Qdrant

QdrantVectorStore

Bases: BasePydanticVectorStore

Qdrant向量存储。

在这个向量存储中，嵌入和文档都存储在Qdrant集合中。

在查询时，索引使用Qdrant查询前k个最相似的节点。

Parameters:

Name	Type	Description	Default
collection_name	str	(str): Qdrant集合的名称	required
client	Optional[Any]	qdrant-client包中的QdrantClient实例	None
aclient	Optional[Any]	qdrant-client包中的AsyncQdrantClient实例	None
url	Optional[str]	Qdrant实例的url	None
api_key	Optional[str]	用于与Qdrant进行身份验证的API密钥	None
batch_size	int	单个请求上传到Qdrant的点的数量。默认为64	64
parallel	int	上传时使用的并行进程数。默认为1	1
max_retries	int	失败时的最大重试次数。默认为3	3
client_kwargs	Optional[dict]	用于QdrantClient和AsyncQdrantClient的额外kwargs	None
enable_hybrid	bool	是否启用使用稠密和稀疏向量进行混合搜索	False
sparse_doc_fn	Optional[SparseEncoderCallable]	用于编码稀疏向量的函数	None
sparse_query_fn	Optional[SparseEncoderCallable]	用于编码稀疏查询的函数	None
hybrid_fusion_fn	Optional[HybridFusionCallable]	用于融合混合搜索结果的函数	None

示例： pip install llama-index-vector-stores-qdrant

```python
import qdrant_client
from llama_index.vector_stores.qdrant import QdrantVectorStore

client = qdrant_client.QdrantClient()

vector_store = QdrantVectorStore(
    collection_name="example_collection", client=client
)
```

Source code in llama_index/vector_stores/qdrant/base.py

class QdrantVectorStore(BasePydanticVectorStore):
    """Qdrant向量存储。

在这个向量存储中，嵌入和文档都存储在Qdrant集合中。

在查询时，索引使用Qdrant查询前k个最相似的节点。

Args:
    collection_name: (str): Qdrant集合的名称
    client (Optional[Any]): `qdrant-client`包中的QdrantClient实例
    aclient (Optional[Any]): `qdrant-client`包中的AsyncQdrantClient实例
    url (Optional[str]): Qdrant实例的url
    api_key (Optional[str]): 用于与Qdrant进行身份验证的API密钥
    batch_size (int): 单个请求上传到Qdrant的点的数量。默认为64
    parallel (int): 上传时使用的并行进程数。默认为1
    max_retries (int): 失败时的最大重试次数。默认为3
    client_kwargs (Optional[dict]): 用于QdrantClient和AsyncQdrantClient的额外kwargs
    enable_hybrid (bool): 是否启用使用稠密和稀疏向量进行混合搜索
    sparse_doc_fn (Optional[SparseEncoderCallable]): 用于编码稀疏向量的函数
    sparse_query_fn (Optional[SparseEncoderCallable]): 用于编码稀疏查询的函数
    hybrid_fusion_fn (Optional[HybridFusionCallable]): 用于融合混合搜索结果的函数

示例：
    `pip install llama-index-vector-stores-qdrant`

    ```python
    import qdrant_client
    from llama_index.vector_stores.qdrant import QdrantVectorStore

    client = qdrant_client.QdrantClient()

    vector_store = QdrantVectorStore(
        collection_name="example_collection", client=client
    )
    ```"""

    stores_text: bool = True
    flat_metadata: bool = False

    collection_name: str
    path: Optional[str]
    url: Optional[str]
    api_key: Optional[str]
    batch_size: int
    parallel: int
    max_retries: int
    client_kwargs: dict = Field(default_factory=dict)
    enable_hybrid: bool

    _client: qdrant_client.QdrantClient = PrivateAttr()
    _aclient: qdrant_client.AsyncQdrantClient = PrivateAttr()
    _collection_initialized: bool = PrivateAttr()
    _sparse_doc_fn: Optional[SparseEncoderCallable] = PrivateAttr()
    _sparse_query_fn: Optional[SparseEncoderCallable] = PrivateAttr()
    _hybrid_fusion_fn: Optional[HybridFusionCallable] = PrivateAttr()

    def __init__(
        self,
        collection_name: str,
        client: Optional[Any] = None,
        aclient: Optional[Any] = None,
        url: Optional[str] = None,
        api_key: Optional[str] = None,
        batch_size: int = 64,
        parallel: int = 1,
        max_retries: int = 3,
        client_kwargs: Optional[dict] = None,
        enable_hybrid: bool = False,
        sparse_doc_fn: Optional[SparseEncoderCallable] = None,
        sparse_query_fn: Optional[SparseEncoderCallable] = None,
        hybrid_fusion_fn: Optional[HybridFusionCallable] = None,
        **kwargs: Any,
    ) -> None:
        """初始化参数。"""
        if (
            client is None
            and aclient is None
            and (url is None or api_key is None or collection_name is None)
        ):
            raise ValueError(
                "Must provide either a QdrantClient instance or a url and api_key."
            )

        if client is None and aclient is None:
            client_kwargs = client_kwargs or {}
            self._client = qdrant_client.QdrantClient(
                url=url, api_key=api_key, **client_kwargs
            )
            self._aclient = qdrant_client.AsyncQdrantClient(
                url=url, api_key=api_key, **client_kwargs
            )
        else:
            if client is not None and aclient is not None:
                logger.warning(
                    "Both client and aclient are provided. If using `:memory:` "
                    "mode, the data between clients is not synced."
                )

            self._client = client
            self._aclient = aclient

        if self._client is not None:
            self._collection_initialized = self._collection_exists(collection_name)
        else:
            #  need to do lazy init for async clients
            self._collection_initialized = False

