AI, ML & DevOps
engineering that ships.

# Production RAG in ~40 lines
from openai import OpenAI
from qdrant_client import QdrantClient

llm = OpenAI()
db  = QdrantClient(url=VECTOR_URL)

def answer(question: str) -> str:
    embedding = llm.embeddings.create(
        model="text-embedding-3-large",
        input=question
    ).data[0].embedding

    hits = db.search(
        collection_name="kb",
        query_vector=embedding,
        limit=5,
    )
    context = "\n\n".join(h.payload["text"] for h in hits)

    resp = llm.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {"role": "system", "content": SYSTEM},
            {"role": "user",   "content": f"{context}\n\nQ: {question}"},
        ],
        temperature=0.2,
    )
    return resp.choices[0].message.content

# Add: eval harness, tracing, caching, guardrails, auth…
#   we wire it all up for you.