AI Agents · Lesson

Combining Vector and Graph Retrieval

Hybrid retrieval: vector similarity + graph path traversal for richer context.

Why Hybrid Retrieval?

Vector search finds semantically similar content but misses structured relationships. Graph traversal captures relationships but struggles with semantic similarity. Hybrid retrieval combines both for richer context.

Vector Search Recap

Vector search converts queries and documents into embeddings (dense vectors), then finds documents with high cosine similarity. It answers What documents are about the same topic?

import openai
import numpy as np

client = openai.OpenAI(api_key='sk-...')

def embed(text: str) -> list:
    response = client.embeddings.create(
        model='text-embedding-3-small',
        input=text
    )
    return response.data[0].embedding

def cosine_similarity(a: list, b: list) -> float:
    a_arr = np.array(a)
    b_arr = np.array(b)
    return float(np.dot(a_arr, b_arr) / (np.linalg.norm(a_arr) * np.linalg.norm(b_arr)))

# Simple in-memory vector store
class SimpleVectorStore:
    def __init__(self):
        self.documents = []
    
    def add(self, text: str, metadata: dict):
        embedding = embed(text)
        self.documents.append({'text': text, 'embedding': embedding, 'metadata': metadata})
    
    def search(self, query: str, top_k: int = 5) -> list:
        query_emb = embed(query)
        scored = [
            (cosine_similarity(query_emb, doc['embedding']), doc)
            for doc in self.documents
        ]
        scored.sort(key=lambda x: x[0], reverse=True)
        return [doc for _, doc in scored[:top_k]]

All lessons in this course

← Back to AI Agents