        # setup hybrid search if enabled
        if enable_hybrid:
            self._sparse_doc_fn = sparse_doc_fn or self.get_default_sparse_doc_encoder(
                collection_name
            )
            self._sparse_query_fn = (
                sparse_query_fn
                or self.get_default_sparse_query_encoder(collection_name)
            )
            self._hybrid_fusion_fn = hybrid_fusion_fn or cast(
                HybridFusionCallable, relative_score_fusion
            )

        super().__init__(
            collection_name=collection_name,
            url=url,
            api_key=api_key,
            batch_size=batch_size,
            parallel=parallel,
            max_retries=max_retries,
            client_kwargs=client_kwargs or {},
            enable_hybrid=enable_hybrid,
        )

    @classmethod
    def class_name(cls) -> str:
        return "QdrantVectorStore"

    def set_query_functions(
        self,
        sparse_doc_fn: Optional[SparseEncoderCallable] = None,
        sparse_query_fn: Optional[SparseEncoderCallable] = None,
        hybrid_fusion_fn: Optional[HybridFusionCallable] = None,
    ):
        self._sparse_doc_fn = sparse_doc_fn
        self._sparse_query_fn = sparse_query_fn
        self._hybrid_fusion_fn = hybrid_fusion_fn

    def _build_points(
        self, nodes: List[BaseNode], sparse_vector_name: str
    ) -> Tuple[List[Any], List[str]]:
        ids = []
        points = []
        for node_batch in iter_batch(nodes, self.batch_size):
            node_ids = []
            vectors: List[Any] = []
            sparse_vectors: List[List[float]] = []
            sparse_indices: List[List[int]] = []
            payloads = []

            if self.enable_hybrid and self._sparse_doc_fn is not None:
                sparse_indices, sparse_vectors = self._sparse_doc_fn(
                    [
                        node.get_content(metadata_mode=MetadataMode.EMBED)
                        for node in node_batch
                    ],
                )

            for i, node in enumerate(node_batch):
                assert isinstance(node, BaseNode)
                node_ids.append(node.node_id)

                if self.enable_hybrid:
                    if (
                        len(sparse_vectors) > 0
                        and len(sparse_indices) > 0
                        and len(sparse_vectors) == len(sparse_indices)
                    ):
                        vectors.append(
                            {
                                # Dynamically switch between the old and new sparse vector name
                                sparse_vector_name: rest.SparseVector(
                                    indices=sparse_indices[i],
                                    values=sparse_vectors[i],
                                ),
                                DENSE_VECTOR_NAME: node.get_embedding(),
                            }
                        )
                    else:
                        vectors.append(
                            {
                                DENSE_VECTOR_NAME: node.get_embedding(),
                            }
                        )
                else:
                    vectors.append(node.get_embedding())

                metadata = node_to_metadata_dict(
                    node, remove_text=False, flat_metadata=self.flat_metadata
                )

                payloads.append(metadata)

            points.extend(
                [
                    rest.PointStruct(id=node_id, payload=payload, vector=vector)
                    for node_id, payload, vector in zip(node_ids, payloads, vectors)
                ]
            )

            ids.extend(node_ids)

        return points, ids

    def get_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
    ) -> List[BaseNode]:
        """从索引中获取节点。

Args:
    node_ids (Optional[List[str]]): 要检索的节点ID列表。
    filters (Optional[MetadataFilters]): 要应用的元数据过滤器。

Returns:
    List[BaseNode]: 从索引中检索到的节点列表。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        response = self._client.scroll(
            collection_name=self.collection_name,
            limit=9999,
            scroll_filter=filter,
        )

        return self.parse_to_query_result(response[0]).nodes

    async def aget_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
    ) -> List[BaseNode]:
        """异步方法，用于从索引中获取节点。

Args:
    node_ids（可选[List[str]]）：要检索的节点ID列表。
    filters（可选[MetadataFilters]）：要应用的元数据过滤器。

Returns:
    List[BaseNode]：从索引中检索到的节点列表。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        response = await self._aclient.scroll(
            collection_name=self.collection_name,
            limit=9999,
            scroll_filter=filter,
        )

        return self.parse_to_query_result(response[0]).nodes

    def add(self, nodes: List[BaseNode], **add_kwargs: Any) -> List[str]:
        """将节点添加到索引中。

