f3fi.dZddlZddlZddlmZddlmZddlmZeje 5ddl Z dddGddeeZ Gdd eeZy#1swY"xYw) zAModule contains a few fake embedding models for testing purposes.N) BaseModel)override) Embeddingsc|eZdZUdZeed< deefdZe dee deeefdZ e de deefdZ y ) FakeEmbeddingsa*Fake embedding model for unit testing purposes. This embedding model creates embeddings by sampling from a normal distribution. !!! danger "Toy model" Do not use this outside of testing, as it is not a real embedding model. Instantiate: ```python from langchain_core.embeddings import FakeEmbeddings embed = FakeEmbeddings(size=100) ``` Embed single text: ```python input_text = "The meaning of life is 42" vector = embed.embed_query(input_text) print(vector[:3]) ``` ```python [-0.700234640213188, -0.581266257710429, -1.1328482266445354] ``` Embed multiple texts: ```python input_texts = ["Document 1...", "Document 2..."] vectors = embed.embed_documents(input_texts) print(len(vectors)) # The first 3 coordinates for the first vector print(vectors[0][:3]) ``` ```python 2 [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257] ``` sizereturncttjjj |j SN)r)listnprandom default_rngnormalr)selfs \/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_core/embeddings/fake.py_get_embeddingzFakeEmbeddings._get_embedding:s,BII))+22 2BCCtextscH|Dcgc]}|jc}Scc}wNrrr_s rembed_documentszFakeEmbeddings.embed_documents=s/45!##%555stextc"|jSrrrrs r embed_queryzFakeEmbeddings.embed_queryAs""$$rN) __name__ __module__ __qualname____doc__int__annotations__r floatrrstrrrrrrrsy$L I+DU D6T#Y64U 3D66%%U %%rrceZdZUdZeed< dedeefdZe de defdZ e dee deeefd Z e de deefd Zy ) DeterministicFakeEmbeddinga~Deterministic fake embedding model for unit testing purposes. This embedding model creates embeddings by sampling from a normal distribution with a seed based on the hash of the text. !!! danger "Toy model" Do not use this outside of testing, as it is not a real embedding model. Instantiate: ```python from langchain_core.embeddings import DeterministicFakeEmbedding embed = DeterministicFakeEmbedding(size=100) ``` Embed single text: ```python input_text = "The meaning of life is 42" vector = embed.embed_query(input_text) print(vector[:3]) ``` ```python [-0.700234640213188, -0.581266257710429, -1.1328482266445354] ``` Embed multiple texts: ```python input_texts = ["Document 1...", "Document 2..."] vectors = embed.embed_documents(input_texts) print(len(vectors)) # The first 3 coordinates for the first vector print(vectors[0][:3]) ``` ```python 2 [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257] ``` rseedr ctjj|}t|j |j Sr )r rrr rr)rr+rngs rrz)DeterministicFakeEmbedding._get_embeddingqs0ii##D)CJJDIIJ.//rrcttj|jdj ddzS)z@Get a seed for the random generator, using the hash of the text.zutf-8i)r$hashlibsha256encode hexdigest)rs r _get_seedz$DeterministicFakeEmbedding._get_seedvs17>>$++g"67AACRH5PPrrcj|Dcgc]#}|j|j|%c}Scc}wN)r+rr4rs rrz*DeterministicFakeEmbedding.embed_documents{s-EJK##):#;KKKs(0cD|j|j|Sr6r7rs rrz&DeterministicFakeEmbedding.embed_querys""t(<"==rN)r r!r"r#r$r%r r&r staticmethodr'r4rrrr(rrr*r*Fs%N I+0304;0 QQQQLT#YL4U 3DLL>>U >>rr*)r# contextlibr0pydanticrtyping_extensionsrlangchain_core.embeddingsrsuppress ImportErrornumpyr rr*r(rrrAs_G&0Z%3%Z3%l;>Y;>us AA