pdf_url)
ichbintonywu commented 1 month ago

same problem happened for several days:(

nickjtay commented 1 month ago

Is there any way to bring-your-own llm rather than use the api?

rijulEDA commented 1 month ago

It seems the "https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all" API is down to use llmsherpa API one needs to host the API on their server and then use it. As mentioned (https://github.com/nlmatics/llmsherpa?tab=readme-ov-file#whats-new)