释放稀疏向量的强大潜能

# pip install -U FlagEmbedding

from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel("BAAI/bge-m3", use_fp16=True)
sentences = ["What is BM25?", "Definition of BM25"]

output = model.encode(sentences, return_dense=True, return_sparse=True)

# The dense embedding of the two texts above:
dense_embedding = output['dense_vecs']
# [[-0.02501617 -0.04525582 -0.01972856 ... -0.0099566   0.01677509
#   0.01292699]
# [-0.0106499  -0.04731942 -0.01477693 ... -0.0149255   0.01040097
#   0.00965083]

sparse_weight_id = output['lexical_weights']

# You can see the weight for each token:
# print(model.convert_id_to_token(sparse_weight_id))
# 
# [{'What': 0.10430284, 'is': 0.10090457, 'BM': 0.2635918, '25': 0.3382988, '?': 0.052101523}, 
# {'Definition': 0.14298248, 'of': 0.076763615, 'BM': 0.2577639, '25': 0.33806682}]

# pip install -U numpy

import numpy as np

# Sparse vector embedding of text
sparse_indices = [[int(token_id) for token_id in text] for text in sparse_weight_id]
# [[4865, 83, 90017, 2588, 32], [155455, 111, 90017, 2588]]
sparse_values = [[float(text[token_id]) for token_id in text] for text in sparse_weight_id]
# [[0.10430284, 0.10090457, 0.2635918, 0.3382988, 0.052101523], [0.14298248, 0.076763615, 0.2577639, 0.33806682]]

# Sparse indexes must be ascending for each pgvecto.rs
for i in range(len(sparse_weight_id)):
    sparse_values[i] = [x for _, x in sorted(zip(sparse_indices[i], sparse_values[i]))]
    sparse_indices[i] = sorted(sparse_indices[i])

docker run \
  --name pgvecto-rs-demo \
  -e POSTGRES_PASSWORD=mysecretpassword \
  -p 5432:5432 \
  -d tensorchord/pgvecto-rs:pg16-v0.3.0

print(len(model.tokenizer))
# 250002

# pip install -U psycopg

import psycopg
URL = "postgresql://postgres:mysecretpassword@localhost:5432/postgres"

with psycopg.connect(URL) as conn:
    conn.execute("DROP TABLE IF EXISTS documents;")
    conn.execute(f"""
        CREATE TABLE documents (
            id SERIAL PRIMARY KEY, 
            text TEXT NOT NULL,
            dense vector(1024) NOT NULL,
            sparse svector({len(model.tokenizer)}) NOT NULL);
    """
    )

# pip install -U pgvecto_rs

import psycopg
from pgvecto_rs.psycopg import register_vector
URL = "postgresql://postgres:mysecretpassword@localhost:5432/postgres"

with psycopg.connect(URL) as conn:
    register_vector(conn)
    for text, dense, sparse_ind, sparse_val in zip(sentences, dense_embedding, sparse_indices, sparse_values):
        conn.execute(
            "INSERT INTO documents (text, dense, sparse) VALUES (%s, %s, to_svector(%s, %s::real[]::int[], %s::real[]));",
            (text, dense, len(model.tokenizer), sparse_ind, sparse_val),
        )
    conn.execute("""
        CREATE INDEX ON documents 
        USING vectors (sparse svector_dot_ops) 
        WITH (options = \"[indexing.hnsw]\");
    """)
    conn.execute("""
        CREATE INDEX ON documents 
        USING vectors (dense vector_l2_ops) 
        WITH (options = \"[indexing.hnsw]\");
    """)

def embedding(sentence: str) -> tuple[np.ndarray, list[list[int]], list[list[float]]]:
    """
    Create dense and sparse embeddings from text
    """
    output = model.encode(sentence, return_dense=True, return_sparse=True, return_colbert_vecs=False)
    dense_embedding = output['dense_vecs']
    sparse_weight_id = output['lexical_weights']
    sparse_indices = [int(token_id) for token_id in sparse_weight_id]
    sparse_values = [float(sparse_weight_id[token_id]) for token_id in sparse_weight_id]

    sparse_values = [x for _, x in sorted(zip(sparse_indices, sparse_values))]
    sparse_indices = sorted(sparse_indices)
    return dense_embedding, sparse_indices, sparse_values

dense_embedding, sparse_indices, sparse_values = embedding("The text you want to search...")

with psycopg.connect(URL) as conn:
    register_vector(conn)
    cur = conn.execute(
        "SELECT text FROM documents ORDER BY sparse <#> to_svector(%s, %s::real[]::int[], %s::real[]) LIMIT 50;",
        (len(model.tokenizer), sparse_indices, sparse_values),
    )
    sparse_result = cur.fetchall()
      
    cur = conn.execute(
              "SELECT text FROM documents ORDER BY dense <-> %s LIMIT 50;",
              (dense_embedding,),
          )
    dense_result = cur.fetchall()
    
# Merge sparse and dense vector search results
mix_text = set([r[0] for r in dense_result]).union([r[0] for r in sparse_result])

from FlagEmbedding import FlagReranker

reranker = FlagReranker('BAAI/bge-reranker-large', use_fp16=True)

# Obtain relevance scores （Higher scores indicate greater relevance）
scores = reranker.compute_score([["The text you want to search...", candidate] for candidate in mix_text])
# Rerank text using combined dense and sparse embeddings
reranked_text = [t for _, t in sorted(zip(scores, mix_text))]