lQjTddlmZmZmZmZmZddlmZmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZmZddlmZddlmZddlm Z erddl!m"Z"Gdded Z#y ) ) TYPE_CHECKINGOptionalUnionListcast)URICollectionMetadata Embedding PyEmbeddingIncludeIndexingStatusMetadataDocumentImageWhereIDs GetResult QueryResultID OneOrMany ReadLevel WhereDocument SearchResult DeleteResultmaybe_cast_one_to_many)CollectionCommon)UpdateCollectionConfiguration)Search)AsyncServerAPIceZdZ d(deedeeeeeefdeee deee deee deee ddfd Z ejfd edefd Zdefd Zdddddddgfdeeed eedeedeedeededefdZd)dedefdZddddddddgdf deeeeeefdeee deee deee deeeded eedeededefdZ d*deedeedeeddfdZd eddfd!Z defd"Z!ejfd#ee"d ede#fd$Z$ d(deedeeeeeefdeee deee deee deee ddfd%Z% d(deedeeeeeefdeee deee deee deee ddfd&Z& d+dee'd eedeedeede(f d'Z)y),AsyncCollectionNids embeddings metadatas documentsimagesurisreturnc K|j||||||}|jj|j|d|d|d|d|d|j|j d{y7w) a]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 r"r#r$r%r&r'r"r#r$r%r' collection_idr"r#r$r%r'tenantdatabaseN)!_validate_and_prepare_add_request_client_addidr-r.)selfr"r#r$r%r&r' add_requests h/home/oem/CyberBrain26-unified/.venv/lib/python3.12/site-packages/chromadb/api/models/AsyncCollection.pyaddzAsyncCollection.add#sD<<! = ll''E""<0!+.!+.V$;;]]  A+A5-A3.A5 read_levelcK|jj|j|j|j|d{S7w)aReturn the number of records in the collection. Args: read_level: Controls whether to read from the write-ahead log (WAL): - ReadLevel.INDEX_AND_WAL: Read from both the compacted index and WAL (default). All committed writes will be visible. - ReadLevel.INDEX_ONLY: Read only from the compacted index, skipping the WAL. Faster, but recent writes that haven't been compacted may not be visible. - ReadLevel.INDEX_AND_BOUNDED_WAL: Read from the index and up to a server-configured number of WAL entries for bounded query latency. Returns: int: The total number of embeddings added to the database )r,r-r.r8N)r0_countr2r-r.)r3r8s r5countzAsyncCollection.countYsF\\(('';;]]! )    sAA AA cK|jj|j|j|jd{S7w)aGet the indexing status of this collection. Returns: IndexingStatus: An object containing: - num_indexed_ops: Number of user operations that have been indexed - num_unindexed_ops: Number of user operations pending indexing - total_ops: Total number of user operations in collection - op_indexing_progress: Proportion of user operations that have been indexed as a float between 0 and 1 r,r-r.N)r0_get_indexing_statusr2r-r.r3s r5get_indexing_statusz#AsyncCollection.get_indexing_statusosC\\66'';;]]7    AA AA wherelimitoffsetwhere_documentincludec K|j||||}|jj|j|d|d|d|d|||j|j  d{}|j ||dS7w) aGet embeddings and their associate data from the data store. If no ids or where filter is provided returns all embeddings up to limit starting at offset. Args: ids: The ids of the embeddings to get. Optional. where: A Where type dict used to filter results by. E.g. `{"$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": "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. )r"rBrErFr"rBrErF) r,r"rBrErFrCrDr-r.NresponserF)!_validate_and_prepare_get_requestr0_getr2r-r._transform_get_response) r3r"rBrCrDrErF get_request get_resultss r5getzAsyncCollection.gets0<<) = !LL--''E"g&&'78 *;;]].   ++ +i*@,    sA'B)B*B cK|j|jj|j||j|j d{S7w)zGet 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. )r,nr-r.N)_transform_peek_responser0_peekr2r-r.)r3rCs r5peekzAsyncCollection.peeksT,,,,$$"gg{{ %    sA AA A)r$r% distancesquery_embeddings query_texts query_images query_uris n_resultsc &K|j|||||||||  } |jj|j| d| d| d| d| d| d|j|j  d {} |j | | d S7w) aGet the n_results nearest neighbor embeddings for provided query_embeddings or query_texts. Args: query_embeddings: The embeddings to get the closes neighbors of. Optional. query_texts: The document texts to get the closes neighbors of. Optional. query_images: The images to get the closes neighbors of. Optional. ids: A subset of ids to search within. Optional. n_results: The number of neighbors to return for each query_embedding or query_texts. Optional. where: A Where type dict used to filter results by. E.g. `{"$and": [{"color" : "red"}, {"price": {"$gte": 4.20}}]}`. Optional. where_document: A WhereDocument type dict used to filter by the documents. E.g. `{"$contains": "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 ) rWrXrYrZr"r[rBrErFr"r#r[rBrErF) r,r"rWr[rBrErFr-r.NrH)#_validate_and_prepare_query_requestr0_queryr2r-r._transform_query_response) r3rWrXrYrZr"r[rBrErF query_request query_resultss r5queryzAsyncCollection.querysX@@-#%!)A  #ll11''e$*<8#K0(()9:!),;;]]2   --"M),D.    sA2B4B5Bnamemetadata configurationcK|j||jj|j||||j|j d{|j |||y7w)zModify the collection name or metadata Args: name: The updated name for the collection. Optional. metadata: The updated metadata for the collection. Optional. Returns: None )r2new_name new_metadatanew_configurationr-r.N)_validate_modify_requestr0_modifyr2r-r."_update_model_after_modify_success)r3rcrdres r5modifyzAsyncCollection.modifysp %%h/ ll""ww!+;;]] #    //h N sAA1A/A1rgcK|jj|j||j|jd{}t |j||j |jS71w)aFork the current collection under a new name. The returning collection should contain identical data to the current collection. This only works for Hosted Chroma for now. Args: new_name: The name of the new collection. Returns: Collection: A new collection with the specified name and containing identical data to the current collection. )r,rgr-r.N)clientmodelembedding_function data_loader)r0_forkr2r-r.r!_embedding_function _data_loader)r3rgrps r5forkzAsyncCollection.fork(snll(('';;]] )   <<#77))    sAA7A52A7cK|jj|j|j|jd{S7w)zGet the number of forks that exist for this collection. This only works for Hosted Chroma for now. Returns: int: The number of forks for this collection. r=N)r0 _fork_countr2r-r.r?s r5 fork_countzAsyncCollection.fork_countBsC\\--'';;]].    rAsearchesc(Kt|}|g}|Dcgc]}|j|}}|jj|jt t t||j|j|d{Scc}w7 w)a Perform hybrid search on the collection. This is an experimental API that only works for Hosted Chroma for now. Args: searches: A single Search object or a list of Search objects, each containing: - where: Where expression for filtering - rank: Ranking expression for hybrid search (defaults to Val(0.0)) - limit: Limit configuration for pagination (defaults to no limit) - select: Select configuration for keys to return (defaults to empty) read_level: Controls whether to read from the write-ahead log (WAL): - ReadLevel.INDEX_AND_WAL: Read from both the compacted index and WAL (default). All committed writes will be visible. - ReadLevel.INDEX_ONLY: Read only from the compacted index, skipping the WAL. Faster, but recent writes that haven't been compacted may not be visible. - ReadLevel.INDEX_AND_BOUNDED_WAL: Read from the index and up to a server-configured number of WAL entries for bounded query latency. Returns: SearchResult: Column-major format response with: - ids: List of result IDs for each search payload - documents: Optional documents for each payload - embeddings: Optional embeddings for each payload - metadatas: Optional metadata for each payload - scores: Optional scores for each payload - select: List of selected keys for each payload Raises: NotImplementedError: For local/segment API implementations Examples: # Using builder pattern