Python walkthrough

Upload a document, wait for it to be ready, then ask a question and print the answer with its source files.

Before you start

Python 3.10 or later and the requests package. Create a Read & write API key in the console.

python3 -m pip install requests

Set these environment variables. Keep the API key private.

export LAB0_API_KEY='lab0_sk_replace_with_your_key'
export LAB0_BASE_URL='https://app.lab0.ai/app'
export LAB0_NAMESPACE='quickstart'

Save a document

Save the following as plan.md, or download it:

# Plan

The rollout uses quillfeather checklists.

The example uploads this file by default. Set LAB0_FILE_PATH to use another path, and change the prompt to match its contents.

Upload, wait and ask

Save this as quickstart.py, or download the example.

import json
import os
import time
from pathlib import Path

import requests

base = os.getenv("LAB0_BASE_URL", "https://app.lab0.ai/app").rstrip("/")
namespace = os.getenv("LAB0_NAMESPACE", "quickstart")
path = Path(os.getenv("LAB0_FILE_PATH", "plan.md"))
session = requests.Session()
session.headers["Authorization"] = f"Bearer {os.environ['LAB0_API_KEY']}"


def request(method, route, **kwargs):
    response = session.request(method, base + route, timeout=200, **kwargs)
    if not response.ok:
        raise RuntimeError(f"HTTP {response.status_code}: {response.text}")
    return response.json()


with path.open("rb") as document:
    uploaded = request("POST", "/api/knowledge/files",
                       files={"file": (path.name, document)},
                       data={"namespace": namespace})
file_id = uploaded["id"]
for _ in range(90):
    document = request("GET", f"/api/knowledge/files/{file_id}")
    if document["status"] == "ready":
        break
    if document["status"] == "failed":
        raise RuntimeError(document.get("error", "Processing failed"))
    time.sleep(2)
else:
    raise TimeoutError(f"Processing timed out; inspect file {file_id}")

answer = request("POST", "/api/knowledge/respond", json={
    "prompt": "How is the rollout run?",
    "namespace": namespace,
    "file_ids": [file_id],
})
print(json.dumps(answer, indent=2))

Run it from the directory containing plan.md:

python3 quickstart.py

The example stops on an HTTP error, a failed upload or a processing timeout. Once the file is ready, it asks “How is the rollout run?” using only the uploaded file.

Read the result

A successful response contains answer, sources and model. The document says that the rollout uses quillfeather checklists; verify that the answer reflects that and that sources identifies plan.md. Exact wording and the model name can vary.

The file stays in your namespace for later questions. See cleanup when you finish, or continue with streaming answers and the API reference.