mirror of
https://github.com/hwchase17/langchain
synced 2024-11-11 19:11:02 +00:00
c113682328
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>
70 lines
2.6 KiB
Python
70 lines
2.6 KiB
Python
from typing import Iterator, Literal, Optional
|
|
|
|
from langchain_core.document_loaders import BaseLoader
|
|
from langchain_core.documents import Document
|
|
from langchain_core.utils import get_from_env
|
|
|
|
|
|
class FireCrawlLoader(BaseLoader):
|
|
"""Load web pages as Documents using FireCrawl.
|
|
|
|
Must have Python package `firecrawl` installed and a FireCrawl API key. See
|
|
https://www.firecrawl.dev/ for more.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
url: str,
|
|
*,
|
|
api_key: Optional[str] = None,
|
|
api_url: Optional[str] = None,
|
|
mode: Literal["crawl", "scrape"] = "crawl",
|
|
params: Optional[dict] = None,
|
|
):
|
|
"""Initialize with API key and url.
|
|
|
|
Args:
|
|
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).
|
|
params: The parameters to pass to the Firecrawl API.
|
|
Examples include crawlerOptions.
|
|
For more details, visit: https://github.com/mendableai/firecrawl-py
|
|
"""
|
|
|
|
try:
|
|
from firecrawl import FirecrawlApp
|
|
except ImportError:
|
|
raise ImportError(
|
|
"`firecrawl` package not found, please run `pip install firecrawl-py`"
|
|
)
|
|
if mode not in ("crawl", "scrape"):
|
|
raise ValueError(
|
|
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, api_url=api_url)
|
|
self.url = url
|
|
self.mode = mode
|
|
self.params = params
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
if self.mode == "scrape":
|
|
firecrawl_docs = [self.firecrawl.scrape_url(self.url, params=self.params)]
|
|
elif self.mode == "crawl":
|
|
firecrawl_docs = self.firecrawl.crawl_url(self.url, params=self.params)
|
|
else:
|
|
raise ValueError(
|
|
f"Unrecognized mode '{self.mode}'. Expected one of 'crawl', 'scrape'."
|
|
)
|
|
for doc in firecrawl_docs:
|
|
yield Document(
|
|
page_content=doc.get("markdown", ""),
|
|
metadata=doc.get("metadata", {}),
|
|
)
|