Args:
    节点: List[BaseNode]: 带有嵌入的节点列表
"""
        if len(nodes) > 0 and not self._collection_initialized:
            self._create_collection(
                collection_name=self.collection_name,
                vector_size=len(nodes[0].get_embedding()),
            )

        sparse_vector_name = self.sparse_vector_name()
        points, ids = self._build_points(nodes, sparse_vector_name)

        self._client.upload_points(
            collection_name=self.collection_name,
            points=points,
            batch_size=self.batch_size,
            parallel=self.parallel,
            max_retries=self.max_retries,
            wait=True,
        )

        return ids

    async def async_add(self, nodes: List[BaseNode], **kwargs: Any) -> List[str]:
        """异步方法，用于向Qdrant索引中添加节点。

Args:
    nodes: List[BaseNode]: 带有嵌入的节点列表。

Returns:
    被添加到索引中的节点ID列表。

抛出：
    ValueError: 如果尝试在没有aclient的情况下使用异步方法。
"""
        collection_initialized = await self._acollection_exists(self.collection_name)

        if len(nodes) > 0 and not collection_initialized:
            await self._acreate_collection(
                collection_name=self.collection_name,
                vector_size=len(nodes[0].get_embedding()),
            )

        sparse_vector_name = await self.asparse_vector_name()
        points, ids = self._build_points(nodes, sparse_vector_name)

        await self._aclient.upload_points(
            collection_name=self.collection_name,
            points=points,
            batch_size=self.batch_size,
            parallel=self.parallel,
            max_retries=self.max_retries,
            wait=True,
        )

        return ids

    def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """使用ref_doc_id删除节点。

Args:
    ref_doc_id（str）：要删除的文档的doc_id。
"""
        self._client.delete(
            collection_name=self.collection_name,
            points_selector=rest.Filter(
                must=[
                    rest.FieldCondition(
                        key="doc_id", match=rest.MatchValue(value=ref_doc_id)
                    )
                ]
            ),
        )

    async def adelete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """异步方法，使用ref_doc_id删除节点。

Args:
    ref_doc_id（str）：要删除的文档的doc_id。
"""
        await self._aclient.delete(
            collection_name=self.collection_name,
            points_selector=rest.Filter(
                must=[
                    rest.FieldCondition(
                        key="doc_id", match=rest.MatchValue(value=ref_doc_id)
                    )
                ]
            ),
        )

    def delete_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
        **delete_kwargs: Any,
    ) -> None:
        """使用node_ids删除节点。

Args:
    node_ids（可选[List[str]）：要删除的节点ID列表。
    filters（可选[MetadataFilters]）：要应用的元数据过滤器。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        self._client.delete(
            collection_name=self.collection_name,
            points_selector=filter,
        )

    async def adelete_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
        **delete_kwargs: Any,
    ) -> None:
        """异步方法，使用节点ID删除节点。

Args:
    node_ids（可选[List[str]）：要删除的节点ID列表。
    filters（可选[MetadataFilters]）：要应用的元数据过滤器。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        await self._aclient.delete(
            collection_name=self.collection_name,
            points_selector=filter,
        )

    def clear(self) -> None:
        """
        清空索引。
        """
        self._client.delete_collection(collection_name=self.collection_name)
        self._collection_initialized = False

    async def aclear(self) -> None:
        """
        异步清除索引的方法。
        """
        await self._aclient.delete_collection(collection_name=self.collection_name)
        self._collection_initialized = False

    @property
    def client(self) -> Any:
        """返回Qdrant客户端。"""
        return self._client

    def _create_collection(self, collection_name: str, vector_size: int) -> None:
        """创建一个Qdrant集合。"""
        from qdrant_client.http import models as rest
        from qdrant_client.http.exceptions import UnexpectedResponse

        try:
            if self.enable_hybrid:
                self._client.create_collection(
                    collection_name=collection_name,
                    vectors_config={
                        DENSE_VECTOR_NAME: rest.VectorParams(
                            size=vector_size,
                            distance=rest.Distance.COSINE,
                        )
                    },
                    # Newly created collection will have the new sparse vector name
                    sparse_vectors_config={
                        SPARSE_VECTOR_NAME: rest.SparseVectorParams(
                            index=rest.SparseIndexParams()
                        )
                    },
                )
            else:
                self._client.create_collection(
                    collection_name=collection_name,
                    vectors_config=rest.VectorParams(
                        size=vector_size,
                        distance=rest.Distance.COSINE,
                    ),
                )
        except (RpcError, ValueError, UnexpectedResponse) as exc:
            if "already exists" not in str(exc):
                raise exc  # noqa: TRY201
            logger.warning(
                "Collection %s already exists, skipping collection creation.",
                collection_name,
            )
        self._collection_initialized = True

    async def _acreate_collection(self, collection_name: str, vector_size: int) -> None:
        """创建一个Qdrant集合的异步方法。"""
        from qdrant_client.http import models as rest
        from qdrant_client.http.exceptions import UnexpectedResponse

