Skip to content

Opensearch

OpensearchVectorStore #

Bases: BasePydanticVectorStore

Elasticsearch/Opensearch vector store.

Parameters:

Name Type Description Default
client OpensearchVectorClient

Vector index client to use for data insertion/querying.

required

Examples:

pip install llama-index-vector-stores-opensearch

from llama_index.vector_stores.opensearch import (
    OpensearchVectorStore,
    OpensearchVectorClient,
)

# http endpoint for your cluster (opensearch required for vector index usage)
endpoint = "http://localhost:9200"
# index to demonstrate the VectorStore impl
idx = "gpt-index-demo"

# OpensearchVectorClient stores text in this field by default
text_field = "content"
# OpensearchVectorClient stores embeddings in this field by default
embedding_field = "embedding"

# OpensearchVectorClient encapsulates logic for a
# single opensearch index with vector search enabled
client = OpensearchVectorClient(
    endpoint, idx, 1536, embedding_field=embedding_field, text_field=text_field
)

# initialize vector store
vector_store = OpensearchVectorStore(client)
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
class OpensearchVectorStore(BasePydanticVectorStore):
    """
    Elasticsearch/Opensearch vector store.

    Args:
        client (OpensearchVectorClient): Vector index client to use
            for data insertion/querying.

    Examples:
        `pip install llama-index-vector-stores-opensearch`

        ```python
        from llama_index.vector_stores.opensearch import (
            OpensearchVectorStore,
            OpensearchVectorClient,
        )

        # http endpoint for your cluster (opensearch required for vector index usage)
        endpoint = "http://localhost:9200"
        # index to demonstrate the VectorStore impl
        idx = "gpt-index-demo"

        # OpensearchVectorClient stores text in this field by default
        text_field = "content"
        # OpensearchVectorClient stores embeddings in this field by default
        embedding_field = "embedding"

        # OpensearchVectorClient encapsulates logic for a
        # single opensearch index with vector search enabled
        client = OpensearchVectorClient(
            endpoint, idx, 1536, embedding_field=embedding_field, text_field=text_field
        )

        # initialize vector store
        vector_store = OpensearchVectorStore(client)
        ```

    """

    stores_text: bool = True
    _client: OpensearchVectorClient = PrivateAttr(default=None)

    def __init__(
        self,
        client: OpensearchVectorClient,
    ) -> None:
        """Initialize params."""
        super().__init__()
        self._client = client

    @property
    def client(self) -> Any:
        """Get client."""
        return self._client

    def add(
        self,
        nodes: List[BaseNode],
        **add_kwargs: Any,
    ) -> List[str]:
        """
        Add nodes to index.

        Args:
            nodes: List[BaseNode]: list of nodes with embeddings.

        """
        self._client.index_results(nodes)
        return [result.node_id for result in nodes]

    async def async_add(
        self,
        nodes: List[BaseNode],
        **add_kwargs: Any,
    ) -> List[str]:
        """
        Async add nodes to index.

        Args:
            nodes: List[BaseNode]: list of nodes with embeddings.

        """
        await self._client.aindex_results(nodes)
        return [result.node_id for result in nodes]

    def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """
        Delete nodes using with ref_doc_id.

        Args:
            ref_doc_id (str): The doc_id of the document to delete.

        """
        self._client.delete_by_doc_id(ref_doc_id)

    async def adelete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """
        Async delete nodes using with ref_doc_id.

        Args:
            ref_doc_id (str): The doc_id of the document to delete.

        """
        await self._client.adelete_by_doc_id(ref_doc_id)

    def delete_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
        **delete_kwargs: Any,
    ) -> None:
        """
        Deletes nodes async.

        Args:
            node_ids (Optional[List[str]], optional): IDs of nodes to delete. Defaults to None.
            filters (Optional[MetadataFilters], optional): Metadata filters. Defaults to None.

        """
        self._client.delete_nodes(node_ids, filters, **delete_kwargs)

    async def adelete_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
        **delete_kwargs: Any,
    ) -> None:
        """
        Async deletes nodes async.

        Args:
            node_ids (Optional[List[str]], optional): IDs of nodes to delete. Defaults to None.
            filters (Optional[MetadataFilters], optional): Metadata filters. Defaults to None.

        """
        await self._client.adelete_nodes(node_ids, filters, **delete_kwargs)

    def clear(self) -> None:
        """Clears index."""
        self._client.clear()

    async def aclear(self) -> None:
        """Async clears index."""
        await self._client.aclear()

    def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
        """
        Query index for top k most similar nodes.

        Args:
            query (VectorStoreQuery): Store query object.

        """
        query_embedding = cast(List[float], query.query_embedding)

        return self._client.query(
            query.mode,
            query.query_str,
            query_embedding,
            query.similarity_top_k,
            filters=query.filters,
        )

    async def aquery(
        self, query: VectorStoreQuery, **kwargs: Any
    ) -> VectorStoreQueryResult:
        """
        Async query index for top k most similar nodes.

        Args:
            query (VectorStoreQuery): Store query object.

        """
        query_embedding = cast(List[float], query.query_embedding)

        return await self._client.aquery(
            query.mode,
            query.query_str,
            query_embedding,
            query.similarity_top_k,
            filters=query.filters,
        )

client property #

client: Any

Get client.

add #

add(nodes: List[BaseNode], **add_kwargs: Any) -> List[str]

Add nodes to index.

