yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-11-03 11:19:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Move WebRetriever's new init parameter to last parameter position (#5673)

Browse Source
This commit is contained in:
Vladimir Blagojevic 2023-08-29 17:46:12 +02:00 committed by GitHub
parent fbc1951e74
commit a9b8fd9658
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
haystack/nodes/retriever/web.py
View File

@ -50,8 +50,6 @@ class WebRetriever(BaseRetriever):
self,
api_key: str,
search_engine_provider: Union[str, SearchEngine] = "SerperDev",
allowed_domains: Optional[List[str]] = None,
link_content_fetcher: Optional[LinkContentFetcher] = None,
top_search_results: Optional[int] = 10,
top_k: Optional[int] = 5,
mode: Literal["snippets", "raw_documents", "preprocessed_documents"] = "snippets",
@ -60,13 +58,12 @@ class WebRetriever(BaseRetriever):
cache_index: Optional[str] = None,
cache_headers: Optional[Dict[str, str]] = None,
cache_time: int = 1 * 24 * 60 * 60,
allowed_domains: Optional[List[str]] = None,
link_content_fetcher: Optional[LinkContentFetcher] = None,
):
"""
:param api_key: API key for the search engine provider.
:param search_engine_provider: Name of the search engine provider class, see `providers.py` for a list of supported providers.
:param allowed_domains: List of domains to restrict the search to. If not provided, the search is unrestricted.
:param link_content_fetcher: LinkContentFetcher to be used to fetch the content from the links. If not provided,
the default LinkContentFetcher is used.
:param top_search_results: Number of top search results to be retrieved.
:param top_k: Top k documents to be returned by the retriever.
:param mode: Whether to return snippets, raw documents, or preprocessed documents. Snippets are the default.
@ -75,6 +72,10 @@ class WebRetriever(BaseRetriever):
:param cache_index: Index name to be used to cache search results.
:param cache_headers: Headers to be used to cache search results.
:param cache_time: Time in seconds to cache search results. Defaults to 24 hours.
:param allowed_domains: List of domains to restrict the search to. If not provided, the search is unrestricted.
:param link_content_fetcher: LinkContentFetcher to be used to fetch the content from the links. If not provided,
the default LinkContentFetcher is used.
"""
super().__init__()
self.web_search = WebSearch(