        try:
            if self.enable_hybrid:
                await self._aclient.create_collection(
                    collection_name=collection_name,
                    vectors_config={
                        DENSE_VECTOR_NAME: rest.VectorParams(
                            size=vector_size,
                            distance=rest.Distance.COSINE,
                        )
                    },
                    sparse_vectors_config={
                        SPARSE_VECTOR_NAME: rest.SparseVectorParams(
                            index=rest.SparseIndexParams()
                        )
                    },
                )
            else:
                await self._aclient.create_collection(
                    collection_name=collection_name,
                    vectors_config=rest.VectorParams(
                        size=vector_size,
                        distance=rest.Distance.COSINE,
                    ),
                )
        except (RpcError, ValueError, UnexpectedResponse) as exc:
            if "already exists" not in str(exc):
                raise exc  # noqa: TRY201
            logger.warning(
                "Collection %s already exists, skipping collection creation.",
                collection_name,
            )
        self._collection_initialized = True

    def _collection_exists(self, collection_name: str) -> bool:
        """检查集合是否存在。"""
        try:
            return self._client.collection_exists(collection_name)
        except (RpcError, UnexpectedResponse, ValueError):
            return False

    async def _acollection_exists(self, collection_name: str) -> bool:
        """异步方法，用于检查集合是否存在。"""
        try:
            return await self._aclient.collection_exists(collection_name)
        except (RpcError, UnexpectedResponse, ValueError):
            return False

    def query(
        self,
        query: VectorStoreQuery,
        **kwargs: Any,
    ) -> VectorStoreQueryResult:
        """查询索引以获取前k个最相似的节点。

Args:
    query（VectorStoreQuery）：查询
"""
        query_embedding = cast(List[float], query.query_embedding)
        #  NOTE: users can pass in qdrant_filters (nested/complicated filters) to override the default MetadataFilters
        qdrant_filters = kwargs.get("qdrant_filters")
        if qdrant_filters is not None:
            query_filter = qdrant_filters
        else:
            query_filter = cast(Filter, self._build_query_filter(query))

        if query.mode == VectorStoreQueryMode.HYBRID and not self.enable_hybrid:
            raise ValueError(
                "Hybrid search is not enabled. Please build the query with "
                "`enable_hybrid=True` in the constructor."
            )
        elif (
            query.mode == VectorStoreQueryMode.HYBRID
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = self._client.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=self.sparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            # sanity check
            assert len(sparse_response) == 2
            assert self._hybrid_fusion_fn is not None

            # flatten the response
            return self._hybrid_fusion_fn(
                self.parse_to_query_result(sparse_response[0]),
                self.parse_to_query_result(sparse_response[1]),
                # NOTE: only for hybrid search (0 for sparse search, 1 for dense search)
                alpha=query.alpha or 0.5,
                # NOTE: use hybrid_top_k if provided, otherwise use similarity_top_k
                top_k=query.hybrid_top_k or query.similarity_top_k,
            )
        elif (
            query.mode == VectorStoreQueryMode.SPARSE
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = self._client.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=self.sparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )
            return self.parse_to_query_result(sparse_response[0])

        elif self.enable_hybrid:
            # search for dense vectors only
            response = self._client.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            return self.parse_to_query_result(response[0])
        else:
            response = self._client.search(
                collection_name=self.collection_name,
                query_vector=query_embedding,
                limit=query.similarity_top_k,
                query_filter=query_filter,
            )
            return self.parse_to_query_result(response)

    async def aquery(
        self, query: VectorStoreQuery, **kwargs: Any
    ) -> VectorStoreQueryResult:
        """异步方法，用于查询前 k 个最相似节点的索引。

Args:
    query (VectorStoreQuery): 查询
"""
        query_embedding = cast(List[float], query.query_embedding)

        #  NOTE: users can pass in qdrant_filters (nested/complicated filters) to override the default MetadataFilters
        qdrant_filters = kwargs.get("qdrant_filters")
        if qdrant_filters is not None:
            query_filter = qdrant_filters
        else:
            # build metadata filters
            query_filter = cast(Filter, self._build_query_filter(query))

        if query.mode == VectorStoreQueryMode.HYBRID and not self.enable_hybrid:
            raise ValueError(
                "Hybrid search is not enabled. Please build the query with "
                "`enable_hybrid=True` in the constructor."
            )
        elif (
            query.mode == VectorStoreQueryMode.HYBRID
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = await self._aclient.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=await self.asparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            # sanity check
            assert len(sparse_response) == 2
            assert self._hybrid_fusion_fn is not None

            # flatten the response
            return self._hybrid_fusion_fn(
                self.parse_to_query_result(sparse_response[0]),
                self.parse_to_query_result(sparse_response[1]),
                alpha=query.alpha or 0.5,
                # NOTE: use hybrid_top_k if provided, otherwise use similarity_top_k
                top_k=query.hybrid_top_k or query.similarity_top_k,
            )
        elif (
            query.mode == VectorStoreQueryMode.SPARSE
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = await self._aclient.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=await self.asparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )
            return self.parse_to_query_result(sparse_response[0])
        elif self.enable_hybrid:
            # search for dense vectors only
            response = await self._aclient.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            return self.parse_to_query_result(response[0])
        else:
            response = await self._aclient.search(
                collection_name=self.collection_name,
                query_vector=query_embedding,
                limit=query.similarity_top_k,
                query_filter=query_filter,
            )

            return self.parse_to_query_result(response)

    def parse_to_query_result(self, response: List[Any]) -> VectorStoreQueryResult:
        """将向量存储响应转换为VectorStoreQueryResult。

