bge-multilingual-gemma2

git clone https://github.com/FlagOpen/FlagEmbedding.git
cd FlagEmbedding
pip install -e .

from FlagEmbedding import FlagLLMModel
queries = ["how much protein should a female eat", "summit define"]
documents = [
    "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
]
model = FlagLLMModel('BAAI/bge-multilingual-gemma2', 
                     query_instruction_for_retrieval="Given a web search query, retrieve relevant passages that answer the query.",
                     use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
embeddings_1 = model.encode_queries(queries)
embeddings_2 = model.encode_corpus(documents)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
# [[ 0.559     0.01654 ]
# [-0.002575  0.4998  ]]

from sentence_transformers import SentenceTransformer
import torch

# Load the model, optionally in float16 precision for faster inference
model = SentenceTransformer("BAAI/bge-multilingual-gemma2", model_kwargs={"torch_dtype": torch.float16})

# Prepare a prompt given an instruction
instruction = 'Given a web search query, retrieve relevant passages that answer the query.'
prompt = f'<instruct>{instruction}\n<query>'
# Prepare queries and documents
queries = [
    'how much protein should a female eat',
    'summit define',
]
documents = [
    "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
]

# Compute the query and document embeddings
query_embeddings = model.encode(queries, prompt=prompt)
document_embeddings = model.encode(documents)

# Compute the cosine similarity between the query and document embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.5591,  0.0164],
#         [-0.0026,  0.4993]], dtype=torch.float16)

import torch
import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel


def last_token_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
    if left_padding:
        return last_hidden_states[:, -1]
    else:
        sequence_lengths = attention_mask.sum(dim=1) - 1
        batch_size = last_hidden_states.shape[0]
        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]


def get_detailed_instruct(task_description: str, query: str) -> str:
    return f'<instruct>{task_description}\n<query>{query}'


task = 'Given a web search query, retrieve relevant passages that answer the query.'
queries = [
    get_detailed_instruct(task, 'how much protein should a female eat'),
    get_detailed_instruct(task, 'summit define')
]
# No need to add instructions for documents
documents = [
    "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
]
input_texts = queries + documents

tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-multilingual-gemma2')
model = AutoModel.from_pretrained('BAAI/bge-multilingual-gemma2')
model.eval()

max_length = 4096
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt', pad_to_multiple_of=8)

with torch.no_grad():
	outputs = model(**batch_dict)
	embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
    
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
# [[55.92064666748047, 1.6549524068832397], [-0.2698777914047241, 49.95653533935547]]