Spaces:
Paused
Paused
| from typing import ( | |
| TYPE_CHECKING, | |
| Optional, | |
| Union, | |
| ) | |
| import numpy as np | |
| from chromadb.api.types import ( | |
| URI, | |
| CollectionMetadata, | |
| Embedding, | |
| Include, | |
| Metadata, | |
| Document, | |
| Image, | |
| Where, | |
| IDs, | |
| GetResult, | |
| QueryResult, | |
| ID, | |
| OneOrMany, | |
| WhereDocument, | |
| ) | |
| from chromadb.api.models.CollectionCommon import CollectionCommon | |
| if TYPE_CHECKING: | |
| from chromadb.api import AsyncServerAPI # noqa: F401 | |
| class AsyncCollection(CollectionCommon["AsyncServerAPI"]): | |
| async def add( | |
| self, | |
| ids: OneOrMany[ID], | |
| embeddings: Optional[ | |
| Union[ | |
| OneOrMany[Embedding], | |
| OneOrMany[np.ndarray], | |
| ] | |
| ] = None, | |
| metadatas: Optional[OneOrMany[Metadata]] = None, | |
| documents: Optional[OneOrMany[Document]] = None, | |
| images: Optional[OneOrMany[Image]] = None, | |
| uris: Optional[OneOrMany[URI]] = None, | |
| ) -> None: | |
| """Add embeddings to the data store. | |
| Args: | |
| ids: The ids of the embeddings you wish to add | |
| embeddings: The embeddings to add. If None, embeddings will be computed based on the documents or images using the embedding_function set for the Collection. Optional. | |
| metadatas: The metadata to associate with the embeddings. When querying, you can filter on this metadata. Optional. | |
| documents: The documents to associate with the embeddings. Optional. | |
| images: The images to associate with the embeddings. Optional. | |
| uris: The uris of the images to associate with the embeddings. Optional. | |
| Returns: | |
| None | |
| Raises: | |
| ValueError: If you don't provide either embeddings or documents | |
| ValueError: If the length of ids, embeddings, metadatas, or documents don't match | |
| ValueError: If you don't provide an embedding function and don't provide embeddings | |
| ValueError: If you provide both embeddings and documents | |
| ValueError: If you provide an id that already exists | |
| """ | |
| ( | |
| ids, | |
| embeddings, | |
| metadatas, | |
| documents, | |
| uris, | |
| ) = self._validate_and_prepare_embedding_set( | |
| ids, embeddings, metadatas, documents, images, uris | |
| ) | |
| await self._client._add(ids, self.id, embeddings, metadatas, documents, uris) | |
| async def count(self) -> int: | |
| """The total number of embeddings added to the database | |
| Returns: | |
| int: The total number of embeddings added to the database | |
| """ | |
| return await self._client._count(collection_id=self.id) | |
| async def get( | |
| self, | |
| ids: Optional[OneOrMany[ID]] = None, | |
| where: Optional[Where] = None, | |
| limit: Optional[int] = None, | |
| offset: Optional[int] = None, | |
| where_document: Optional[WhereDocument] = None, | |
| include: Include = ["metadatas", "documents"], | |
| ) -> GetResult: | |
| """Get embeddings and their associate data from the data store. If no ids or where filter is provided returns | |
| all embeddings up to limit starting at offset. | |
| Args: | |
| ids: The ids of the embeddings to get. Optional. | |
| where: A Where type dict used to filter results by. E.g. `{"$and": ["color" : "red", "price": {"$gte": 4.20}]}`. Optional. | |
| limit: The number of documents to return. Optional. | |
| offset: The offset to start returning results from. Useful for paging results with limit. Optional. | |
| where_document: A WhereDocument type dict used to filter by the documents. E.g. `{$contains: {"text": "hello"}}`. Optional. | |
| include: A list of what to include in the results. Can contain `"embeddings"`, `"metadatas"`, `"documents"`. Ids are always included. Defaults to `["metadatas", "documents"]`. Optional. | |
| Returns: | |
