Comparação de Modelos de Busca Semântica e Embeddings

A busca semântica é um sistema que pesquisa com base na similaridade de significado, em vez de correspondência por palavra-chave. Neste guia, examinamos modelos de embedding e implementações de busca semântica.

Busca por Palavra-chave vs Busca Semântica

1Keyword Search:
2Query: "cheap phone"
3Result: Only documents containing "cheap" and "phone"
4
5Semantic Search:
6Query: "cheap phone"
7Result: "budget-friendly smart device", "economical smartphone", 
8       "affordable mobile" and semantically similar documents

Comparação de Modelos de Embedding

Modelos Populares

OpenAI Embedding

1from openai import OpenAI
2
3client = OpenAI()
4
5def get_embedding(text: str, model: str = "text-embedding-3-large"):
6    response = client.embeddings.create(
7        input=text,
8        model=model,
9        dimensions=1024  # Dimension reduction (optional)
10    )
11    return response.data[0].embedding
12
13# Batch embedding
14def get_embeddings_batch(texts: list[str]):
15    response = client.embeddings.create(
16        input=texts,
17        model="text-embedding-3-large"
18    )
19    return [item.embedding for item in response.data]

Cohere Embedding

1import cohere
2
3co = cohere.Client("api-key")
4
5def get_cohere_embedding(texts: list[str], input_type: str = "search_document"):
6    response = co.embed(
7        texts=texts,
8        model="embed-multilingual-v3.0",
9        input_type=input_type  # search_document or search_query
10    )
11    return response.embeddings

Sentence Transformers (Local)

1from sentence_transformers import SentenceTransformer
2
3model = SentenceTransformer("BAAI/bge-m3")
4
5# Single text
6embedding = model.encode("Hello world")
7
8# Batch
9embeddings = model.encode([
10    "First text",
11    "Second text",
12    "Third text"
13], batch_size=32, show_progress_bar=True)

Implementação de Busca Semântica

Similaridade de Cosseno Simples

1import numpy as np
2
3def cosine_similarity(a, b):
4    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
5
6def search(query: str, documents: list[dict], top_k: int = 5):
7    query_embedding = get_embedding(query)
8    
9    results = []
10    for doc in documents:
11        similarity = cosine_similarity(query_embedding, doc["embedding"])
12        results.append({
13            "document": doc,
14            "score": similarity
15        })
16    
17    results.sort(key=lambda x: x["score"], reverse=True)
18    return results[:top_k]

Busca com Banco de Dados Vetorial

1from pinecone import Pinecone
2
3pc = Pinecone(api_key="xxx")
4index = pc.Index("semantic-search")
5
6def semantic_search(query: str, top_k: int = 10, filter: dict = None):
7    query_embedding = get_embedding(query)
8    
9    results = index.query(
10        vector=query_embedding,
11        top_k=top_k,
12        filter=filter,
13        include_metadata=True
14    )
15    
16    return [
17        {
18            "id": match.id,
19            "score": match.score,
20            "metadata": match.metadata
21        }
22        for match in results.matches
23    ]
24## Pesquisa Híbrida
25
26Combinação de busca por palavra-chave + busca semântica:
27
28```python
29from rank_bm25 import BM25Okapi
30
31class HybridSearch:
32    def __init__(self, documents):
33        self.documents = documents
34        
35        # BM25 index
36        tokenized = [doc["text"].split() for doc in documents]
37        self.bm25 = BM25Okapi(tokenized)
38        
39        # Embeddings
40        texts = [doc["text"] for doc in documents]
41        self.embeddings = get_embeddings_batch(texts)
42    
43    def search(self, query: str, top_k: int = 10, alpha: float = 0.5):
44        # BM25 scores
45        bm25_scores = self.bm25.get_scores(query.split())
46        bm25_scores = (bm25_scores - bm25_scores.min()) / (bm25_scores.max() - bm25_scores.min() + 1e-6)
47        
48        # Semantic scores
49        query_emb = get_embedding(query)
50        semantic_scores = [
51            cosine_similarity(query_emb, emb) 
52            for emb in self.embeddings
53        ]
54        semantic_scores = np.array(semantic_scores)
55        
56        # Hybrid score
57        hybrid_scores = alpha * semantic_scores + (1 - alpha) * bm25_scores
58        
59        # Sort and return
60        top_indices = np.argsort(hybrid_scores)[::-1][:top_k]
61        
62        return [
63            {
64                "document": self.documents[i],
65                "score": hybrid_scores[i],
66                "bm25_score": bm25_scores[i],
67                "semantic_score": semantic_scores[i]
68            }
69            for i in top_indices
70        ]