Args:
    response: List[Any]: 从向量存储返回的结果列表。
"""
        nodes = []
        similarities = []
        ids = []

        for point in response:
            payload = cast(Payload, point.payload)
            try:
                node = metadata_dict_to_node(payload)
            except Exception:
                metadata, node_info, relationships = legacy_metadata_dict_to_node(
                    payload
                )

                node = TextNode(
                    id_=str(point.id),
                    text=payload.get("text"),
                    metadata=metadata,
                    start_char_idx=node_info.get("start", None),
                    end_char_idx=node_info.get("end", None),
                    relationships=relationships,
                )
            nodes.append(node)
            ids.append(str(point.id))
            try:
                similarities.append(point.score)
            except AttributeError:
                # certain requests do not return a score
                similarities.append(1.0)

        return VectorStoreQueryResult(nodes=nodes, similarities=similarities, ids=ids)

    def _build_subfilter(self, filters: MetadataFilters) -> Filter:
        conditions = []
        for subfilter in filters.filters:
            # only for exact match
            if isinstance(subfilter, MetadataFilters) and len(subfilter.filters) > 0:
                conditions.append(self._build_subfilter(subfilter))
            elif not subfilter.operator or subfilter.operator == FilterOperator.EQ:
                if isinstance(subfilter.value, float):
                    conditions.append(
                        FieldCondition(
                            key=subfilter.key,
                            range=Range(
                                gte=subfilter.value,
                                lte=subfilter.value,
                            ),
                        )
                    )
                else:
                    conditions.append(
                        FieldCondition(
                            key=subfilter.key,
                            match=MatchValue(value=subfilter.value),
                        )
                    )
            elif subfilter.operator == FilterOperator.LT:
                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        range=Range(lt=subfilter.value),
                    )
                )
            elif subfilter.operator == FilterOperator.GT:
                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        range=Range(gt=subfilter.value),
                    )
                )
            elif subfilter.operator == FilterOperator.GTE:
                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        range=Range(gte=subfilter.value),
                    )
                )
            elif subfilter.operator == FilterOperator.LTE:
                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        range=Range(lte=subfilter.value),
                    )
                )
            elif subfilter.operator == FilterOperator.TEXT_MATCH:
                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        match=MatchText(text=subfilter.value),
                    )
                )
            elif subfilter.operator == FilterOperator.NE:
                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        match=MatchExcept(**{"except": [subfilter.value]}),
                    )
                )
            elif subfilter.operator == FilterOperator.IN:
                # match any of the values
                # https://qdrant.tech/documentation/concepts/filtering/#match-any
                if isinstance(subfilter.value, List):
                    values = [str(val) for val in subfilter.value]
                else:
                    values = str(subfilter.value).split(",")

                conditions.append(
                    FieldCondition(
                        key=subfilter.key,
                        match=MatchAny(any=values),
                    )
                )

        filter = Filter()
        if filters.condition == FilterCondition.AND:
            filter.must = conditions
        elif filters.condition == FilterCondition.OR:
            filter.should = conditions
        return filter

    def _build_query_filter(self, query: VectorStoreQuery) -> Optional[Any]:
        if not query.doc_ids and not query.query_str:
            return None

        must_conditions = []

        if query.doc_ids:
            must_conditions.append(
                FieldCondition(
                    key="doc_id",
                    match=MatchAny(any=query.doc_ids),
                )
            )

        # Point id is a “service” id, it is not stored in payload. There is ‘HasId’ condition to filter by point id
        # https://qdrant.tech/documentation/concepts/filtering/#has-id
        if query.node_ids:
            must_conditions.append(
                HasIdCondition(has_id=query.node_ids),
            )

        # Qdrant does not use the query.query_str property for the filtering. Full-text
        # filtering cannot handle longer queries and can effectively filter our all the
        # nodes. See: https://github.com/jerryjliu/llama_index/pull/1181

        if query.filters and query.filters.filters:
            must_conditions.append(self._build_subfilter(query.filters))

        return Filter(must=must_conditions)

    def use_old_sparse_encoder(self, collection_name: str) -> bool:
        collection_exists = self._collection_exists(collection_name)
        if collection_exists:
            cur_collection = self.client.get_collection(collection_name)
            return SPARSE_VECTOR_NAME_OLD in (
                cur_collection.config.params.sparse_vectors or {}
            )

        return False

    def sparse_vector_name(self) -> str:
        return (
            SPARSE_VECTOR_NAME_OLD
            if self.use_old_sparse_encoder(self.collection_name)
            else SPARSE_VECTOR_NAME
        )

