Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

community: add Kendra DocumentRelevanceOverrideConfigurations request parameter #20695

Merged
merged 2 commits into from
May 6, 2024
Merged

community: add Kendra DocumentRelevanceOverrideConfigurations request parameter #20695

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8327d22
feat: add Kendra DocumentRelevanceOverrideConfigurations request para…
scaseriniklarna Apr 20, 2024
db495c9
Merge branch 'master' into add-kendra-document-relevance-config
baskaryan Apr 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions libs/community/langchain_community/retrievers/kendra.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,6 +344,10 @@ class AmazonKendraRetriever(BaseRetriever):
attribute_filter: Additional filtering of results based on metadata
See: https://docs.aws.amazon.com/kendra/latest/APIReference

document_relevance_override_configurations: Overrides relevance tuning
configurations of fields/attributes set at the index level
See: https://docs.aws.amazon.com/kendra/latest/APIReference

page_content_formatter: generates the Document page_content
allowing access to all result item attributes. By default, it uses
the item's title and excerpt.
Expand All @@ -367,6 +371,7 @@ class AmazonKendraRetriever(BaseRetriever):
credentials_profile_name: Optional[str] = None
top_k: int = 3
attribute_filter: Optional[Dict] = None
document_relevance_override_configurations: Optional[List[Dict]] = None
page_content_formatter: Callable[[ResultItem], str] = combined_text
client: Any
user_context: Optional[Dict] = None
Expand Down Expand Up @@ -421,6 +426,10 @@ def _kendra_query(self, query: str) -> Sequence[ResultItem]:
}
if self.attribute_filter is not None:
kendra_kwargs["AttributeFilter"] = self.attribute_filter
if self.document_relevance_override_configurations is not None:
kendra_kwargs[
"DocumentRelevanceOverrideConfigurations"
] = self.document_relevance_override_configurations
if self.user_context is not None:
kendra_kwargs["UserContext"] = self.user_context

Expand Down
Loading