1. Create a collection
python
from openai import OpenAI
client = OpenAI(base_url="https://api.plugsky.com/v1", api_key="sk-live-...")
c = client.rag.collections.create(name="acme-handbook")
print(c.id)2. Upload documents
python
with open("handbook.pdf", "rb") as f:
doc = client.rag.documents.create(
collection_id=c.id,
file=f,
metadata={"department": "engineering"},
)3. Query
python
result = client.rag.query.create(
collection_id=c.id,
query="What is our vacation policy?",
top_k=5,
)
for chunk in result.chunks:
print(f"[{chunk.score:.2f}] {chunk.text[:80]}")
print(f" source: {chunk.source}")4. Compose with chat
python
context = "
".join(c.text for c in result.chunks)
resp = client.chat.completions.create(
model="plugsky-pro",
messages=[
{"role":"system","content":f"Answer using this context. Cite sources.\n\n{context}"},
{"role":"user","content":"What is our vacation policy?"},
],
)See /articles/rag-api for the full feature overview.