    async def ause_old_sparse_encoder(self, collection_name: str) -> bool:
        collection_exists = await self._acollection_exists(collection_name)
        if collection_exists:
            cur_collection = await self._aclient.get_collection(collection_name)
            return SPARSE_VECTOR_NAME_OLD in (
                cur_collection.config.params.sparse_vectors or {}
            )

        return False

    async def asparse_vector_name(self) -> str:
        return (
            SPARSE_VECTOR_NAME_OLD
            if await self.ause_old_sparse_encoder(self.collection_name)
            else SPARSE_VECTOR_NAME
        )

    def get_default_sparse_doc_encoder(
        self, collection_name: str
    ) -> SparseEncoderCallable:
        if self.use_old_sparse_encoder(collection_name):
            return default_sparse_encoder("naver/efficient-splade-VI-BT-large-doc")

        return fastembed_sparse_encoder(model_name="prithvida/Splade_PP_en_v1")

    def get_default_sparse_query_encoder(
        self, collection_name: str
    ) -> SparseEncoderCallable:
        if self.use_old_sparse_encoder(collection_name):
            return default_sparse_encoder("naver/efficient-splade-VI-BT-large-query")

        return fastembed_sparse_encoder(model_name="prithvida/Splade_PP_en_v1")

client property

client: Any

返回Qdrant客户端。

get_nodes

get_nodes(
    node_ids: Optional[List[str]] = None,
    filters: Optional[MetadataFilters] = None,
) -> List[BaseNode]

从索引中获取节点。

Parameters:

Name	Type	Description	Default
node_ids	Optional[List[str]]	要检索的节点ID列表。	None
filters	Optional[MetadataFilters]	要应用的元数据过滤器。	None

Returns:

Type	Description
List[BaseNode]	List[BaseNode]: 从索引中检索到的节点列表。

Source code in llama_index/vector_stores/qdrant/base.py

    def get_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
    ) -> List[BaseNode]:
        """从索引中获取节点。

Args:
    node_ids (Optional[List[str]]): 要检索的节点ID列表。
    filters (Optional[MetadataFilters]): 要应用的元数据过滤器。

Returns:
    List[BaseNode]: 从索引中检索到的节点列表。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        response = self._client.scroll(
            collection_name=self.collection_name,
            limit=9999,
            scroll_filter=filter,
        )

        return self.parse_to_query_result(response[0]).nodes

aget_nodes async

aget_nodes(
    node_ids: Optional[List[str]] = None,
    filters: Optional[MetadataFilters] = None,
) -> List[BaseNode]

异步方法，用于从索引中获取节点。

Returns:

Type	Description
List[BaseNode]	List[BaseNode]：从索引中检索到的节点列表。

Source code in llama_index/vector_stores/qdrant/base.py

    async def aget_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
    ) -> List[BaseNode]:
        """异步方法，用于从索引中获取节点。

Args:
    node_ids（可选[List[str]]）：要检索的节点ID列表。
    filters（可选[MetadataFilters]）：要应用的元数据过滤器。

Returns:
    List[BaseNode]：从索引中检索到的节点列表。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        response = await self._aclient.scroll(
            collection_name=self.collection_name,
            limit=9999,
            scroll_filter=filter,
        )

        return self.parse_to_query_result(response[0]).nodes

add

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

将节点添加到索引中。

Parameters:

Name	Type	Description	Default
节点		List[BaseNode]: 带有嵌入的节点列表	required

Source code in llama_index/vector_stores/qdrant/base.py

    def add(self, nodes: List[BaseNode], **add_kwargs: Any) -> List[str]:
        """将节点添加到索引中。

Args:
    节点: List[BaseNode]: 带有嵌入的节点列表
"""
        if len(nodes) > 0 and not self._collection_initialized:
            self._create_collection(
                collection_name=self.collection_name,
                vector_size=len(nodes[0].get_embedding()),
            )

        sparse_vector_name = self.sparse_vector_name()
        points, ids = self._build_points(nodes, sparse_vector_name)

        self._client.upload_points(
            collection_name=self.collection_name,
            points=points,
            batch_size=self.batch_size,
            parallel=self.parallel,
            max_retries=self.max_retries,
            wait=True,
        )

        return ids

async_add async

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

异步方法，用于向Qdrant索引中添加节点。

Parameters:

Name	Type	Description	Default
nodes	List[BaseNode]	List[BaseNode]: 带有嵌入的节点列表。	required

Returns:

Type	Description
List[str]	被添加到索引中的节点ID列表。

抛出： ValueError: 如果尝试在没有aclient的情况下使用异步方法。

Source code in llama_index/vector_stores/qdrant/base.py

    async def async_add(self, nodes: List[BaseNode], **kwargs: Any) -> List[str]:
        """异步方法，用于向Qdrant索引中添加节点。

