github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-08 12:31:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

community:Add support for specifying document_loaders.firecrawl api url. (#24747)

Browse Source 
community:Add support for specifying document_loaders.firecrawl api url.


Add support for specifying document_loaders.firecrawl api url. 
This is mainly to support the
[self-hosting](https://github.com/mendableai/firecrawl/blob/main/SELF_HOST.md)
option firecrawl provides. Eg. now I can specify localhost:....

The corresponding firecrawl class already provides functionality to pass
the argument. See here:
4c9d62f6d3/apps/python-sdk/firecrawl/firecrawl.py (L29)

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
AmosDinh 2024-07-28 20:30:36 +02:00 committed by GitHub
parent df37c0d086
commit c113682328
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
libs/community/langchain_community/document_loaders/firecrawl.py
View File

@ -17,6 +17,7 @@ class FireCrawlLoader(BaseLoader):
url: str,
*,
api_key: Optional[str] = None,
api_url: Optional[str] = None,
mode: Literal["crawl", "scrape"] = "crawl",
params: Optional[dict] = None,
):
@ -26,6 +27,8 @@ class FireCrawlLoader(BaseLoader):
url: The url to be crawled.
api_key: The Firecrawl API key. If not specified will be read from env var
FIRECRAWL_API_KEY. Get an API key
api_url: The Firecrawl API URL. If not specified will be read from env var
FIRECRAWL_API_URL or defaults to https://api.firecrawl.dev.
mode: The mode to run the loader in. Default is "crawl".
Options include "scrape" (single url) and
"crawl" (all accessible sub pages).
@ -45,7 +48,7 @@ class FireCrawlLoader(BaseLoader):
f"Unrecognized mode '{mode}'. Expected one of 'crawl', 'scrape'."
)
api_key = api_key or get_from_env("api_key", "FIRECRAWL_API_KEY")
self.firecrawl = FirecrawlApp(api_key=api_key)
self.firecrawl = FirecrawlApp(api_key=api_key, api_url=api_url)
self.url = url
self.mode = mode
self.params = params