jyapayne/dify
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

refactor: Update Firecrawl API parameters and default settings (#13082)

Browse source
This commit is contained in:
Ademílson Tonato 2025-01-29 03:21:05 +00:00 • committed by GitHub
commit d0a21086bd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 10 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

3
api/core/rag/extractor/firecrawl/firecrawl_web_extractor.py
View file

@ -13,9 +13,10 @@ class FirecrawlWebExtractor(BaseExtractor):
api_key: The API key for Firecrawl.
base_url: The base URL for the Firecrawl API. Defaults to 'https://api.firecrawl.dev'.
mode: The mode of operation. Defaults to 'scrape'. Options are 'crawl', 'scrape' and 'crawl_return_urls'.
only_main_content: Only return the main content of the page excluding headers, navs, footers, etc.
"""
def __init__(self, url: str, job_id: str, tenant_id: str, mode: str = "crawl", only_main_content: bool = False):
def __init__(self, url: str, job_id: str, tenant_id: str, mode: str = "crawl", only_main_content: bool = True):
"""Initialize with url, api_key, base_url and mode."""
self._url = url
self.job_id = job_id