search

run-llama / llama_parse

Parse files for optimal RAG
https://www.llamaindex.ai
MIT License
1.87k stars 168 forks source link

Parsing 2 page PDF file taking a long time. #103

Open poornimapk opened 3 months ago

poornimapk commented 3 months ago

I am new to LlamaIndex and LlamaParse I am using below code to parse PDF file: def main(): load_dotenv() nest_asyncio.apply() LLAMA_CLOUD_API_KEY = os.getenv("LLAMA_CLOUD_API_KEY")

#setup parser
parser = LlamaParse(
    api_key=LLAMA_CLOUD_API_KEY,
    result_type="markdown",
    verbose=True,
)

documents = parser.load_data("./data/Oracle-SEC-Filing.pdf")
print(documents)

It takes more than 15 minutes and still has not finished parsing. What am I doing wrong? The pdf is a 2 page PDF attached here. Oracle-SEC-Filing.pdf

poornimapk commented 3 months ago

83 seems to be the same issue