Embeddings & Semantic Search

import openai

response = openai.Embedding.create(
    model="text-embedding-3-small",
    input="Redis connection timeout in production cluster"
)

vector = response["data"][0]["embedding"]
print(f"Dimensions: {len(vector)}")  # 1536
print(f"First 5 values: {vector[:5]}")

import numpy as np

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# These should be semantically similar
doc1 = "Redis connection timeout"
doc2 = "Cannot reach Redis instance"

emb1 = get_embedding(doc1)  # Your embedding function
emb2 = get_embedding(doc2)

similarity = cosine_similarity(emb1, emb2)
print(f"Similarity: {similarity:.4f}")  # ~0.85

import openai
import numpy as np

# Your knowledge base chunks
docs = [
    "Runbook: Redis failover procedure for production cluster",
    "Incident: DNS resolution failures in us-east-1",
    "How to scale Kubernetes pods based on CPU metrics",
]

# Embed all documents
doc_embeddings = [get_embedding(doc) for doc in docs]

def search(query, top_k=2):
    query_emb = get_embedding(query)
    similarities = [
        cosine_similarity(query_emb, emb) for emb in doc_embeddings
    ]
    ranked = sorted(enumerate(similarities), key=lambda x: x[1], reverse=True)
    return [(docs[i], score) for i, score in ranked[:top_k]]

results = search("Redis is down, how do I failover?")
for doc, score in results:
    print(f"[{score:.4f}] {doc}")