Google Scholar Search Tool using serpapi (#11513)

- **Description:** Implementing the Google Scholar Tool as requested in
PR #11505. The tool will be using the [serpapi python
package](https://serpapi.com/integrations/python#search-google-scholar).
The main idea of the tool will be to return the results from a Google
Scholar search given a query as an input to the tool.

- **Tag maintainer:** @baskaryan, @eyurtsev, @hwchase17
This commit is contained in:
Mohammad Mohtashim
2023-10-21 02:35:55 +05:00
committed by GitHub
parent e542bf1b6b
commit d5400f6502
6 changed files with 283 additions and 0 deletions

View File

@@ -34,6 +34,7 @@ from langchain.tools.base import BaseTool
from langchain.tools.bing_search.tool import BingSearchRun
from langchain.tools.ddg_search.tool import DuckDuckGoSearchRun
from langchain.tools.google_search.tool import GoogleSearchResults, GoogleSearchRun
from langchain.tools.google_scholar.tool import GoogleScholarQueryRun
from langchain.tools.metaphor_search.tool import MetaphorSearchResults
from langchain.tools.google_serper.tool import GoogleSerperResults, GoogleSerperRun
from langchain.tools.searchapi.tool import SearchAPIResults, SearchAPIRun
@@ -64,6 +65,7 @@ from langchain.utilities.bing_search import BingSearchAPIWrapper
from langchain.utilities.duckduckgo_search import DuckDuckGoSearchAPIWrapper
from langchain.utilities.google_search import GoogleSearchAPIWrapper
from langchain.utilities.google_serper import GoogleSerperAPIWrapper
from langchain.utilities.google_scholar import GoogleScholarAPIWrapper
from langchain.utilities.metaphor_search import MetaphorSearchAPIWrapper
from langchain.utilities.awslambda import LambdaWrapper
from langchain.utilities.graphql import GraphQLAPIWrapper
@@ -222,6 +224,10 @@ def _get_google_serper(**kwargs: Any) -> BaseTool:
return GoogleSerperRun(api_wrapper=GoogleSerperAPIWrapper(**kwargs))
def _get_google_scholar(**kwargs: Any) -> BaseTool:
return GoogleScholarQueryRun(api_wrapper=GoogleScholarAPIWrapper(**kwargs))
def _get_google_serper_results_json(**kwargs: Any) -> BaseTool:
return GoogleSerperResults(api_wrapper=GoogleSerperAPIWrapper(**kwargs))
@@ -337,6 +343,10 @@ _EXTRA_OPTIONAL_TOOLS: Dict[str, Tuple[Callable[[KwArg(Any)], BaseTool], List[st
"metaphor-search": (_get_metaphor_search, ["metaphor_api_key"]),
"ddg-search": (_get_ddg_search, []),
"google-serper": (_get_google_serper, ["serper_api_key", "aiosession"]),
"google-scholar": (
_get_google_scholar,
["top_k_results", "hl", "lr", "serp_api_key"],
),
"google-serper-results-json": (
_get_google_serper_results_json,
["serper_api_key", "aiosession"],

View File

@@ -0,0 +1,5 @@
"""Google Scholar API Toolkit."""
from langchain.tools.google_scholar.tool import GoogleScholarQueryRun
__all__ = ["GoogleScholarQueryRun"]

View File

@@ -0,0 +1,28 @@
"""Tool for the Google Scholar"""
from typing import Optional
from langchain.callbacks.manager import CallbackManagerForToolRun
from langchain.tools.base import BaseTool
from langchain.utilities.google_scholar import GoogleScholarAPIWrapper
class GoogleScholarQueryRun(BaseTool):
"""Tool that queries the Google search API."""
name: str = "google_scholar"
description: str = (
"A wrapper around Google Scholar Search. "
"Useful for when you need to get information about"
"research papers from Google Scholar"
"Input should be a search query."
)
api_wrapper: GoogleScholarAPIWrapper
def _run(
self,
query: str,
run_manager: Optional[CallbackManagerForToolRun] = None,
) -> str:
"""Use the tool."""
return self.api_wrapper.run(query)

