Citation RAG on Qdrant (Self-Hosted Vector Store)

docker pull qdrant/qdrant
docker run -p 6333:6333 -p 6334:6334 \
    -v "$(pwd)/qdrant_storage:/qdrant/storage:z" \
    qdrant/qdrant

pip install qdrant-client openai
export OPENAI_API_KEY=sk-...

import re
import uuid
from openai import OpenAI
from qdrant_client import QdrantClient, models

oai = OpenAI()
qdrant = QdrantClient(url="http://localhost:6333")
COLL = "kb"
EMBED_MODEL = "text-embedding-3-small"  # 1536-dimension vectors by default

def embed(texts):
    resp = oai.embeddings.create(model=EMBED_MODEL, input=texts)
    return [d.embedding for d in resp.data]

if not qdrant.collection_exists(COLL):
    qdrant.create_collection(
        collection_name=COLL,
        vectors_config=models.VectorParams(size=1536, distance=models.Distance.COSINE),
    )
    # Index the field you filter on, so filtered search stays fast
    qdrant.create_payload_index(
        collection_name=COLL,
        field_name="tenant",
        field_schema=models.PayloadSchemaType.KEYWORD,
    )

chunks = [  # from your own chunker
    {"doc": "refund-policy.md", "chunk": 0, "tenant": "acme",
     "text": "Customers can request a refund within 30 days of purchase."},
]

vectors = embed([c["text"] for c in chunks])
qdrant.upsert(
    collection_name=COLL,
    wait=True,
    points=[
        models.PointStruct(
            # Stable ID: re-indexing the same chunk overwrites it instead of duplicating
            id=str(uuid.uuid5(uuid.NAMESPACE_URL, f'{c["doc"]}#{c["chunk"]}')),
            vector=v,
            payload=c,
        )
        for c, v in zip(chunks, vectors)
    ],
)

def retrieve(question, tenant, k=5):
    return qdrant.query_points(
        collection_name=COLL,
        query=embed([question])[0],
        query_filter=models.Filter(
            must=[models.FieldCondition(key="tenant", match=models.MatchValue(value=tenant))]
        ),
        with_payload=True,
        limit=k,
    ).points

def answer(question, tenant):
    hits = retrieve(question, tenant)
    if not hits:
        return "I don't have a source for that."
    context = "\n\n".join(f'[{h.id}] ({h.payload["doc"]}) {h.payload["text"]}' for h in hits)
    resp = oai.chat.completions.create(
        model="gpt-6-luna",  # re-check OpenAI's current model list before shipping
        messages=[
            {"role": "system", "content": (
                "Answer only from the sources. After each claim, cite the source id in "
                "square brackets. If the sources don't answer it, say you don't know.")},
            {"role": "user", "content": f"Sources:\n{context}\n\nQuestion: {question}"},
        ],
    )
    text = resp.choices[0].message.content or ""
    allowed = {str(h.id) for h in hits}
    cited = set(re.findall(r"\[([0-9a-f-]{36})\]", text))
    if not cited or not cited <= allowed:
        return "I couldn't produce a grounded answer for that."
    return text

qdrant = QdrantClient(url="https://<your-cluster-url>:6333", api_key="<your-api-key>")