| GetResult: A GetResult object containing the results. | |
| """ | |
| ( | |
| valid_ids, | |
| valid_where, | |
| valid_where_document, | |
| valid_include, | |
| ) = self._validate_and_prepare_get_request(ids, where, where_document, include) | |
| get_results = await self._client._get( | |
| self.id, | |
| valid_ids, | |
| valid_where, | |
| None, | |
| limit, | |
| offset, | |
| where_document=valid_where_document, | |
| include=valid_include, | |
| ) | |
| return self._transform_get_response(get_results, valid_include) | |
| async def peek(self, limit: int = 10) -> GetResult: | |
| """Get the first few results in the database up to limit | |
| Args: | |
| limit: The number of results to return. | |
| Returns: | |
| GetResult: A GetResult object containing the results. | |
| """ | |
| return await self._client._peek(self.id, limit) | |
| async def query( | |
| self, | |
| query_embeddings: Optional[ | |
| Union[ | |
| OneOrMany[Embedding], | |
| OneOrMany[np.ndarray], | |
| ] | |
| ] = None, | |
| query_texts: Optional[OneOrMany[Document]] = None, | |
| query_images: Optional[OneOrMany[Image]] = None, | |
| query_uris: Optional[OneOrMany[URI]] = None, | |
| n_results: int = 10, | |
| where: Optional[Where] = None, | |
| where_document: Optional[WhereDocument] = None, | |
| include: Include = ["metadatas", "documents", "distances"], | |
| ) -> QueryResult: | |
| """Get the n_results nearest neighbor embeddings for provided query_embeddings or query_texts. | |
| Args: | |
| query_embeddings: The embeddings to get the closes neighbors of. Optional. | |
| query_texts: The document texts to get the closes neighbors of. Optional. | |
| query_images: The images to get the closes neighbors of. Optional. | |
| n_results: The number of neighbors to return for each query_embedding or query_texts. Optional. | |
| where: A Where type dict used to filter results by. E.g. `{"$and": ["color" : "red", "price": {"$gte": 4.20}]}`. Optional. | |
| where_document: A WhereDocument type dict used to filter by the documents. E.g. `{$contains: {"text": "hello"}}`. Optional. | |
| include: A list of what to include in the results. Can contain `"embeddings"`, `"metadatas"`, `"documents"`, `"distances"`. Ids are always included. Defaults to `["metadatas", "documents", "distances"]`. Optional. | |
| Returns: | |
| QueryResult: A QueryResult object containing the results. | |
| Raises: | |
| ValueError: If you don't provide either query_embeddings, query_texts, or query_images | |
| ValueError: If you provide both query_embeddings and query_texts | |
| ValueError: If you provide both query_embeddings and query_images | |
| ValueError: If you provide both query_texts and query_images | |
| """ | |
| ( | |
| valid_query_embeddings, | |
| valid_n_results, | |
| valid_where, | |
| valid_where_document, | |
| ) = self._validate_and_prepare_query_request( | |
| query_embeddings, | |
| query_texts, | |
| query_images, | |
| query_uris, | |
| n_results, | |
| where, | |
| where_document, | |
| include, | |
| ) | |
| query_results = await self._client._query( | |
| collection_id=self.id, | |
| query_embeddings=valid_query_embeddings, | |
| n_results=valid_n_results, | |
| where=valid_where, | |
| where_document=valid_where_document, | |
| include=include, | |
| ) | |
| return self._transform_query_response(query_results, include) | |
| async def modify( | |
| self, name: Optional[str] = None, metadata: Optional[CollectionMetadata] = None | |
| ) -> None: | |
| """Modify the collection name or metadata | |
| Args: | |
| name: The updated name for the collection. Optional. | |
| metadata: The updated metadata for the collection. Optional. | |
| Returns: | |
| None | |
| """ | |
| self._validate_modify_request(metadata) | |
| # Note there is a race condition here where the metadata can be updated | |
