mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
83d10df78d
Change 'FIREWALL' to 'FIRECRAWL' as I believe this may have been in
error. Other docs refer to 'FIRECRAWL_API_KEY'.
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
67 lines
2.4 KiB
Python
67 lines
2.4 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,
|
|
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
|
|
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)
|
|
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", {}),
|
|
)
|