昺h(ddlmZddlmZddlZddlZddlmZddlmZddl m Z m Z m Z m Z Gdd ejZdS) )Tensor)nnN)import_from_string) OrderedDict)ListDictUnionTupleceZdZd deeeejfdeffd Z deee ffdZ de fdZ d Zd eeeeeeefffd Zed ZxZS)AsymT sub_modulesallow_empty_keycN||_||_t}|D]J\}}t |t s|g}t |D]\}}|||dzt|z<Ktt| |dS)a This model allows to create asymmetric SentenceTransformer models, that apply different models depending on the specified input key. In the below example, we create two different Dense models for 'query' and 'doc'. Text that is passed as {'query': 'My query'} will be passed along along the first Dense model, and text that will be passed as {'doc': 'My document'} will use the other Dense model. Note, that when you call encode(), that only inputs of the same type can be encoded. Mixed-Types cannot be encoded. Example:: word_embedding_model = models.Transformer(model_name) pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension()) asym_model = models.Asym({'query': [models.Dense(word_embedding_model.get_word_embedding_dimension(), 128)], 'doc': [models.Dense(word_embedding_model.get_word_embedding_dimension(), 128)]}) model = SentenceTransformer(modules=[word_embedding_model, pooling_model, asym_model]) model.encode([{'query': 'Q1'}, {'query': 'Q2'}] model.encode([{'doc': 'Doc1'}, {'doc': 'Doc2'}] #You can train it with InputExample like this. Note, that the order must always be the same: train_example = InputExample(texts=[{'query': 'Train query'}, {'doc': 'Document'}], label=1) :param sub_modules: Dict in the format str -> List[models]. The models in the specified list will be applied for input marked with the respective key. :param allow_empty_key: If true, inputs without a key can be processed. If false, an exception will be thrown if no key is specified. -N) rrritems isinstancer enumeratestrsuperr __init__) selfrr ordered_dictnamemodelsidxmodel __class__s i/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/sentence_transformers/models/Asym.pyrz Asym.__init__ s2'."}} '--// < >C/$u++2FF). X&(,U (> H%%,,X6666  7 ,1133 # #OHek3x==AAJ K T 2 2 2 2 JJz " " " " "',,{M::C& Q Q Q UY I(!0#4d6J"K                       s=#E--E14E1textsc*t|dtstdd}|D]?}tt |\}}||}||ksJ@|j|d|S)z? Tokenizes a text and maps tokens to token-ids rzDAsym. model requires that texts are passed as dicts: {'key': 'text'}N)rdictAttributeErrornextiterrrtokenize)rrK module_keylookupr&texts rrQz Asym.tokenize]s%(D)) i !ghh h  * *F!$v||~~"6"677NHd!% z))))) +A.77>>>r cJttj|d5}t j|}dddn #1swxYwYi}|dD]L\}}t|}|tj||}|||<Mi}|dD]0\} } g|| <| D]#}|| ||$1t|fi|d} | S)Nr/r3r4r5) rAr<r=r>rBloadrrr;r ) input_pathfInconfigmodulesrH model_type module_classmodulerGkey_name models_listrs rrVz Asym.loadnsv "',,z=99 : : $cYs^^F $ $ $ $ $ $ $ $ $ $ $ $ $ $ $$*7O$9$9$;$; ' ' Hj-j99L!&&rw||J'I'IJJF &GH  %+K%8%>%>%@%@ D D !Hk(*OH %' D D)001BCCCC D_==|(<== sAAA)T)r9r: __qualname__r rrrModuleboolrrr'intr*r@r r rQ staticmethodrV __classcell__)rs@rr r s#1#1Dd29o)=$>#1QU#1#1#1#1#1#1JS&[ 1# :?eDItE#s(O/D$DE????"\r r )torchrrr<rButilr collectionsrtypingrr r r Sequentialr r rrls %%%%%%######++++++++++++vvvvv2=vvvvvr