mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 21:12:48 +00:00
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
This commit is contained in:
Bagatur
GitHub
137
libs/community/langchain_community/utilities/google_search.py
Normal file
137
libs/community/langchain_community/utilities/google_search.py
Normal file
@@ -0,0 +1,137 @@
|
||||
"""Util that calls Google Search."""
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
|
||||
from langchain_core.utils import get_from_dict_or_env
|
||||
|
||||
|
||||
class GoogleSearchAPIWrapper(BaseModel):
|
||||
"""Wrapper for Google Search API.
|
||||
|
||||
Adapted from: Instructions adapted from https://stackoverflow.com/questions/
|
||||
37083058/
|
||||
programmatically-searching-google-in-python-using-custom-search
|
||||
|
||||
TODO: DOCS for using it
|
||||
1. Install google-api-python-client
|
||||
- If you don't already have a Google account, sign up.
|
||||
- If you have never created a Google APIs Console project,
|
||||
read the Managing Projects page and create a project in the Google API Console.
|
||||
- Install the library using pip install google-api-python-client
|
||||
|
||||
2. Enable the Custom Search API
|
||||
- Navigate to the APIs & Services→Dashboard panel in Cloud Console.
|
||||
- Click Enable APIs and Services.
|
||||
- Search for Custom Search API and click on it.
|
||||
- Click Enable.
|
||||
URL for it: https://console.cloud.google.com/apis/library/customsearch.googleapis
|
||||
.com
|
||||
|
||||
3. To create an API key:
|
||||
- Navigate to the APIs & Services → Credentials panel in Cloud Console.
|
||||
- Select Create credentials, then select API key from the drop-down menu.
|
||||
- The API key created dialog box displays your newly created key.
|
||||
- You now have an API_KEY
|
||||
|
||||
Alternatively, you can just generate an API key here:
|
||||
https://developers.google.com/custom-search/docs/paid_element#api_key
|
||||
|
||||
4. Setup Custom Search Engine so you can search the entire web
|
||||
- Create a custom search engine here: https://programmablesearchengine.google.com/.
|
||||
- In `What to search` to search, pick the `Search the entire Web` option.
|
||||
After search engine is created, you can click on it and find `Search engine ID`
|
||||
on the Overview page.
|
||||
|
||||
"""
|
||||
|
||||
search_engine: Any #: :meta private:
|
||||
google_api_key: Optional[str] = None
|
||||
google_cse_id: Optional[str] = None
|
||||
k: int = 10
|
||||
siterestrict: bool = False
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
extra = Extra.forbid
|
||||
|
||||
def _google_search_results(self, search_term: str, **kwargs: Any) -> List[dict]:
|
||||
cse = self.search_engine.cse()
|
||||
if self.siterestrict:
|
||||
cse = cse.siterestrict()
|
||||
res = cse.list(q=search_term, cx=self.google_cse_id, **kwargs).execute()
|
||||
return res.get("items", [])
|
||||
|
||||
@root_validator()
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""Validate that api key and python package exists in environment."""
|
||||
google_api_key = get_from_dict_or_env(
|
||||
values, "google_api_key", "GOOGLE_API_KEY"
|
||||
)
|
||||
values["google_api_key"] = google_api_key
|
||||
|
||||
google_cse_id = get_from_dict_or_env(values, "google_cse_id", "GOOGLE_CSE_ID")
|
||||
values["google_cse_id"] = google_cse_id
|
||||
|
||||
try:
|
||||
from googleapiclient.discovery import build
|
||||
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"google-api-python-client is not installed. "
|
||||
"Please install it with `pip install google-api-python-client"
|
||||
">=2.100.0`"
|
||||
)
|
||||
|
||||
service = build("customsearch", "v1", developerKey=google_api_key)
|
||||
values["search_engine"] = service
|
||||
|
||||
return values
|
||||
|
||||
def run(self, query: str) -> str:
|
||||
"""Run query through GoogleSearch and parse result."""
|
||||
snippets = []
|
||||
results = self._google_search_results(query, num=self.k)
|
||||
if len(results) == 0:
|
||||
return "No good Google Search Result was found"
|
||||
for result in results:
|
||||
if "snippet" in result:
|
||||
snippets.append(result["snippet"])
|
||||
|
||||
return " ".join(snippets)
|
||||
|
||||
def results(
|
||||
self,
|
||||
query: str,
|
||||
num_results: int,
|
||||
search_params: Optional[Dict[str, str]] = None,
|
||||
) -> List[Dict]:
|
||||
"""Run query through GoogleSearch and return metadata.
|
||||
|
||||
Args:
|
||||
query: The query to search for.
|
||||
num_results: The number of results to return.
|
||||
search_params: Parameters to be passed on search
|
||||
|
||||
Returns:
|
||||
A list of dictionaries with the following keys:
|
||||
snippet - The description of the result.
|
||||
title - The title of the result.
|
||||
link - The link to the result.
|
||||
"""
|
||||
metadata_results = []
|
||||
results = self._google_search_results(
|
||||
query, num=num_results, **(search_params or {})
|
||||
)
|
||||
if len(results) == 0:
|
||||
return [{"Result": "No good Google Search Result was found"}]
|
||||
for result in results:
|
||||
metadata_result = {
|
||||
"title": result["title"],
|
||||
"link": result["link"],
|
||||
}
|
||||
if "snippet" in result:
|
||||
metadata_result["snippet"] = result["snippet"]
|
||||
metadata_results.append(metadata_result)
|
||||
|
||||
return metadata_results
|
||||
Reference in New Issue
Block a user