Skip to content

fix: strip markdown code fences from LLM JSON responses #1787

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
Br1an67 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: strip markdown code fences from LLM JSON responses #1787

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
18 changes: 14 additions & 4 deletions crawl4ai/extraction_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,16 @@
from bs4 import BeautifulSoup
from lxml import html, etree

_MARKDOWN_JSON_FENCE_RE = re.compile(
r"^\s*```(?:json)?\s*\n(.*?)\n\s*```\s*$", re.DOTALL
)


def _strip_markdown_json(text: str) -> str:
"""Strip markdown code fences from LLM JSON responses."""
m = _MARKDOWN_JSON_FENCE_RE.match(text.strip())
return m.group(1) if m else text


class ExtractionStrategy(ABC):
"""
Expand Down Expand Up @@ -677,7 +687,7 @@ def extract(self, url: str, ix: int, html: str) -> List[Dict[str, Any]]:
blocks = None

if self.force_json_response:
blocks = json.loads(content)
blocks = json.loads(_strip_markdown_json(content))
if isinstance(blocks, dict):
# If it has only one key which calue is list then assign that to blocks, exampled: {"news": [..]}
if len(blocks) == 1 and isinstance(list(blocks.values())[0], list):
Expand Down Expand Up @@ -877,7 +887,7 @@ async def aextract(self, url: str, ix: int, html: str) -> List[Dict[str, Any]]:
blocks = None

if self.force_json_response:
blocks = json.loads(content)
blocks = json.loads(_strip_markdown_json(content))
if isinstance(blocks, dict):
if len(blocks) == 1 and isinstance(list(blocks.values())[0], list):
blocks = list(blocks.values())[0]
Expand Down Expand Up @@ -1382,7 +1392,7 @@ def generate_schema(
base_url=llm_config.base_url,
extra_args=kwargs
)
return json.loads(response.choices[0].message.content)
return json.loads(_strip_markdown_json(response.choices[0].message.content))
except Exception as e:
raise Exception(f"Failed to generate schema: {str(e)}")

Expand Down Expand Up @@ -1429,7 +1439,7 @@ async def agenerate_schema(
base_url=llm_config.base_url,
extra_args=kwargs
)
return json.loads(response.choices[0].message.content)
return json.loads(_strip_markdown_json(response.choices[0].message.content))
except Exception as e:
raise Exception(f"Failed to generate schema: {str(e)}")

Expand Down