sentence-transformers How to use SQAI/bge-embedding-model2 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("SQAI/bge-embedding-model2")
sentences = [
"threshold.highLuxThreshold",
"\"Can you provide the timestamp of the last update to the threshold settings, and detail any faults in the lux module related to light level sensing and control for the streetlight on this specific street name? I also want to know the longitude of the streetlight. And also, can you tell me what type of dimming schedule is applied to the streetlight, the type of port used for its dimming controls, and the total energy it has consumed, recorded in kilowatt-hours. Lastly, could you also provide the timestamp of the recorded streetlighting error, and confirm the status of the relay responsible for turning this streetlight on and off, as I am suspecting it might be sticking?\"",
"\"Can you provide me with the unique streetlight identifier, upper lux level for managing light intensity, a brief description, and the delta or height of the grid area occupied by a group of streetlights? Also, can you note the AC voltage supply for these streetlights, any issues with communication related to their lux sensors, and the count of how many times each streetlight has been switched on? Please ensure that the data is constrained to just those that can be determined with the unique streetlight identifier I provided.\"",
"\"What was the last recorded data or action timestamp of the streetlight located at the specific longitude, and in which time zone is it situated? Could you also provide information on its default dimming level and the maximum power usage threshold above which indicates potential faults? Are there any identified faults in the lux module impacting light level sensing and control? Additionally, what are the minimum longitude and delta or height for the grid area occupied by this group of streetlights and could you specify the network time received from the central control for synchronization purposes?\""
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