Reranking

Ordenação mais precisa dos resultados iniciais:

1import cohere
2
3co = cohere.Client("api-key")
4
5def rerank_results(query: str, documents: list[str], top_k: int = 10):
6    response = co.rerank(
7        query=query,
8        documents=documents,
9        model="rerank-multilingual-v3.0",
10        top_n=top_k
11    )
12    
13    return [
14        {
15            "index": result.index,
16            "text": documents[result.index],
17            "score": result.relevance_score
18        }
19        for result in response.results
20    ]
21
22# Pipeline: Retrieve → Rerank
23def search_with_rerank(query: str, top_k: int = 5):
24    # Step 1: Get more candidates
25    candidates = semantic_search(query, top_k=top_k * 3)
26    
27    # Step 2: Rerank
28    docs = [c["metadata"]["text"] for c in candidates]
29    reranked = rerank_results(query, docs, top_k=top_k)
30    
31    return reranked

Compreensão de Consulta

Expansão de Consulta

1def expand_query(query: str) -> list[str]:
2    """Query expansion with LLM"""
3    response = client.chat.completions.create(
4        model="gpt-4-turbo",
5        messages=[
6            {
7                "role": "system",
8                "content": "Generate 3 different variations of the given search query."
9            },
10            {"role": "user", "content": query}
11        ]
12    )
13    
14    variations = response.choices[0].message.content.split("\n")
15    return [query] + variations

HyDE (Hypothetical Document Embeddings)

1def hyde_search(query: str, top_k: int = 5):
2    """Generate hypothetical document and get embedding"""
3    
4    # Generate hypothetical document
5    response = client.chat.completions.create(
6        model="gpt-4-turbo",
7        messages=[
8            {
9                "role": "system",
10                "content": "Write a paragraph that answers this question."
11            },
12            {"role": "user", "content": query}
13        ]
14    )
15    
16    hypothetical_doc = response.choices[0].message.content
17    
18    # Embed the hypothetical document
19    hyde_embedding = get_embedding(hypothetical_doc)
20    
21    # Search with this embedding
22    return vector_search(hyde_embedding, top_k)
23## Métricas de Avaliação
24
25### Métricas de Recuperação
26
27```python
28def calculate_metrics(retrieved: list, relevant: list, k: int):
29    """Calculate Precision@K, Recall@K, MRR"""
30    
31    # Precision@K
32    retrieved_k = retrieved[:k]
33    relevant_in_k = len(set(retrieved_k) & set(relevant))
34    precision_k = relevant_in_k / k
35    
36    # Recall@K
37    recall_k = relevant_in_k / len(relevant)
38    
39    # MRR
40    mrr = 0
41    for i, doc in enumerate(retrieved):
42        if doc in relevant:
43            mrr = 1 / (i + 1)
44            break
45    
46    return {
47        "precision@k": precision_k,
48        "recall@k": recall_k,
49        "mrr": mrr
50    }

Otimizações de Produção

Cache de Embeddings

1import hashlib
2import redis
3
4redis_client = redis.Redis()
5
6def get_embedding_cached(text: str, model: str = "text-embedding-3-large"):
7    cache_key = f"emb:{model}:{hashlib.md5(text.encode()).hexdigest()}"
8    
9    cached = redis_client.get(cache_key)
10    if cached:
11        return json.loads(cached)
12    
13    embedding = get_embedding(text, model)
14    redis_client.setex(cache_key, 86400, json.dumps(embedding))  # 24h TTL
15    
16    return embedding

Processamento em Lotes

1async def process_documents_async(documents: list[dict], batch_size: int = 100):
2    """Async batch embedding"""
3    
4    async def process_batch(batch):
5        texts = [doc["text"] for doc in batch]
6        embeddings = await async_get_embeddings(texts)
7        
8        for doc, emb in zip(batch, embeddings):
9            doc["embedding"] = emb
10        
11        return batch
12    
13    tasks = []
14    for i in range(0, len(documents), batch_size):
15        batch = documents[i:i + batch_size]
16        tasks.append(process_batch(batch))
17    
18    results = await asyncio.gather(*tasks)
19    return [doc for batch in results for doc in batch]

Conclusão

A busca semântica é uma tecnologia poderosa que melhora significativamente a experiência do usuário. Com a seleção correta do modelo de embeddings, busca híbrida e reranking, você pode criar sistemas de busca de alta qualidade.

Como Veni AI, desenvolvemos soluções empresariais de busca semântica.