bge-code-v1

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

from FlagEmbedding import FlagLLMModel
queries = [
    "Delete the record with ID 4 from the 'Staff' table.", 
    'Delete all records in the "Livestock" table where age is greater than 5'
]
documents = [
    "DELETE FROM Staff WHERE StaffID = 4;",
    "DELETE FROM Livestock WHERE age > 5;"
]
model = FlagLLMModel('BAAI/bge-code-v1', 
                     query_instruction_format="<instruct>{}\n<query>{}",
                     query_instruction_for_retrieval="Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
                     trust_remote_code=True,
                     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)

from sentence_transformers import SentenceTransformer
import torch

# Load the model, optionally in float16 precision for faster inference
model = SentenceTransformer(
    "BAAI/bge-code-v1",
    trust_remote_code=True,
    model_kwargs={"torch_dtype": torch.float16},
)

# Prepare a prompt given an instruction
instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
prompt = f'<instruct>{instruction}\n<query>'
# Prepare queries and documents
queries = [
    "Delete the record with ID 4 from the 'Staff' table.", 
    'Delete all records in the "Livestock" table where age is greater than 5'
]
documents = [
    "DELETE FROM Staff WHERE StaffID = 4;",
    "DELETE FROM Livestock WHERE age > 5;"
]

# 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)

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}'


instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
queries = [
    "Delete the record with ID 4 from the 'Staff' table.", 
    'Delete all records in the "Livestock" table where age is greater than 5'
]
documents = [
    "DELETE FROM Staff WHERE StaffID = 4;",
    "DELETE FROM Livestock WHERE age > 5;"
]
input_texts = queries + documents

tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-code-v1', trust_remote_code=True)
model = AutoModel.from_pretrained('BAAI/bge-code-v1', trust_remote_code=True)
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())

{
    "Apps": "Given a code contest problem description, retrieve relevant code that can help solve the problem.",
    "CosQA": "Given a web search query, retrieve relevant code that can help answer the query.",
    "Text2SQL": "Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
    "CSN": "Given a piece of code, retrieve the document string that summarizes the code.",
    "CSN-CCR": "Given a piece of code segment, retrieve the code segment that is the latter part of the code.",
    "CodeTrans-DL": "Given a piece of code, retrieve code that is semantically equivalent to the input code.",
    "CodeTrans-Contest": "Given a piece of Python code, retrieve C++ code that is semantically equivalent to the input code.",
    "StackOverFlow-QA": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
    "CodeFeedBack-ST": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
    "CodeFeedBack-MT": "Given a multi-turn conversation history that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
    "HummanEval": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
    "MBPP": "Given a textual explanation of code functionality, retrieve the corresponding code implementation.",
    "DS-1000": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
    "ODEX": "Given a question, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
    "RepoEval": "Given a piece of code segment, retrieve the code segment that is the latter part of the code.",
    "SWE-bench-Lite": "Given a code snippet containing a bug and a natural language description of the bug or error, retrieve code snippets that demonstrate solutions or fixes for similar bugs or errors (the desired documents)."
}

@misc{bge_code,
    title={Towards A Generalist Code Embedding Model Based On Massive Data Synthesis}, 
    author={Chaofan Li and Jianlyu Chen and Yingxia Shao and Defu Lian and Zheng Liu},
    year={2025},
    eprint={2505.12697},
    archivePrefix={arXiv},
    primaryClass={cs.IR},
    url={https://arxiv.org/abs/2505.12697}, 
}