RAGchain.utils.websearch package

Submodules

RAGchain.utils.websearch.base module

class RAGchain.utils.websearch.base.BaseWebSearch

Bases: Runnable[str, RetrievalResult], ABC

Abstract class for using a web search engine for passage contents.

property InputType: Type[Input]

The type of input this runnable accepts specified as a type annotation.

property OutputType: Type[Output]

The type of output this runnable produces specified as a type annotation.

abstract get_search_data(query: str, num_results: int = 5) → List[Passage]

Abstract method for searching passages from the web search engine.

invoke(input: Input, config: RunnableConfig | None = None) → Output

Invoke the WebSearch module. :param input: A query string. :param config: You can set num_results in config. The configurable key is “web_search_options”. For example,

runnable.invoke(“your search query”, config={“configurable”: {“web_search_options”: {“num_results”: 10}}})

RAGchain.utils.websearch.bing_search module

class RAGchain.utils.websearch.bing_search.BingSearch

Bases: BaseWebSearch

Langchain’s ‘BingSearchAPIWrapper’ returns a List[Dict[str, str]] as the return value. This BingSearch class wraps this return value in a Passage.

First, you need to set up the proper API keys and environment variables. To set it up, create the BING_SUBSCRIPTION_KEY in the Bing Search API (https://portal.azure.com/#home) and a BING_SEARCH_URL using the Bing Search API

get_search_data(query, num_results=5) → List[Passage]

Abstract method for searching passages from the web search engine.

RAGchain.utils.websearch.google_search module

class RAGchain.utils.websearch.google_search.GoogleSearch

Bases: BaseWebSearch

Langchain’s ‘GoogleSearchAPIWrapper’ returns a List[Dict[str, str]] as the return value. This GoogleSearch class wraps this return value in a Passage.

First, you need to set up the proper API keys and environment variables. To set it up, create the GOOGLE_API_KEY in the Google Cloud credential console (https://console.cloud.google.com/apis/credentials) and a GOOGLE_CSE_ID using the Programmable Search Engine (https://programmablesearchengine.google.com/controlpanel/create).

batch(inputs: List[Input], config: RunnableConfig | List[RunnableConfig] | None = None, *, return_exceptions: bool = False, **kwargs: Any | None) → List[Output]

Default implementation runs invoke in parallel using a thread pool executor.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying runnable uses an API which supports a batch mode.

get_search_data(query, num_results=5, search_params: Dict[str, str] | None = None) → List[Passage]

Abstract method for searching passages from the web search engine.

Module contents