sentence-transformers How to use dhruvnayee/test_help_text with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("dhruvnayee/test_help_text")
sentences = [
"Under what conditions is the default start position of 1 used for a dimension in the resulting array?",
"Array variables example 3: Variable Unit_Prices\n\nInheritance of dimension start position and index values in numerical\nexpressions.\n\nThe following non-aggregating non-portfolio 1-dimensional array currency variables are defined in\nthe assumption set Assumption_Set (in all cases the dimension name is Fund and it has character\nindex values):\n\n | Dimension properties | \nVariable | Size | Start\n position | Indices | Array elements\nUnit_Prices | 3 | 101 | \"A\", \"B\", \"C\" | 1.25, 0.93, 1.81\nUnit_Prices_2 | 3 | 101 | \"A\", \"B\", \"C\" | 1.21, 0.97, 1.73\nUnit_Prices_3 | 3 | 201 | \"A\", \"B\", \"C\" | 1.32, 0.79, 1.35\nUnit_Prices_4 | 3 | 101 | \"X\", \"Y\", \"Z\" | 1.12, 0.89, 1.97\nUnit_Prices_5 | 2 | 102 | \"B\", \"C\" | 0.93, 1.93\nUnit_Prices_6 | 3 | 201 | \"X\", \"Y\", \"Z\" | 1.19, 0.98, 1.95\n\nThese variables are used in the formula of the following variables in the program Program in the\nprojection process Projection_Process, which is used in the model Array_Model (all these variables\nhave a single dimension called Fund):\n\n | | Dimension properties | \nVariable | Formula | Size | Start position | Indices | Array elements\nVariable_21 | Unit_Prices - Unit_Prices_2 | 3 | 101 | \"A\", \"B\", \"C\" | 0.04, -0.04, 0.08\nVariable_22 | Unit_Prices - Unit_Prices_3 | 3 | 1 | \"A\", \"B\", \"C\" | -0.07, 0.14, 0.46\nVariable_23 | Unit_Prices - Unit_Prices_4 | 3 | 101 | (undefined) | 0.13, 0.04, -0.16\nVariable_24 | Unit_Prices[<Fund.index= \"B\" : \"C\">] - Unit_Prices_5 | 2 | 102 | (undefined) | 0, -0.12\nVariable_25 | Unit_Prices - Unit_Prices_6 | 3 | 1 | (undefined) | 0.06, -0.05, -0.14\n\nNotes:\n\n* The rank of the arrays (number of dimensions), dimension names and dimension sizes must be\nidentical for such numerical expressions to be valid.\n* If the indices in a particular dimension are the same in both arrays, they will be inherited by\nthe resulting array, otherwise no indices will be defined in that dimension.\n* If the start positions in a particular dimension are the same in both arrays, they will be\ninherited by the resulting array, otherwise the default start position of 1 will be used in that\ndimension.\n* We could not have a formula like Unit_Prices - Unit_Prices_5, because these arrays have\ndifferently sized dimensions.\n* The subset of an array variable in the formula of Variable_24 loses its indices. This means that\nVariable_24 cannot inherit consistent indices and so none are defined for it.\n* The subset of an array variable in the formula of Variable_24 inherits the numbering of its\nelement positions from the variable Unit_Prices, so its start position is set to 102. This is the\nsame as the start position of Unit_Prices_5, so Variable_24 has its dimension start position set to\n102.",
"## Examples\n\nSuppose:\n\nVariable is a 2-dimensional array\n\n | Dimension name | Size | Start position\n1 | Dimension_1 | 2 | 4\n2 | Dimension_2 | 3 | 7\n\nDimension_2 | Dimension_1\nPosition = 4 | Position = 5\nPosition = 7 | 1 | 2\nPosition = 8 | 3 | 4\nPosition = 9 | 5 | 6\n\nThen:\n\nDimension_Start(Variable, <Dimension_1>)\n\n= 4\n\nDimension_Start(Variable, <Dimension_2>)\n\n= 7",
"## Other situations where indices are lost\n\nThere are a number of other circumstances where the indices for an array dimension are lost:\n\n* If an array has a changeable dimension and the array is aggregated acrosseventsusing the.totalextension, the indices in\nthat dimension will be lost.\n* If an array has a changeable dimension and the array is passed from a sub layer to a calling\nlayer then the indices in that dimension will be lost.\n* If an array has a changeable dimension and the array is calculated in a stochastic return value\nvariable then the indices in that dimension will be lost."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