| # but another thread sees the cached local metadata. | |
| # TODO: fixme | |
| await self._client._modify(id=self.id, new_name=name, new_metadata=metadata) | |
| self._update_model_after_modify_success(name, metadata) | |
| async def update( | |
| self, | |
| ids: OneOrMany[ID], | |
| embeddings: Optional[ | |
| Union[ | |
| OneOrMany[Embedding], | |
| OneOrMany[np.ndarray], | |
| ] | |
| ] = None, | |
| metadatas: Optional[OneOrMany[Metadata]] = None, | |
| documents: Optional[OneOrMany[Document]] = None, | |
| images: Optional[OneOrMany[Image]] = None, | |
| uris: Optional[OneOrMany[URI]] = None, | |
| ) -> None: | |
| """Update the embeddings, metadatas or documents for provided ids. | |
| Args: | |
| ids: The ids of the embeddings to update | |
| embeddings: The embeddings to update. If None, embeddings will be computed based on the documents or images using the embedding_function set for the Collection. Optional. | |
| metadatas: The metadata to associate with the embeddings. When querying, you can filter on this metadata. Optional. | |
| documents: The documents to associate with the embeddings. Optional. | |
| images: The images to associate with the embeddings. Optional. | |
| Returns: | |
| None | |
| """ | |
| ( | |
| ids, | |
| embeddings, | |
| metadatas, | |
| documents, | |
| uris, | |
| ) = self._validate_and_prepare_update_request( | |
| ids, embeddings, metadatas, documents, images, uris | |
| ) | |
| await self._client._update(self.id, ids, embeddings, metadatas, documents, uris) | |
| async def upsert( | |
| self, | |
| ids: OneOrMany[ID], | |
| embeddings: Optional[ | |
| Union[ | |
| OneOrMany[Embedding], | |
| OneOrMany[np.ndarray], | |
| ] | |
| ] = None, | |
| metadatas: Optional[OneOrMany[Metadata]] = None, | |
| documents: Optional[OneOrMany[Document]] = None, | |
| images: Optional[OneOrMany[Image]] = None, | |
| uris: Optional[OneOrMany[URI]] = None, | |
| ) -> None: | |
| """Update the embeddings, metadatas or documents for provided ids, or create them if they don't exist. | |
| Args: | |
| ids: The ids of the embeddings to update | |
| embeddings: The embeddings to add. If None, embeddings will be computed based on the documents using the embedding_function set for the Collection. Optional. | |
| metadatas: The metadata to associate with the embeddings. When querying, you can filter on this metadata. Optional. | |
| documents: The documents to associate with the embeddings. Optional. | |
| Returns: | |
| None | |
| """ | |
| ( | |
| ids, | |
| embeddings, | |
| metadatas, | |
| documents, | |
| uris, | |
| ) = self._validate_and_prepare_upsert_request( | |
| ids, embeddings, metadatas, documents, images, uris | |
| ) | |
| await self._client._upsert( | |
| collection_id=self.id, | |
| ids=ids, | |
| embeddings=embeddings, | |
| metadatas=metadatas, | |
| documents=documents, | |
| uris=uris, | |
| ) | |
| async def delete( | |
| self, | |
| ids: Optional[IDs] = None, | |
| where: Optional[Where] = None, | |
| where_document: Optional[WhereDocument] = None, | |
| ) -> None: | |
| """Delete the embeddings based on ids and/or a where filter | |
| Args: | |
| ids: The ids of the embeddings to delete | |
| where: A Where type dict used to filter the delection by. E.g. `{"$and": ["color" : "red", "price": {"$gte": 4.20}]}`. Optional. | |
| where_document: A WhereDocument type dict used to filter the deletion by the document content. E.g. `{$contains: {"text": "hello"}}`. Optional. | |
| Returns: | |
| None | |
| Raises: | |
| ValueError: If you don't provide either ids, where, or where_document | |
| """ | |
| (ids, where, where_document) = self._validate_and_prepare_delete_request( | |
| ids, where, where_document | |
| ) | |
| await self._client._delete(self.id, ids, where, where_document) | |