search

run-llama / llama_parse

Parse files for optimal RAG
https://www.llamaindex.ai
MIT License
2.74k stars 263 forks source link

Unable to parse any pdf #266

Closed SKashyap1999 closed 2 months ago

SKashyap1999 commented 3 months ago

I am facing issues while using the LlamaParse python library. My usage is as follows:

p=LlamaParse(verbose=True, api_key="xxxxxxxx",parsing_instruction=''' Try your best to parse the table contents carefully and in a proper markdown format, without any formatting errors.''', language='en',gpt4o_mode=True,gpt4o_api_key=os.environ['OPENAI_API_KEY'],skip_diagonal_text=True)

json_objs=p.get_json_result(r"PATH_TO_PDF")

Error: Started parsing the file under job_id xxxxxxxxx Error while parsing the file PATH_TO_PDF: Failed to parse the file: xxxxxxxx, status: ERROR

What is the cause for this error? Is there a way to know what went wrong?

FlorentScarpaSustaain commented 3 months ago

I guess it's linked to how this issue started a couple days ago:

https://github.com/run-llama/llama_parse/issues/261

BinaryBrain commented 2 months ago

This should be fixed since our latest API release. If it happens again, please re-open this issue.