run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Gemini LVM Bug #501

New Issue
Open
opened 2026-02-16 00:18:03 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:18:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @TLTP1995 on GitHub (Jul 6, 2025).

When running Llamaparse with LVM Gemini-2.0-Flash, the model in many cases (about 1/3) starts filling the parsed output with either long set of blanks or random long sequence of random letters such as:

0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0

This severely prolongs the parsing, increases the output cost and polutes the outcome. Would be nice to have a solution for this, or at least a way to limit it by setting for example the maximum token output per page.

Originally created by @TLTP1995 on GitHub (Jul 6, 2025). When running Llamaparse with LVM Gemini-2.0-Flash, the model in many cases (about 1/3) starts filling the parsed output with either long set of blanks or random long sequence of random letters such as: 0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0gQJ0gQ0gQJ0gQJ0 This severely prolongs the parsing, increases the output cost and polutes the outcome. Would be nice to have a solution for this, or at least a way to limit it by setting for example the maximum token output per page.
yindo added the bug label 2026-02-16 00:18:03 -05:00
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#501
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?