Images from PDF do not download properly. #95

Closed
opened 2026-02-16 00:16:51 -05:00 by yindo · 0 comments
Owner

Originally created by @ikostis-ucl on GitHub (Apr 24, 2024).

Hello, everyone!

I want to use LLamaParse in JSON mode to perform multimodal RAG. I provide as input a .pdf file:

doc_parser = LlamaParse(api_key="llx-myLLamaParseKey", verbose=False, language='en')
json_objects = doc_parser.get_json_result(file_path='./path/to/my/example.pdf')
image_dicts = doc_parser.get_images(json_objects, download_path="./path/to/image/directory")

The result of this procedure is one file per image, titled (abstractly):
llama-parse-api-proc-id-img_pX_imgNo
with no extension, containing the a Python dictionary:
{"detail":"Result not found. Check job status to see if it has completed."}

Job seems to be finishing properly, judging by the text nodes results received.
Any apparent issues that I overlooked? Thank you in advance!

Originally created by @ikostis-ucl on GitHub (Apr 24, 2024). Hello, everyone! I want to use LLamaParse in JSON mode to perform multimodal RAG. I provide as input a .pdf file: ``` doc_parser = LlamaParse(api_key="llx-myLLamaParseKey", verbose=False, language='en') json_objects = doc_parser.get_json_result(file_path='./path/to/my/example.pdf') image_dicts = doc_parser.get_images(json_objects, download_path="./path/to/image/directory") ``` The result of this procedure is one file per image, titled (abstractly): `llama-parse-api-proc-id-img_pX_imgNo` with no extension, containing the a Python dictionary: `{"detail":"Result not found. Check job status to see if it has completed."}` Job seems to be finishing properly, judging by the text nodes results received. Any apparent issues that I overlooked? Thank you in advance!
yindo closed this issue 2026-02-16 00:16:51 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#95