How to send a llama_parse job in python async?

[AyushParikh]

hi, I want to start a job in python but not wait for the response. How can I achieve this?

    parser = LlamaParse(
        webhook_url=webhook_url
    ).load_data(file_path=path)

[logan-markewich]

await parser.aload_data(...)

[AyushParikh]

await parser.aload_data(...)

When I do this, i get

'await parser.aload_data(...)' was never awaited

[AyushParikh]

i also tried:

async def start_parser(parser, local_file_path: str):
    await parser.aload_data(file_path=local_file_path)
    
start_parser(parser=parser, local_file_path=local_file_path)

[AyushParikh]

@logan-markewich

[AyushParikh]

ok so this work, but issue is that my lambda endpoint returns right away before the job even starts. any suggestions?

[logan-markewich]

Sorry, I misunderstood your question. Async is probably not what you want.

You'll probably want to use the raw api. Create a job, return the job ID, use the job ID to check if the status is done and retrieve the result
https://docs.cloud.llamaindex.ai/category/API/parsing

[logan-markewich]

https://docs.cloud.llamaindex.ai/llamaparse/getting_started/api

[AyushParikh]

@logan-markewich i see but in the docs i don't see how i can provide webhook url in the API call?

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/parsing/upload'  \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -F 'file=@/path/to/your/file.pdf;type=application/pdf'

[AyushParikh]

https://docs.cloud.llamaindex.ai/llamaparse/features/webhook @logan-markewich this is webhook docs for llama cloud. the API example doesnt show how to pass webhook url @logan-markewich

[AyushParikh]

ok it works. you have to pass in

        data = {
            'webhook_url': webhook_url
        }

in the payload. maybe docs should be updated