Skip to content

fix: Handle markdown-wrapped JSON in LLM schema generation (#1663) #1720

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
YuriNachos wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: Handle markdown-wrapped JSON in LLM schema generation (#1663) #1720

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion crawl4ai/extraction_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1380,7 +1380,15 @@ def generate_schema(
)

# Extract and return schema
return json.loads(response.choices[0].message.content)
# Clean markdown code blocks that LLMs sometimes wrap JSON in
content = response.choices[0].message.content
# Remove markdown code block markers if present
if "```json" in content:
content = content.replace("```json\n", "").replace("\n```", "")
elif "```" in content:
content = content.replace("```\n", "").replace("\n```", "")
content = content.strip()
return json.loads(content)

except Exception as e:
raise Exception(f"Failed to generate schema: {str(e)}")
Expand Down