feat: add WikiData Component and depeciates the WikiData API tool component (#5872)
* update * [autofix.ci] apply automated fixes * Update test_wikidata_api.py * [autofix.ci] apply automated fixes * Update wikidata.py --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Edwin Jose
GitHub
parent
dcd68c5f4e
commit
229ba19a66
4 changed files with 252 additions and 136 deletions
|
|
@ -24,6 +24,7 @@ from .serp import SerpComponent
|
|||
from .serp_api import SerpAPIComponent
|
||||
from .tavily import TavilySearchComponent
|
||||
from .tavily_search import TavilySearchToolComponent
|
||||
from .wikidata import WikidataComponent
|
||||
from .wikidata_api import WikidataAPIComponent
|
||||
from .wikipedia import WikipediaComponent
|
||||
from .wikipedia_api import WikipediaAPIComponent
|
||||
|
|
@ -62,6 +63,7 @@ __all__ = [
|
|||
"TavilySearchComponent",
|
||||
"TavilySearchToolComponent",
|
||||
"WikidataAPIComponent",
|
||||
"WikidataComponent",
|
||||
"WikipediaAPIComponent",
|
||||
"WikipediaComponent",
|
||||
"WolframAlphaAPIComponent",
|
||||
|
|
|
|||
86
src/backend/base/langflow/components/tools/wikidata.py
Normal file
86
src/backend/base/langflow/components/tools/wikidata.py
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
import httpx
|
||||
from httpx import HTTPError
|
||||
from langchain_core.tools import ToolException
|
||||
|
||||
from langflow.custom import Component
|
||||
from langflow.helpers.data import data_to_text
|
||||
from langflow.io import MultilineInput, Output
|
||||
from langflow.schema import Data
|
||||
from langflow.schema.message import Message
|
||||
|
||||
|
||||
class WikidataComponent(Component):
|
||||
display_name = "Wikidata"
|
||||
description = "Performs a search using the Wikidata API."
|
||||
icon = "Wikipedia"
|
||||
|
||||
inputs = [
|
||||
MultilineInput(
|
||||
name="query",
|
||||
display_name="Query",
|
||||
info="The text query for similarity search on Wikidata.",
|
||||
required=True,
|
||||
tool_mode=True,
|
||||
),
|
||||
]
|
||||
|
||||
outputs = [
|
||||
Output(display_name="Data", name="data", method="fetch_content"),
|
||||
Output(display_name="Message", name="text", method="fetch_content_text"),
|
||||
]
|
||||
|
||||
def fetch_content(self) -> list[Data]:
|
||||
try:
|
||||
# Define request parameters for Wikidata API
|
||||
params = {
|
||||
"action": "wbsearchentities",
|
||||
"format": "json",
|
||||
"search": self.query,
|
||||
"language": "en",
|
||||
}
|
||||
|
||||
# Send request to Wikidata API
|
||||
wikidata_api_url = "https://www.wikidata.org/w/api.php"
|
||||
response = httpx.get(wikidata_api_url, params=params)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Extract search results
|
||||
results = response_json.get("search", [])
|
||||
|
||||
if not results:
|
||||
return [Data(data={"error": "No search results found for the given query."})]
|
||||
|
||||
# Transform the API response into Data objects
|
||||
data = [
|
||||
Data(
|
||||
text=f"{result['label']}: {result.get('description', '')}",
|
||||
data={
|
||||
"label": result["label"],
|
||||
"id": result.get("id"),
|
||||
"url": result.get("url"),
|
||||
"description": result.get("description", ""),
|
||||
"concepturi": result.get("concepturi"),
|
||||
},
|
||||
)
|
||||
for result in results
|
||||
]
|
||||
|
||||
self.status = data
|
||||
except HTTPError as e:
|
||||
error_message = f"HTTP Error in Wikidata Search API: {e!s}"
|
||||
raise ToolException(error_message) from None
|
||||
except KeyError as e:
|
||||
error_message = f"Data parsing error in Wikidata API response: {e!s}"
|
||||
raise ToolException(error_message) from None
|
||||
except ValueError as e:
|
||||
error_message = f"Value error in Wikidata API: {e!s}"
|
||||
raise ToolException(error_message) from None
|
||||
else:
|
||||
return data
|
||||
|
||||
def fetch_content_text(self) -> Message:
|
||||
data = self.fetch_content()
|
||||
result_string = data_to_text("{text}", data)
|
||||
self.status = result_string
|
||||
return Message(text=result_string)
|
||||
|
|
@ -1,19 +1,63 @@
|
|||
from typing import Any
|
||||
|
||||
import httpx
|
||||
from httpx import HTTPError
|
||||
from langchain_core.tools import ToolException
|
||||
from langchain_core.tools import StructuredTool, ToolException
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from langflow.custom import Component
|
||||
from langflow.helpers.data import data_to_text
|
||||
from langflow.io import MultilineInput, Output
|
||||
from langflow.base.langchain_utilities.model import LCToolComponent
|
||||
from langflow.field_typing import Tool
|
||||
from langflow.inputs import MultilineInput
|
||||
from langflow.schema import Data
|
||||
from langflow.schema.message import Message
|
||||
|
||||
|
||||
class WikidataAPIComponent(Component):
|
||||
display_name = "Wikidata API"
|
||||
class WikidataSearchSchema(BaseModel):
|
||||
query: str = Field(..., description="The search query for Wikidata")
|
||||
|
||||
|
||||
class WikidataAPIWrapper(BaseModel):
|
||||
"""Wrapper around Wikidata API."""