Args:
    nodes: List[BaseNode]: 带有嵌入的节点列表。

Returns:
    被添加到索引中的节点ID列表。

抛出：
    ValueError: 如果尝试在没有aclient的情况下使用异步方法。
"""
        collection_initialized = await self._acollection_exists(self.collection_name)

        if len(nodes) > 0 and not collection_initialized:
            await self._acreate_collection(
                collection_name=self.collection_name,
                vector_size=len(nodes[0].get_embedding()),
            )

        sparse_vector_name = await self.asparse_vector_name()
        points, ids = self._build_points(nodes, sparse_vector_name)

        await self._aclient.upload_points(
            collection_name=self.collection_name,
            points=points,
            batch_size=self.batch_size,
            parallel=self.parallel,
            max_retries=self.max_retries,
            wait=True,
        )

        return ids

delete

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

使用ref_doc_id删除节点。

Source code in llama_index/vector_stores/qdrant/base.py

    def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """使用ref_doc_id删除节点。

Args:
    ref_doc_id（str）：要删除的文档的doc_id。
"""
        self._client.delete(
            collection_name=self.collection_name,
            points_selector=rest.Filter(
                must=[
                    rest.FieldCondition(
                        key="doc_id", match=rest.MatchValue(value=ref_doc_id)
                    )
                ]
            ),
        )

adelete async

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

异步方法，使用ref_doc_id删除节点。

Source code in llama_index/vector_stores/qdrant/base.py

    async def adelete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """异步方法，使用ref_doc_id删除节点。

Args:
    ref_doc_id（str）：要删除的文档的doc_id。
"""
        await self._aclient.delete(
            collection_name=self.collection_name,
            points_selector=rest.Filter(
                must=[
                    rest.FieldCondition(
                        key="doc_id", match=rest.MatchValue(value=ref_doc_id)
                    )
                ]
            ),
        )

delete_nodes

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

使用node_ids删除节点。

Source code in llama_index/vector_stores/qdrant/base.py

    def delete_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
        **delete_kwargs: Any,
    ) -> None:
        """使用node_ids删除节点。

Args:
    node_ids（可选[List[str]）：要删除的节点ID列表。
    filters（可选[MetadataFilters]）：要应用的元数据过滤器。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        self._client.delete(
            collection_name=self.collection_name,
            points_selector=filter,
        )

adelete_nodes async

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

异步方法，使用节点ID删除节点。

Source code in llama_index/vector_stores/qdrant/base.py

    async def adelete_nodes(
        self,
        node_ids: Optional[List[str]] = None,
        filters: Optional[MetadataFilters] = None,
        **delete_kwargs: Any,
    ) -> None:
        """异步方法，使用节点ID删除节点。

Args:
    node_ids（可选[List[str]）：要删除的节点ID列表。
    filters（可选[MetadataFilters]）：要应用的元数据过滤器。
"""
        should = []
        if node_ids is not None:
            should = [
                HasIdCondition(
                    has_id=node_ids,
                )
            ]

        if filters is not None:
            filter = self._build_subfilter(filters)
            if filter.should is None:
                filter.should = should
            else:
                filter.should.extend(should)
        else:
            filter = Filter(should=should)

        await self._aclient.delete(
            collection_name=self.collection_name,
            points_selector=filter,
        )

clear

clear() -> None

清空索引。

Source code in llama_index/vector_stores/qdrant/base.py

def clear(self) -> None:
    """
    清空索引。
    """
    self._client.delete_collection(collection_name=self.collection_name)
    self._collection_initialized = False

aclear async

aclear() -> None

异步清除索引的方法。

Source code in llama_index/vector_stores/qdrant/base.py

async def aclear(self) -> None:
    """
    异步清除索引的方法。
    """
    await self._aclient.delete_collection(collection_name=self.collection_name)
    self._collection_initialized = False

query

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

查询索引以获取前k个最相似的节点。

Source code in llama_index/vector_stores/qdrant/base.py

    def query(
        self,
        query: VectorStoreQuery,
        **kwargs: Any,
    ) -> VectorStoreQueryResult:
        """查询索引以获取前k个最相似的节点。

Args:
    query（VectorStoreQuery）：查询
"""
        query_embedding = cast(List[float], query.query_embedding)
        #  NOTE: users can pass in qdrant_filters (nested/complicated filters) to override the default MetadataFilters
        qdrant_filters = kwargs.get("qdrant_filters")
        if qdrant_filters is not None:
            query_filter = qdrant_filters
        else:
            query_filter = cast(Filter, self._build_query_filter(query))

        if query.mode == VectorStoreQueryMode.HYBRID and not self.enable_hybrid:
            raise ValueError(
                "Hybrid search is not enabled. Please build the query with "
                "`enable_hybrid=True` in the constructor."
            )
        elif (
            query.mode == VectorStoreQueryMode.HYBRID
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = self._client.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=self.sparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            # sanity check
            assert len(sparse_response) == 2
            assert self._hybrid_fusion_fn is not None

