mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
aed46cd6f2
**Description:** It will add support for filter out kendra search by score confidence which will make result more accurate. For example ``` retriever = AmazonKendraRetriever( index_id=kendra_index_id, top_k=5, region_name=region, score_confidence="HIGH" ) ``` Result will not include the records which has score confidence "LOW" or "MEDIUM". Relevant docs https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/kendra/client/query.html https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/kendra/client/retrieve.html **Issue:** the issue # it resolve #11801 **twitter:** [@SmitCode](https://twitter.com/SmitCode) |
||
---|---|---|
.. | ||
__init__.py | ||
arcee.py | ||
arxiv.py | ||
azure_cognitive_search.py | ||
bedrock.py | ||
bm25.py | ||
breebs.py | ||
chaindesk.py | ||
chatgpt_plugin_retriever.py | ||
cohere_rag_retriever.py | ||
databerry.py | ||
docarray.py | ||
elastic_search_bm25.py | ||
embedchain.py | ||
google_cloud_documentai_warehouse.py | ||
google_vertex_ai_search.py | ||
kay.py | ||
kendra.py | ||
knn.py | ||
llama_index.py | ||
metal.py | ||
milvus.py | ||
outline.py | ||
pinecone_hybrid_search.py | ||
pubmed.py | ||
pupmed.py | ||
qdrant_sparse_vector_retriever.py | ||
remote_retriever.py | ||
svm.py | ||
tavily_search_api.py | ||
tfidf.py | ||
vespa_retriever.py | ||
weaviate_hybrid_search.py | ||
wikipedia.py | ||
you.py | ||
zep.py | ||
zilliz.py |