Skip to content
This repository was archived by the owner on Jul 22, 2025. It is now read-only.

Commit 8393dd7

Browse files
committed
PR comments
1 parent bcb7cdf commit 8393dd7

File tree

3 files changed

+2
-4
lines changed

3 files changed

+2
-4
lines changed

evals/lib/llm.rb

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -106,6 +106,4 @@ def name
106106
def vision?
107107
@llm_model.vision_enabled
108108
end
109-
110-
private
111109
end

lib/utils/image_to_text.rb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -91,7 +91,7 @@ def extract_text(retries: 3)
9191
def system_message
9292
<<~MSG
9393
OCR the following page into Markdown. Tables should be formatted as Github flavored markdown.
94-
Do not sorround your output with triple backticks.
94+
Do not surround your output with triple backticks.
9595
9696
Chunk the document into sections of roughly 250 - 1000 words. Our goal is to identify parts of the page with same semantic theme. These chunks will be embedded and used in a RAG pipeline.
9797

lib/utils/pdf_to_images.rb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,7 @@ def extract_pages
7575

7676
@uploaded_pages = uploads
7777
ensure
78-
FileUtils.rm_rf(temp_dir) if Dir.exist?(temp_dir)
78+
FileUtils.rm_rf(temp_dir)
7979
end
8080
end
8181
end

0 commit comments

Comments
 (0)