            # flatten the response
            return self._hybrid_fusion_fn(
                self.parse_to_query_result(sparse_response[0]),
                self.parse_to_query_result(sparse_response[1]),
                # NOTE: only for hybrid search (0 for sparse search, 1 for dense search)
                alpha=query.alpha or 0.5,
                # NOTE: use hybrid_top_k if provided, otherwise use similarity_top_k
                top_k=query.hybrid_top_k or query.similarity_top_k,
            )
        elif (
            query.mode == VectorStoreQueryMode.SPARSE
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = self._client.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=self.sparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )
            return self.parse_to_query_result(sparse_response[0])

        elif self.enable_hybrid:
            # search for dense vectors only
            response = self._client.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            return self.parse_to_query_result(response[0])
        else:
            response = self._client.search(
                collection_name=self.collection_name,
                query_vector=query_embedding,
                limit=query.similarity_top_k,
                query_filter=query_filter,
            )
            return self.parse_to_query_result(response)

aquery async

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

异步方法，用于查询前 k 个最相似节点的索引。

Parameters:

Name	Type	Description	Default
query	VectorStoreQuery	查询	required

Source code in llama_index/vector_stores/qdrant/base.py

    async def aquery(
        self, query: VectorStoreQuery, **kwargs: Any
    ) -> VectorStoreQueryResult:
        """异步方法，用于查询前 k 个最相似节点的索引。

Args:
    query (VectorStoreQuery): 查询
"""
        query_embedding = cast(List[float], query.query_embedding)

        #  NOTE: users can pass in qdrant_filters (nested/complicated filters) to override the default MetadataFilters
        qdrant_filters = kwargs.get("qdrant_filters")
        if qdrant_filters is not None:
            query_filter = qdrant_filters
        else:
            # build metadata filters
            query_filter = cast(Filter, self._build_query_filter(query))

        if query.mode == VectorStoreQueryMode.HYBRID and not self.enable_hybrid:
            raise ValueError(
                "Hybrid search is not enabled. Please build the query with "
                "`enable_hybrid=True` in the constructor."
            )
        elif (
            query.mode == VectorStoreQueryMode.HYBRID
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = await self._aclient.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=await self.asparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            # sanity check
            assert len(sparse_response) == 2
            assert self._hybrid_fusion_fn is not None

            # flatten the response
            return self._hybrid_fusion_fn(
                self.parse_to_query_result(sparse_response[0]),
                self.parse_to_query_result(sparse_response[1]),
                alpha=query.alpha or 0.5,
                # NOTE: use hybrid_top_k if provided, otherwise use similarity_top_k
                top_k=query.hybrid_top_k or query.similarity_top_k,
            )
        elif (
            query.mode == VectorStoreQueryMode.SPARSE
            and self.enable_hybrid
            and self._sparse_query_fn is not None
            and query.query_str is not None
        ):
            sparse_indices, sparse_embedding = self._sparse_query_fn(
                [query.query_str],
            )
            sparse_top_k = query.sparse_top_k or query.similarity_top_k

            sparse_response = await self._aclient.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedSparseVector(
                            # Dynamically switch between the old and new sparse vector name
                            name=await self.asparse_vector_name(),
                            vector=rest.SparseVector(
                                indices=sparse_indices[0],
                                values=sparse_embedding[0],
                            ),
                        ),
                        limit=sparse_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )
            return self.parse_to_query_result(sparse_response[0])
        elif self.enable_hybrid:
            # search for dense vectors only
            response = await self._aclient.search_batch(
                collection_name=self.collection_name,
                requests=[
                    rest.SearchRequest(
                        vector=rest.NamedVector(
                            name=DENSE_VECTOR_NAME,
                            vector=query_embedding,
                        ),
                        limit=query.similarity_top_k,
                        filter=query_filter,
                        with_payload=True,
                    ),
                ],
            )

            return self.parse_to_query_result(response[0])
        else:
            response = await self._aclient.search(
                collection_name=self.collection_name,
                query_vector=query_embedding,
                limit=query.similarity_top_k,
                query_filter=query_filter,
            )

            return self.parse_to_query_result(response)

parse_to_query_result

parse_to_query_result(
    response: List[Any],
) -> VectorStoreQueryResult

将向量存储响应转换为VectorStoreQueryResult。

Parameters:

Name	Type	Description	Default
response	List[Any]	List[Any]: 从向量存储返回的结果列表。	required

Source code in llama_index/vector_stores/qdrant/base.py

    def parse_to_query_result(self, response: List[Any]) -> VectorStoreQueryResult:
        """将向量存储响应转换为VectorStoreQueryResult。

Args:
    response: List[Any]: 从向量存储返回的结果列表。
"""
        nodes = []
        similarities = []
        ids = []

        for point in response:
            payload = cast(Payload, point.payload)
            try:
                node = metadata_dict_to_node(payload)
            except Exception:
                metadata, node_info, relationships = legacy_metadata_dict_to_node(
                    payload
                )

                node = TextNode(
                    id_=str(point.id),
                    text=payload.get("text"),
                    metadata=metadata,
                    start_char_idx=node_info.get("start", None),
                    end_char_idx=node_info.get("end", None),
                    relationships=relationships,
                )
            nodes.append(node)
            ids.append(str(point.id))
            try:
                similarities.append(point.score)
            except AttributeError:
                # certain requests do not return a score
                similarities.append(1.0)

        return VectorStoreQueryResult(nodes=nodes, similarities=similarities, ids=ids)