|
||||
|
||||
wikidata_api_url: str = "https://www.wikidata.org/w/api.php"
|
||||
|
||||
def results(self, query: str) -> list[dict[str, Any]]:
|
||||
# Define request parameters for Wikidata API
|
||||
params = {
|
||||
"action": "wbsearchentities",
|
||||
"format": "json",
|
||||
"search": query,
|
||||
"language": "en",
|
||||
}
|
||||
|
||||
# Send request to Wikidata API
|
||||
response = httpx.get(self.wikidata_api_url, params=params)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Extract and return search results
|
||||
return response_json.get("search", [])
|
||||
|
||||
def run(self, query: str) -> list[dict[str, Any]]:
|
||||
try:
|
||||
results = self.results(query)
|
||||
if results:
|
||||
return results
|
||||
|
||||
error_message = "No search results found for the given query."
|
||||
|
||||
raise ToolException(error_message)
|
||||
|
||||
except Exception as e:
|
||||
error_message = f"Error in Wikidata Search API: {e!s}"
|
||||
|
||||
raise ToolException(error_message) from e
|
||||
|
||||
|
||||
class WikidataAPIComponent(LCToolComponent):
|
||||
display_name = "Wikidata API [Deprecated]"
|
||||
description = "Performs a search using the Wikidata API."
|
||||
name = "WikidataAPI"
|
||||
icon = "Wikipedia"
|
||||
legacy = True
|
||||
|
||||
inputs = [
|
||||
MultilineInput(
|
||||
|
|
@ -21,67 +65,38 @@ class WikidataAPIComponent(Component):
|
|||
display_name="Query",
|
||||
info="The text query for similarity search on Wikidata.",
|
||||
required=True,
|
||||
tool_mode=True,
|
||||
),
|
||||
]
|
||||
|
||||
outputs = [
|
||||
Output(display_name="Data", name="data", method="fetch_content"),
|
||||
Output(display_name="Message", name="text", method="fetch_content_text"),
|
||||
]
|
||||
def build_tool(self) -> Tool:
|
||||
wrapper = WikidataAPIWrapper()
|
||||
|
||||
def fetch_content(self) -> list[Data]:
|
||||
try:
|
||||
# Define request parameters for Wikidata API
|
||||
params = {
|
||||
"action": "wbsearchentities",
|
||||
"format": "json",
|
||||
"search": self.query,
|
||||
"language": "en",
|
||||
}
|
||||
# Define the tool using StructuredTool and wrapper's run method
|
||||
tool = StructuredTool.from_function(
|
||||
name="wikidata_search_api",
|
||||
description="Perform similarity search on Wikidata API",
|
||||
func=wrapper.run,
|
||||
args_schema=WikidataSearchSchema,
|
||||
)
|
||||
|
||||
# Send request to Wikidata API
|
||||
wikidata_api_url = "https://www.wikidata.org/w/api.php"
|
||||
response = httpx.get(wikidata_api_url, params=params)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
self.status = "Wikidata Search API Tool for Langchain"
|
||||
|
||||
# Extract search results
|
||||
results = response_json.get("search", [])
|
||||
return tool
|
||||
|
||||
if not results:
|
||||
return [Data(data={"error": "No search results found for the given query."})]
|
||||
def run_model(self) -> list[Data]:
|
||||
tool = self.build_tool()
|
||||
|
||||
# Transform the API response into Data objects
|
||||
data = [
|
||||
Data(
|
||||
text=f"{result['label']}: {result.get('description', '')}",
|
||||
data={
|
||||
"label": result["label"],
|
||||
"id": result.get("id"),
|
||||
"url": result.get("url"),
|
||||
"description": result.get("description", ""),
|
||||
"concepturi": result.get("concepturi"),
|
||||
},
|
||||
)
|
||||
for result in results
|
||||
]
|
||||
results = tool.run({"query": self.query})
|
||||
|
||||
self.status = data
|
||||
except HTTPError as e:
|
||||
error_message = f"HTTP Error in Wikidata Search API: {e!s}"
|
||||
raise ToolException(error_message) from None
|
||||
except KeyError as e:
|
||||
error_message = f"Data parsing error in Wikidata API response: {e!s}"
|
||||
raise ToolException(error_message) from None
|
||||
except ValueError as e:
|
||||
error_message = f"Value error in Wikidata API: {e!s}"
|
||||
raise ToolException(error_message) from None
|
||||
else:
|
||||
return data
|
||||
# Transform the API response into Data objects
|
||||
data = [
|
||||
Data(
|
||||
text=result["label"],
|
||||
metadata=result,
|
||||
)
|
||||
for result in results
|
||||
]
|
||||
|
||||
def fetch_content_text(self) -> Message:
|
||||
data = self.fetch_content()
|
||||
result_string = data_to_text("{text}", data)
|
||||
self.status = result_string
|
||||
return Message(text=result_string)
|
||||
self.status = data # type: ignore[assignment]
|
||||
|
||||
return data
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue