fix: update parameters in spider components (#3280)

* fix: make spider tool work

* upgrade spider-client

* [autofix.ci] apply automated fixes

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
William Espegren 2024-08-12 21:45:20 +02:00 committed by GitHub
commit e09f157af6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 16 additions and 11 deletions

2
poetry.lock generated
View file

@ -5236,7 +5236,7 @@ python-multipart = "^0.0.7"
rich = "^13.7.0"
sentry-sdk = {version = "^2.5.1", extras = ["fastapi", "loguru"]}
setuptools = ">=70"
spider-client = "^0.0.27"
spider-client = "^0.0.60"
sqlmodel = "^0.0.18"
typer = "^0.12.0"
uncurl = "^0.0.11"

View file

@ -1,4 +1,4 @@
from spider.spider import Spider # type: ignore
from spider.spider import Spider
from langflow.base.langchain_utilities.spider_constants import MODES
from langflow.custom import Component
@ -59,7 +59,7 @@ class SpiderTool(Component):
advanced=True,
),
BoolInput(
name="use_readability",
name="readability",
display_name="Use Readability",
info="Use readability to pre-process the content for reading.",
advanced=True,
@ -89,15 +89,15 @@ class SpiderTool(Component):
def crawl(self) -> list[Data]:
if self.params:
parameters = self.params.data
parameters = self.params["data"]
else:
parameters = {
"limit": self.limit,
"depth": self.depth,
"blacklist": self.blacklist,
"whitelist": self.whitelist,
"use_readability": self.use_readability,
"request_timeout": self.request_timeout,
"limit": self.limit if self.limit else None,
"depth": self.depth if self.depth else None,
"blacklist": self.blacklist if self.blacklist else None,
"whitelist": self.whitelist if self.whitelist else None,
"readability": self.readability,
"request_timeout": self.request_timeout if self.request_timeout else None,
"metadata": self.metadata,
"return_format": "markdown",
}
@ -117,5 +117,10 @@ class SpiderTool(Component):
records = []
for record in result:
records.append(Data(data={"content": record["content"], "url": record["url"]}))
if self.metadata:
records.append(
Data(data={"content": record["content"], "url": record["url"], "metadata": record["metadata"]})
)
else:
records.append(Data(data={"content": record["content"], "url": record["url"]}))
return records