Recherche sémantique avec NumPy

Semantic Search Without a Database

Building the Document Corpus

import numpy as np
from openai import OpenAI

client = OpenAI()

documents = [
    'Python is a high-level programming language.',
    'NumPy provides fast numerical computing for Python.',
    'Embeddings represent text as dense vectors.',
    'Cosine similarity measures angle between vectors.',
    'RAG combines retrieval with language generation.'
]

response = client.embeddings.create(
    model='text-embedding-3-small',
    input=documents
)

corpus_embeddings = np.array([item.embedding for item in response.data])
print(f'Corpus shape: {corpus_embeddings.shape}')  # (5, 1536)

Embedding the User Query

from openai import OpenAI
import numpy as np

client = OpenAI()

query = 'How do I compute similarity between text?'

response = client.embeddings.create(
    model='text-embedding-3-small',   # must match corpus model
    input=query
)

query_embedding = np.array(response.data[0].embedding)
print(f'Query vector shape: {query_embedding.shape}')  # (1536,)

Computing Cosine Similarity with NumPy

import numpy as np

# corpus_embeddings: (n_docs, 1536)
# query_embedding: (1536,)

def semantic_search(query_vec, corpus_vecs):
    # Matrix-vector dot product: shape (n_docs,)
    similarities = corpus_vecs @ query_vec
    return similarities

# Example call (assuming pre-computed embeddings)
# sims = semantic_search(query_embedding, corpus_embeddings)
# print(sims)  # array of similarity scores, one per document

Ranking and Retrieving Top-K Results

import numpy as np

def get_top_k(query_vec, corpus_vecs, documents, k=3):
    similarities = corpus_vecs @ query_vec
    # argsort gives ascending order; [::-1] reverses to descending
    ranked_indices = np.argsort(similarities)[::-1]
    top_k_indices = ranked_indices[:k]
    return [
        {'text': documents[i], 'score': float(similarities[i])}
        for i in top_k_indices
    ]

# results = get_top_k(query_embedding, corpus_embeddings, documents, k=3)
# for r in results:
#     print(f'{r["score"]:.4f}: {r["text"]}')

Full Semantic Search Example

import numpy as np
from openai import OpenAI

client = OpenAI()

docs = [
    'Embeddings map text to numerical vectors.',
    'Python lists store ordered collections.',
    'Cosine similarity compares vector directions.',
    'RAG retrieves documents to ground LLM answers.',
    'Dictionaries store key-value pairs in Python.'
]

corpus_resp = client.embeddings.create(model='text-embedding-3-small', input=docs)
corpus = np.array([d.embedding for d in corpus_resp.data])

query = 'finding similar text using angles'
q_resp = client.embeddings.create(model='text-embedding-3-small', input=query)
q_vec = np.array(q_resp.data[0].embedding)

scores = corpus @ q_vec
for i in np.argsort(scores)[::-1][:3]:
    print(f'{scores[i]:.3f}: {docs[i]}')

Score Thresholding

import numpy as np

def search_with_threshold(query_vec, corpus_vecs, documents, k=5, threshold=0.75):
    similarities = corpus_vecs @ query_vec
    ranked = np.argsort(similarities)[::-1][:k]
    results = []
    for i in ranked:
        if similarities[i] >= threshold:
            results.append({'text': documents[i], 'score': float(similarities[i])})
    return results

# Only returns documents above the minimum similarity threshold

Performance Characteristics of NumPy Search

Persisting Embeddings to Disk

import numpy as np
import json

# Save
np.save('/tmp/corpus_embeddings.npy', corpus_embeddings)
with open('/tmp/corpus_docs.json', 'w') as f:
    json.dump(documents, f)

# Load
corpus_embeddings = np.load('/tmp/corpus_embeddings.npy')
with open('/tmp/corpus_docs.json') as f:
    documents = json.load(f)

print(f'Loaded {len(documents)} docs, shape {corpus_embeddings.shape}')

Handling New Documents Incrementally

import numpy as np
from openai import OpenAI

client = OpenAI()

# Assume these exist from a previous session:
# corpus_embeddings: (n, 1536)
# documents: list of strings

new_docs = ['New document about vector search.']
resp = client.embeddings.create(model='text-embedding-3-small', input=new_docs)
new_vecs = np.array([item.embedding for item in resp.data])

corpus_embeddings = np.vstack([corpus_embeddings, new_vecs])
documents.extend(new_docs)
print(f'Corpus now has {len(documents)} documents')

Limitations of In-Memory Search

Quick Check

Lesson Recap