Similarity Search Patterns

# similarity-search-patterns — templates and worked examples

## Templates

### Template 1: Pinecone Implementation

```python
from pinecone import Pinecone, ServerlessSpec
from typing import List, Dict, Optional
import hashlib

class PineconeVectorStore:
    def __init__(
        self,
        api_key: str,
        index_name: str,
        dimension: int = 1536,
        metric: str = "cosine"
    ):
        self.pc = Pinecone(api_key=api_key)

        # Create index if not exists
        if index_name not in self.pc.list_indexes().names():
            self.pc.create_index(
                name=index_name,
                dimension=dimension,
                metric=metric,
                spec=ServerlessSpec(cloud="aws", region="us-east-1")
            )

        self.index = self.pc.Index(index_name)

    def upsert(
        self,
        vectors: List[Dict],
        namespace: str = ""
    ) -> int:
        """
        Upsert vectors.
        vectors: [{"id": str, "values": List[float], "metadata": dict}]
        """
        # Batch upsert
        batch_size = 100
        total = 0

        for i in range(0, len(vectors), batch_size):
            batch = vectors[i:i + batch_size]
            self.index.upsert(vectors=batch, namespace=namespace)
            total += len(batch)

        return total

    def search(
        self,
        query_vector: List[float],
        top_k: int = 10,
        namespace: str = "",
        filter: Optional[Dict] = None,
        include_metadata: bool = True
    ) -> List[Dict]:
        """Search for similar vectors."""
        results = self.index.query(
            vector=query_vector,
            top_k=top_k,
            namespace=namespace,
            filter=filter,
            include_metadata=include_metadata
        )

        return [
            {
                "id": match.id,
                "score": match.score,
                "metadata": match.metadata
            }
            for match in results.matches
        ]

    def search_with_rerank(
        self,
        query: str,
        query_vector: List[float],
        top_k: int = 10,
        rerank_top_n: int = 50,
        namespace: str = ""
    ) -> List[Dict]:
        """Search and rerank results."""
        # Over-fetch for reranking
        initial_results = self.search(
            query_vector,
            top_k=rerank_top_n,
            namespace=namespace
        )

        # Rerank with cross-encoder or LLM
        reranked = self._rerank(query, initial_results)

        return reranked[:top_k]

    def _rerank(self, query: str, results: List[Dict]) -> List[Dict]:
        """Rerank results using cross-encoder."""
        from sentence_transformers import CrossEncoder

        model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')

        pairs = [(query, r["metadata"]["text"]) for r in results]
        scores = model.predict(pairs)

        for result, score in zip(results, scores):
            result["rerank_score"] = float(score)

        return sorted(results, key=lambda x: x["rerank_score"], reverse=True)

    def delete(self, ids: List[str], namespace: str = ""):
        """Delete vectors by ID."""
        self.index.delete(ids=ids, namespace=namespace)

    def delete_by_filter(self, filter: Dict, namespace: str = ""):
        """Delete vectors matching filter."""
        self.index.delete(filter=filter, namespace=namespace)
```

### Template 2: Qdrant Implementation

```python
from qdrant_client import QdrantClient
from qdrant_client.http import models
from typing import List, Dict, Optional

class QdrantVectorStore:
    def __init__(
        self,
        url: str = "localhost",
        port: int = 6333,
        collection_name: str = "documents",
        vector_size: int = 1536
    ):
        self.client = QdrantClient(url=url, port=port)
        self.collection_name = collection_name

        # Create collection if not exists
        collections = self.client.get_collections().collections