with Key constants from chromadb.execution.expression import ( Search, Key, K, Knn, Val ) # Note: K is an alias for Key, so K.DOCUMENT == Key.DOCUMENT search = (Search() .where((K("category") == "science") & (K("score") > 0.5)) .rank(Knn(query=[0.1, 0.2, 0.3]) * 0.8 + Val(0.5) * 0.2) .limit(10, offset=0) .select(K.DOCUMENT, K.SCORE, "title")) # Direct construction from chromadb.execution.expression import ( Search, Eq, And, Gt, Knn, Limit, Select, Key ) search = Search( where=And([Eq("category", "science"), Gt("score", 0.5)]), rank=Knn(query=[0.1, 0.2, 0.3]), limit=Limit(offset=0, limit=10), select=Select(keys={Key.DOCUMENT, Key.SCORE, "title"}) ) # Single search result = await collection.search(search) # Multiple searches at once searches = [ Search().where(K("type") == "article").rank(Knn(query=[0.1, 0.2])), Search().where(K("type") == "paper").rank(Knn(query=[0.3, 0.4])) ] results = await collection.search(searches) # Skip WAL for faster queries (may miss recent uncommitted writes) from chromadb.api.types import ReadLevel result = await collection.search(search, read_level=ReadLevel.INDEX_ONLY) N)r,rzr-r.r8) r_embed_search_string_queriesr0_searchr2rrrr-r.)r3rzr8 searches_listsearchembedded_searchess r5rzAsyncCollection.searchOsT/x8  MER :@D - -f 5  \\))''$v,(9:;;]]! *     sBB ABB Bc K|j||||||}|jj|j|d|d|d|d|d|j|j d{y7w) aUpdate 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 r*r"r#r$r%r'r+N)$_validate_and_prepare_update_requestr0_updater2r-r.)r3r"r#r$r%r&r'update_requests r5updatezAsyncCollection.update2BB! C ll""''u%%l3$[1$[1';;]]#  r7c K|j||||||}|jj|j|d|d|d|d|d|j|j d{y7w) aOUpdate the embeddings, metadatas or documents for provided ids, or create them if they don't exist. Args: ids: The ids of the embeddings to update embeddings: The embeddings to add. If None, embeddings will be computed based on the documents using the embedding_function set for the Collection. Optional. metadatas: The metadata to associate with the embeddings. When querying, you can filter on this metadata. Optional. documents: The documents to associate with the embeddings. Optional. Returns: None r*r"r#r$r%r'r+N)$_validate_and_prepare_upsert_requestr0_upsertr2r-r.)r3r"r#r$r%r&r'upsert_requests r5upsertzAsyncCollection.upsertrr7c K|j||||}|jj|j|d|d|d|d|j|j d{S7w)a1Delete 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. `{"$contains": "hello"}`. Optional. limit: Maximum number of records to delete. Can only be used with where or where_document filters. Returns: DeleteResult: A dict containing the number of records deleted. Raises: ValueError: If you don't provide either ids, where, or where_document ValueError: If limit is specified without a where or where_document clause. )rCr"rBrErC)r,r"rBrErCr-r.N)$_validate_and_prepare_delete_requestr0_deleter2r-r.)r3r"rBrErCdelete_requests r5deletezAsyncCollection.deletes,BB eC \\))''u% ))*:; );;]]*    sA%A.'A,(A.)NNNNN)rP)NNN)NNNN)*__name__ __module__ __qualname__rrrrr r rrrrr6r INDEX_AND_WALintr;r r@rrr rrOrUrrbstrr rrmrvryrrrrrrrrr5r!r!"s 3737-1)-4 r]4  )$+&(  4 Ih/04 Ih/04 5)*4 y~&4  4 l3<2I2I i c , > $(,!%# $26'5- im $- - } -  - !/ - -  - ^  Y 2 5937/3'+!%26 F " )$+&(  F i12F y/0F Ys^,F im $F F F !/F F ( )F T#15AE OsmO-.O => O  O@    4  #  !* 7 7Y F#Y Y   Y F 3737-1)-+ r]+  )$+&(  + Ih/0+ Ih/0+ 5)*+ y~&+  + j 3737-1)-+ r]+  )$+&(  + Ih/0+ Ih/0+ 5)*+ y~&+  + ^"!%26# " c]" " !/ " } "  " rr!rN)$typingrrrrrchromadb.api.typesrr r r r r rrrrrrrrrrrrrr$chromadb.api.models.CollectionCommonr%chromadb.api.collection_configurationr"chromadb.execution.expression.planr chromadb.apirr!rrr5rsP==.BO5+D &'78D r