Parameters:

Name Type Description Default
nodes List[BaseNode]

List[BaseNode]: list of nodes with embeddings.

required
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
968
969
970
971
972
973
974
975
976
977
978
979
980
981
def add(
    self,
    nodes: List[BaseNode],
    **add_kwargs: Any,
) -> List[str]:
    """
    Add nodes to index.

    Args:
        nodes: List[BaseNode]: list of nodes with embeddings.

    """
    self._client.index_results(nodes)
    return [result.node_id for result in nodes]

async_add async #

async_add(nodes: List[BaseNode], **add_kwargs: Any) -> List[str]

Async add nodes to index.

Parameters:

Name Type Description Default
nodes List[BaseNode]

List[BaseNode]: list of nodes with embeddings.

required
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
983
984
985
986
987
988
989
990
991
992
993
994
995
996
async def async_add(
    self,
    nodes: List[BaseNode],
    **add_kwargs: Any,
) -> List[str]:
    """
    Async add nodes to index.

    Args:
        nodes: List[BaseNode]: list of nodes with embeddings.

    """
    await self._client.aindex_results(nodes)
    return [result.node_id for result in nodes]

delete #

delete(ref_doc_id: str, **delete_kwargs: Any) -> None

Delete nodes using with ref_doc_id.

Parameters:

Name Type Description Default
ref_doc_id str

The doc_id of the document to delete.

required
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
 998
 999
1000
1001
1002
1003
1004
1005
1006
def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
    """
    Delete nodes using with ref_doc_id.

    Args:
        ref_doc_id (str): The doc_id of the document to delete.

    """
    self._client.delete_by_doc_id(ref_doc_id)

adelete async #

adelete(ref_doc_id: str, **delete_kwargs: Any) -> None

Async delete nodes using with ref_doc_id.

Parameters:

Name Type Description Default
ref_doc_id str

The doc_id of the document to delete.

required
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1008
1009
1010
1011
1012
1013
1014
1015
1016
async def adelete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
    """
    Async delete nodes using with ref_doc_id.

    Args:
        ref_doc_id (str): The doc_id of the document to delete.

    """
    await self._client.adelete_by_doc_id(ref_doc_id)

delete_nodes #

delete_nodes(node_ids: Optional[List[str]] = None, filters: Optional[MetadataFilters] = None, **delete_kwargs: Any) -> None

Deletes nodes async.

Parameters:

Name Type Description Default
node_ids Optional[List[str]]

IDs of nodes to delete. Defaults to None.

None
filters Optional[MetadataFilters]

Metadata filters. Defaults to None.

None
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
def delete_nodes(
    self,
    node_ids: Optional[List[str]] = None,
    filters: Optional[MetadataFilters] = None,
    **delete_kwargs: Any,
) -> None:
    """
    Deletes nodes async.

    Args:
        node_ids (Optional[List[str]], optional): IDs of nodes to delete. Defaults to None.
        filters (Optional[MetadataFilters], optional): Metadata filters. Defaults to None.

    """
    self._client.delete_nodes(node_ids, filters, **delete_kwargs)

adelete_nodes async #

adelete_nodes(node_ids: Optional[List[str]] = None, filters: Optional[MetadataFilters] = None, **delete_kwargs: Any) -> None

Async deletes nodes async.

Parameters:

Name Type Description Default
node_ids Optional[List[str]]

IDs of nodes to delete. Defaults to None.

None
filters Optional[MetadataFilters]

Metadata filters. Defaults to None.

None
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
async def adelete_nodes(
    self,
    node_ids: Optional[List[str]] = None,
    filters: Optional[MetadataFilters] = None,
    **delete_kwargs: Any,
) -> None:
    """
    Async deletes nodes async.

    Args:
        node_ids (Optional[List[str]], optional): IDs of nodes to delete. Defaults to None.
        filters (Optional[MetadataFilters], optional): Metadata filters. Defaults to None.

    """
    await self._client.adelete_nodes(node_ids, filters, **delete_kwargs)

clear #

clear() -> None

Clears index.

Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1050
1051
1052
def clear(self) -> None:
    """Clears index."""
    self._client.clear()

aclear async #

aclear() -> None

Async clears index.

Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1054
1055
1056
async def aclear(self) -> None:
    """Async clears index."""
    await self._client.aclear()

query #

query(query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult

Query index for top k most similar nodes.

Parameters:

Name Type Description Default
query VectorStoreQuery

Store query object.

required
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
    """
    Query index for top k most similar nodes.

    Args:
        query (VectorStoreQuery): Store query object.

    """
    query_embedding = cast(List[float], query.query_embedding)

    return self._client.query(
        query.mode,
        query.query_str,
        query_embedding,
        query.similarity_top_k,
        filters=query.filters,
    )

aquery async #

aquery(query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult

Async query index for top k most similar nodes.

Parameters:

Name Type Description Default
query VectorStoreQuery

Store query object.

required
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
async def aquery(
    self, query: VectorStoreQuery, **kwargs: Any
) -> VectorStoreQueryResult:
    """
    Async query index for top k most similar nodes.

    Args:
        query (VectorStoreQuery): Store query object.

    """
    query_embedding = cast(List[float], query.query_embedding)

    return await self._client.aquery(
        query.mode,
        query.query_str,
        query_embedding,
        query.similarity_top_k,
        filters=query.filters,
    )