How does pgvector fit into a RAG (Retrieval-Augmented Generation) pipeline?

import psycopg2
from pgvector.psycopg2 import register_vector
from openai import OpenAI

conn = psycopg2.connect("postgresql://user:pass@localhost/mydb")
register_vector(conn)
cur = conn.cursor()
oai = OpenAI()

# STAGE 1: INGEST - embed and store documents
documents = [
    "pgvector is a PostgreSQL extension for vector search.",
    "HNSW indexes provide fast approximate nearest neighbour search.",
    "Cosine distance is commonly used for text embeddings.",
]
for text in documents:
    emb = oai.embeddings.create(
        model="text-embedding-3-small", input=text
    ).data[0].embedding
    cur.execute(
        "INSERT INTO documents (content, embedding) VALUES (%s, %s)",
        (text, emb)
    )
conn.commit()

# STAGE 2: RETRIEVE - semantic search for user query
user_question = "What kind of index should I use for fast search?"
q_emb = oai.embeddings.create(
    model="text-embedding-3-small", input=user_question
).data[0].embedding

cur.execute(
    "SELECT content FROM documents ORDER BY embedding <=> %s LIMIT 3",
    (q_emb,)
)
context_chunks = [r[0] for r in cur.fetchall()]

# STAGE 3: GENERATE - pass context to LLM
context = "\n".join(context_chunks)
completion = oai.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": f"Answer using this context:\n{context}"},
        {"role": "user",   "content": user_question}
    ]
)
print(completion.choices[0].message.content)