View File

@@ -74,6 +74,12 @@ def _import_google_places_api() -> Any:
return GooglePlacesAPIWrapper
def _import_google_scholar() -> Any:
from langchain.utilities.google_scholar import GoogleScholarAPIWrapper
return GoogleScholarAPIWrapper
def _import_google_search() -> Any:
from langchain.utilities.google_search import GoogleSearchAPIWrapper
@@ -225,6 +231,8 @@ def __getattr__(name: str) -> Any:
return _import_duckduckgo_search()
elif name == "GoldenQueryAPIWrapper":
return _import_golden_query()
elif name == "GoogleScholarAPIWrapper":
return _import_google_scholar()
elif name == "GooglePlacesAPIWrapper":
return _import_google_places_api()
elif name == "GoogleSearchAPIWrapper":
@@ -286,6 +294,7 @@ __all__ = [
"DuckDuckGoSearchAPIWrapper",
"GoldenQueryAPIWrapper",
"GooglePlacesAPIWrapper",
"GoogleScholarAPIWrapper",
"GoogleSearchAPIWrapper",
"GoogleSerperAPIWrapper",
"GraphQLAPIWrapper",

View File

@@ -0,0 +1,129 @@
"""Util that calls Google Scholar Search."""
from typing import Dict, Optional
from langchain.pydantic_v1 import BaseModel, Extra, root_validator
from langchain.utils import get_from_dict_or_env
class GoogleScholarAPIWrapper(BaseModel):
"""Wrapper for Google Scholar API
You can create serpapi key by signing up at: https://serpapi.com/users/sign_up.
The wrapper uses the serpapi python package:
https://serpapi.com/integrations/python#search-google-scholar
To use, you should have the environment variable ``SERP_API_KEY``
set with your API key, or pass `serp_api_key` as a named parameter
to the constructor.
Attributes:
top_k_results: number of results to return from google-scholar query search.
By default it returns top 10 results.
hl: attribute defines the language to use for the Google Scholar search.
It's a two-letter language code.
(e.g., en for English, es for Spanish, or fr for French). Head to the
Google languages page for a full list of supported Google languages:
https://serpapi.com/google-languages
lr: attribute defines one or multiple languages to limit the search to.
It uses lang_{two-letter language code} to specify languages
and | as a delimiter. (e.g., lang_fr|lang_de will only search French
and German pages). Head to the Google lr languages for a full
list of supported languages: https://serpapi.com/google-lr-languages
Example:
.. code-block:: python
from langchain.utilities import GoogleScholarAPIWrapper
google_scholar = GoogleScholarAPIWrapper()
google_scholar.run('langchain')
"""
top_k_results: int = 10
hl: str = "en"
lr: str = "lang_en"
serp_api_key: Optional[str] = None
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that api key and python package exists in environment."""
serp_api_key = get_from_dict_or_env(values, "serp_api_key", "SERP_API_KEY")
values["SERP_API_KEY"] = serp_api_key
try:
from serpapi import GoogleScholarSearch
except ImportError:
raise ImportError(
"google-search-results is not installed. "
"Please install it with `pip install google-search-results"
">=2.4.2`"
)
GoogleScholarSearch.SERP_API_KEY = serp_api_key
values["google_scholar_engine"] = GoogleScholarSearch
return values
def run(self, query: str) -> str:
"""Run query through GoogleSearchScholar and parse result"""
total_results = []
page = 0
while page < max((self.top_k_results - 20), 1):
# We are getting 20 results from every page
# which is the max in order to reduce the number of API CALLS.
# 0 is the first page of results, 20 is the 2nd page of results,
# 40 is the 3rd page of results, etc.
results = (
self.google_scholar_engine( # type: ignore
{
"q": query,
"start": page,
"hl": self.hl,
"num": min(
self.top_k_results, 20
), # if top_k_result is less than 20.
"lr": self.lr,
}
)
.get_dict()
.get("organic_results", [])
)
total_results.extend(results)
if not results: # No need to search for more pages if current page
# has returned no results
break
page += 20
if (
self.top_k_results % 20 != 0 and page > 20 and total_results
): # From the last page we would only need top_k_results%20 results
# if k is not divisible by 20.
results = (
self.google_scholar_engine( # type: ignore
{
"q": query,
"start": page,
"num": self.top_k_results % 20,
"hl": self.hl,
"lr": self.lr,
}
)
.get_dict()
.get("organic_results", [])
)
total_results.extend(results)
if not total_results:
return "No good Google Scholar Result was found"
docs = [
f"Title: {result.get('title','')}\n"
f"Authors: {','.join([author.get('name') for author in result.get('publication_info',{}).get('authors',[])])}\n" # noqa: E501
f"Summary: {result.get('publication_info',{}).get('summary','')}\n"
f"Total-Citations: {result.get('inline_links',{}).get('cited_by',{}).get('total','')}" # noqa: E501
for result in total_results
]
return "\n\n".join(docs)