Build records for Pinecone upsert.
Arguments:
embeddings
(List[List[float]]
): List of embeddings to upsert.routes
(List[str]
): List of routes to upsert.utterances
(List[str]
): List of utterances to upsert.function_schemas
(Optional[List[Dict[str, Any]]]
): List of function schemas to upsert.metadata_list
(List[Dict[str, Any]]
): List of metadata to upsert.List[List[float]]
0 (List[List[float]]
1): List of sparse embeddings to upsert.Returns:
List[List[float]]
2: List of records to upsert.
Additional metadata dictionary
Initialize PineconeRecord.
Arguments:
**data
(dict
): Keyword arguments to pass to the BaseModel constructor.Convert PineconeRecord to a dictionary.
Returns:
dict
: Dictionary representation of the PineconeRecord.
Initialize PineconeIndex.
Arguments:
api_key
(Optional[str]
): Pinecone API key.index_name
(str
): Name of the index.dimensions
(Optional[int]
): Dimensions of the index.metric
(str
): Metric of the index.cloud
(str
): Cloud provider of the index.Optional[str]
0 (str
): Region of the index.Optional[str]
2 (str
): Host of the index.Optional[str]
4 (Optional[str]
): Namespace of the index.Optional[str]
6 (Optional[str]
): Base URL of the Pinecone API.Optional[str]
8 (Optional[str]
9): Whether to initialize the index asynchronously.Add vectors to Pinecone in batches.
Arguments:
embeddings
(List[List[float]]
): List of embeddings to upsert.routes
(List[str]
): List of routes to upsert.utterances
(List[str]
): List of utterances to upsert.function_schemas
(Optional[List[Dict[str, Any]]]
): List of function schemas to upsert.metadata_list
(List[Dict[str, Any]]
): List of metadata to upsert.List[List[float]]
0 (List[List[float]]
1): Number of vectors to upsert in a single batch.List[List[float]]
2 (List[List[float]]
3): List of sparse embeddings to upsert.Add vectors to Pinecone in batches.
Arguments:
embeddings
(List[List[float]]
): List of embeddings to upsert.routes
(List[str]
): List of routes to upsert.utterances
(List[str]
): List of utterances to upsert.function_schemas
(Optional[List[Dict[str, Any]]]
): List of function schemas to upsert.metadata_list
(List[Dict[str, Any]]
): List of metadata to upsert.List[List[float]]
0 (List[List[float]]
1): Number of vectors to upsert in a single batch.List[List[float]]
2 (List[List[float]]
3): List of sparse embeddings to upsert.Delete specified route from index if it exists. Returns the IDs of the vectors
deleted.
Arguments:
route_name
(str
): Name of the route to delete.Returns:
list[str]
: List of IDs of the vectors deleted.
Asynchronously delete specified route from index if it exists. Returns the IDs
of the vectors deleted.
Arguments:
route_name
(str
): Name of the route to delete.Returns:
list[str]
: List of IDs of the vectors deleted.
Delete all routes from index if it exists.
Returns:
None
: None
Describe the index.
Returns:
IndexConfig
: IndexConfig
Checks if the index is ready to be used.
Returns:
bool
: True if the index is ready, False otherwise.
Search the index for the query vector and return the top_k results.
Arguments:
vector
(np.ndarray
): The query vector to search for.top_k
(int, optional
): The number of top results to return, defaults to 5.route_filter
(Optional[List[str]], optional
): A list of route names to filter the search results, defaults to None.sparse_vector
(Optional[SparseEmbedding]
): An optional sparse vector to include in the query.kwargs
(Any
): Additional keyword arguments for the query, including sparse_vector.Raises:
np.ndarray
0: If the index is not populated.Returns:
np.ndarray
1: A tuple containing an array of scores and a list of route names.
Asynchronously search the index for the query vector and return the top_k results.
Arguments:
vector
(np.ndarray
): The query vector to search for.top_k
(int, optional
): The number of top results to return, defaults to 5.route_filter
(Optional[List[str]], optional
): A list of route names to filter the search results, defaults to None.kwargs
(Any
): Additional keyword arguments for the query, including sparse_vector.sparse_vector
(Optional[dict]
): An optional sparse vector to include in the query.Raises:
np.ndarray
0: If the index is not populated.Returns:
np.ndarray
1: A tuple containing an array of scores and a list of route names.
Asynchronously get a list of route and utterance objects currently
stored in the index.
Returns:
List[Tuple]
: A list of (route_name, utterance) objects.
Delete the index.
Returns:
None
: None
Asynchronously delete the index.
Checks if class attributes exist to be used for async operations.
Arguments:
client_only
(bool, optional
): Whether to check only the client attributes. If False
attributes will be checked for both client and index operations. If True
only attributes for client operations will be checked. Defaults to False.Returns:
bool
: True if the class attributes exist, False otherwise.
Returns the total number of vectors in the index. If the index is not initialized
returns 0.
Returns:
int
: The total number of vectors.
Async version of len. Returns the total number of vectors in the index.
If the index is not initialized, initializes it first or returns 0.
Returns:
int
: The total number of vectors.