Zi_NddlmZmZmZmZmZddlmZmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZddlmZddlmZddlmZerddl m!Z!Gdded Z"d S) ) TYPE_CHECKINGOptionalUnionListcast)URICollectionMetadata Embedding PyEmbeddingIncludeIndexingStatusMetadataDocumentImageWhereIDs GetResult QueryResultID OneOrMany ReadLevel WhereDocument SearchResultmaybe_cast_one_to_many)CollectionCommon)UpdateCollectionConfiguration)Search)AsyncServerAPIceZdZ d'deedeeeeeefdeee deee deee deee ddfd Z defd Zdefd Zdddddddgfdeeed eed eedeedeededefdZd(d edefdZddddddddgdf deeeeeefdeee deee deee deeeded eedeededefdZ d)deedeedeeddfdZdeddfd Zej fd!ee!d"ede"fd#Z# d'deedeeeeeefdeee deee deee deee ddfd$Z$ d'deedeeeeeefdeee deee deee deee ddfd%Z% d)dee&d eedeeddfd&Z'dS)*AsyncCollectionNids embeddings metadatas documentsimagesurisreturnc K|||||||}|j|j|d|d|d|d|d|j|jd{VdS) 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 `/root/projects/butler/venv/lib64/python3.11/site-packages/chromadb/api/models/AsyncCollection.pyaddzAsyncCollection.add"sD<<! =  l'E""<0!+.!+.V$;]   cjK|j|j|j|jd{VS)zThe total number of embeddings added to the database Returns: int: The total number of embeddings added to the database r+r,r-N)r/_countr1r,r-r2s r4countzAsyncCollection.countXsT\((';])         r6cjK|j|j|j|jd{VS)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 r8N)r/_get_indexing_statusr1r,r-r:s r4get_indexing_statusz#AsyncCollection.get_indexing_statusesT\66';]7         r6wherelimitoffsetwhere_documentincludec K|||||}|j|j|d|d|d|d|||j|j d{V}|||dS) 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!r?rBrCr!r?rBrC) r+r!r?rBrCr@rAr,r-NresponserC)!_validate_and_prepare_get_requestr/_getr1r,r-_transform_get_response) r2r!r?r@rArBrC get_request get_resultss r4getzAsyncCollection.getus0<<) =  !L--'E"g&&'78 *;].         ++ +i*@,   r6 cK||j|j||j|jd{VS)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_responser/_peekr1r,r-)r2r@s r4peekzAsyncCollection.peeksj,,,$$"g{ %         r6)r#r$ distancesquery_embeddings query_texts query_images query_uris n_resultsc 4K||||||||||  } |j|j| d| d| d| d| d| d|j|j d {V} || | d S) 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. `{"$contains": "hello"}`. Optional. include: A list of what to include in the results. Can contain `"embeddings"`, `"metadatas"`, `"documents"`, `"distances"`. Ids are always included. Defaults to `["metadatas", "documents", "distances"]`. Optional. Returns: QueryResult: A QueryResult object containing the results. Raises: ValueError: If you don't provide either query_embeddings, query_texts, or query_images ValueError: If you provide both query_embeddings and query_texts ValueError: If you provide both query_embeddings and query_images ValueError: If you provide both query_texts and query_images ) rTrUrVrWr!rXr?rBrCr!r"rXr?rBrC) r+r!rTrXr?rBrCr,r-NrE)#_validate_and_prepare_query_requestr/_queryr1r,r-_transform_query_response) r2rTrUrVrWr!rXr?rBrC query_request query_resultss r4queryzAsyncCollection.querysX@@-#%!)A   #l11'e$*<8#K0(()9:!),;]2         --"M),D.   r6namemetadata configurationcK|||j|j||||j|jd{V||||dS)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 )r1new_name new_metadatanew_configurationr,r-N)_validate_modify_requestr/_modifyr1r,r-"_update_model_after_modify_success)r2r`rarbs r4modifyzAsyncCollection.modifys %%h/// l""w!+;] #          //h NNNNNr6rdcK|j|j||j|jd{V}t |j||j|jS)aFork the current collection under a new name. The returning collection should contain identical data to the current collection. This is an experimental API that 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+rdr,r-N)clientmodelembedding_function data_loader)r/_forkr1r,r-r _embedding_function _data_loader)r2rdrms r4forkzAsyncCollection.forksl((';] )         <#7)     r6searches read_levelcKt|}|g}fd|D}jjt t t |jj|d{VS)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. 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) Nc:g|]}|S)_embed_search_string_queries).0searchr2s r4 z*AsyncCollection.search..s4   :@D - -f 5 5   r6)r+rtr,r-ru) rr/_searchr1rrrr,r-)r2rtru searches_listembedded_searchess` r4r{zAsyncCollection.search8sP/x88  M    DQ   \))'$v,(9::;]! *         r6c K|||||||}|j|j|d|d|d|d|d|j|jd{VdS) aUpdate the embeddings, metadatas or documents for provided ids. Args: ids: The ids of the embeddings to update embeddings: The embeddings to update. If None, embeddings will be computed based on the documents or images using the embedding_function set for the Collection. Optional. metadatas: The metadata to associate with the embeddings. When querying, you can filter on this metadata. Optional. documents: The documents to associate with the embeddings. Optional. images: The images to associate with the embeddings. Optional. Returns: None r)r!r"r#r$r&r*N)$_validate_and_prepare_update_requestr/_updater1r,r-)r2r!r"r#r$r%r&update_requests r4updatezAsyncCollection.update2BB! C  l""'u%%l3$[1$[1';]#   r6c K|||||||}|j|j|d|d|d|d|d|j|jd{VdS) 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_requestr/_upsertr1r,r-)r2r!r"r#r$r%r&upsert_requests r4upsertzAsyncCollection.upsertrr6cK||||}|j|j|d|d|d|j|jd{VdS)a0Delete the embeddings based on ids and/or a where filter Args: ids: The ids of the embeddings to delete where: A Where type dict used to filter the delection by. E.g. `{"$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. Returns: None Raises: ValueError: If you don't provide either ids, where, or where_document r!r?rB)r+r!r?rBr,r-N)$_validate_and_prepare_delete_requestr/_deleter1r,r-)r2r!r?rBdelete_requests r4deletezAsyncCollection.deletes&BB   l""'u% ))*:;;] #           r6)NNNNN)rM)NNN)(__name__ __module__ __qualname__rrrrr r rrrrr5intr;r r>rrr rrLrRrr_strr rrjrsr INDEX_AND_WALrrr{rrrrrxr6r4r r !sg 3737-1)-4 4 r]4  )$+&(  4 Ih/04 Ih/04 5)*4 y~&4  4 4 4 4 l  S      >    $(,!%# $26'5- - im $- - } -  - !/ - -  - - - - ^   Y    2 5937/3'+!%26   F F " )$+&(  F i12F y/0F Ys^,F im $F F F !/F F ( )F F F F T#15AE OOsmO-.O => O  OOOO@       :!* 7W W F#W W   W W W W B 3737-1)-+ + r]+  )$+&(  + Ih/0+ Ih/0+ 5)*+ y~&+  + + + + j 3737-1)-+ + r]+  )$+&(  + Ih/0+ Ih/0+ 5)*+ y~&+  + + + + ^"!%26   c]  !/         r6r rN)#typingrrrrrchromadb.api.typesrr r r r r rrrrrrrrrrrrr$chromadb.api.models.CollectionCommonr%chromadb.api.collection_configurationr"chromadb.execution.expression.planr chromadb.apirr rxr6r4rs==============,BAAAAAOOOOOO555555,++++++h h h h h &'78h h h h h r6