run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

parsemode with lvm results in parsemode with llm #451

New Issue
Closed
opened 2026-02-16 00:17:53 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 00:17:53 -05:00
Owner
Copy Link
Copy Source

Originally created by @Constipn on GitHub (Mar 20, 2025).

Originally assigned to: @BinaryBrain on GitHub.

When I call parsemode = "parse_page_with_lvm", llama parse uses "parse_page_with_llm" instead (to be seen in the UI under parameters). However, I explicitly set parsemode to lvm. Only using the UI with parsemode = "parse_page_with_lvm", everything works fine.

Job ID
0bf15760-6d72-4f9d-9901-e524ee3fb1f0

Client:
Please remove untested options:

  • calling the API via Python
Originally created by @Constipn on GitHub (Mar 20, 2025). Originally assigned to: @BinaryBrain on GitHub. When I call parsemode = "parse_page_with_lvm", llama parse uses "parse_page_with_llm" instead (to be seen in the UI under parameters). However, I explicitly set parsemode to lvm. Only using the UI with parsemode = "parse_page_with_lvm", everything works fine. **Job ID** 0bf15760-6d72-4f9d-9901-e524ee3fb1f0 **Client:** Please remove untested options: - calling the API via Python
yindo added the bug label 2026-02-16 00:17:53 -05:00
yindo closed this issue 2026-02-16 00:17:53 -05:00
yindo commented 2026-02-16 00:17:53 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Mar 20, 2025):

I see you also have auto_mode=True. You cannot use both at the same time, so your job was parsed using Auto Mode.

@BinaryBrain commented on GitHub (Mar 20, 2025): I see you also have `auto_mode=True`. You cannot use both at the same time, so your job was parsed using Auto Mode.
yindo commented 2026-02-16 00:17:53 -05:00
Author
Owner
Copy Link
Copy Source

@Constipn commented on GitHub (Mar 20, 2025):

please check 93faa876-e686-47cf-b25f-33e7d3b61898. same error without automode

@Constipn commented on GitHub (Mar 20, 2025): please check 93faa876-e686-47cf-b25f-33e7d3b61898. same error without automode
yindo commented 2026-02-16 00:17:53 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Mar 20, 2025):

Can you share you code where you're calling our API?

@BinaryBrain commented on GitHub (Mar 20, 2025): Can you share you code where you're calling our API?
yindo commented 2026-02-16 00:17:54 -05:00
Author
Owner
Copy Link
Copy Source

@Constipn commented on GitHub (Mar 20, 2025):

from llama_cloud_services import LlamaParse
import nest_asyncio
llamaparse_key = key
nest_asyncio.apply()

parser = LlamaParse(
api_key = llamaparse_key,
parse_mode = "parse_page_with_lvm",
vendor_multimodal_model_name = "gemini-2.0-flash-001",
invalidate_cache = True)

result = parser.get_json_result(r"xxxx.pdf")

@Constipn commented on GitHub (Mar 20, 2025): from llama_cloud_services import LlamaParse import nest_asyncio llamaparse_key = key nest_asyncio.apply() parser = LlamaParse( api_key = llamaparse_key, parse_mode = "parse_page_with_lvm", vendor_multimodal_model_name = "gemini-2.0-flash-001", invalidate_cache = True) result = parser.get_json_result(r"xxxx.pdf")
yindo commented 2026-02-16 00:17:54 -05:00
Author
Owner
Copy Link
Copy Source

@Constipn commented on GitHub (Mar 22, 2025):

@BinaryBrain any updates? the error persists which is weird

@Constipn commented on GitHub (Mar 22, 2025): @BinaryBrain any updates? the error persists which is weird
yindo commented 2026-02-16 00:17:54 -05:00
Author
Owner
Copy Link
Copy Source

@Constipn commented on GitHub (Mar 25, 2025):

@BinaryBrain ? Unfortunately, the error persists which makes it impossible to use parse with lvm for me

@Constipn commented on GitHub (Mar 25, 2025): @BinaryBrain ? Unfortunately, the error persists which makes it impossible to use parse with lvm for me
yindo commented 2026-02-16 00:17:54 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Mar 25, 2025):

Hey @Constipn, we just fixed the bug. Please upgrade llama-cloud-services 0.6.8

@BinaryBrain commented on GitHub (Mar 25, 2025): Hey @Constipn, we just fixed the bug. Please upgrade [llama-cloud-services](https://pypi.org/project/llama-cloud-services/) 0.6.8
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#451
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?