End-to-End Training Pipeline

pip install decimalai
export DECIMAL_API_KEY="dai_sk_..."

"""Emit a support-agent trace corpus — the rows a dataset build reads."""
import json
import decimalai

decimalai.init()  # reads DECIMAL_API_KEY from the environment

SYSTEM = "You are a support agent for an online store. Answer from the docs; be brief."

# (question, answer, your quality score for that answer)
CONVERSATIONS = [
    ("How do I reset my password?",
     "Click 'Forgot password' on the sign-in page, then follow the emailed link.", 0.95),
    ("What's your return window?",
     "You can return any item within 30 days of delivery for a full refund.", 0.93),
    ("Do you ship internationally?",
     "Yes — we ship to 40+ countries. Rates are shown at checkout.", 0.91),
    ("Where do I enter a promo code?",
     "Add items to your cart, then enter the code in the 'Promo code' box at checkout.", 0.90),
    ("Is the warranty transferable?",
     "Yes. The 2-year limited warranty transfers to the new owner with the receipt.", 0.88),
    ("How does your laptop compare to a MacBook?",
     "I'm not able to discuss other brands.", 0.20),   # a bad answer, on purpose
]

scored = {}
for question, answer, quality in CONVERSATIONS:
    with decimalai.start_trace(agent_name="support-agent") as t:
        t.set_input(question)
        t.log_tool_call(name="search_docs", input={"query": question},
                        output={"snippet": answer}, latency_ms=40)
        t.log_llm_call(
            model="gpt-4o-mini",
            input=[{"role": "system", "content": SYSTEM},
                   {"role": "user", "content": question}],
            output={"content": answer},
            input_tokens=120, output_tokens=40, latency_ms=800,
        )
        t.set_output(answer)
        scored[t.get_trace_id()] = quality

decimalai.flush()          # traces are sent in the background; make sure they land
json.dump(scored, open("trace_scores.json", "w"), indent=2)
print(f"sent {len(scored)} traces")

sent 6 traces

import json
import decimalai

decimalai.init()

for trace_id, quality in json.load(open("trace_scores.json")).items():
    decimalai.score(trace_id, "answer_quality", quality)

Version 1 · ready · 6 rows

{
  "messages": [
    {"role": "system", "content": "You are a support agent for an online store. Answer from the docs; be brief."},
    {"role": "user", "content": "How do I reset my password?"},
    {"role": "assistant", "content": "Click 'Forgot password' on the sign-in page, then follow the emailed link."}
  ],
  "tools": [
    {"type": "function", "function": {"name": "search_docs", "parameters": {"...": null}}}
  ]
}

import json, httpx, os

DATASET_ID = "..."   # from the dataset page URL
scores = json.load(open("trace_scores.json"))
good = [tid for tid, s in scores.items() if s >= 0.5]

resp = httpx.post(
    f"{os.environ.get('DECIMAL_BASE_URL', 'https://api.decimal.ai')}"
    f"/api/v1/datasets/{DATASET_ID}/build",
    headers={"Authorization": f"Bearer {os.environ['DECIMAL_API_KEY']}"},
    json={"trace_ids": good},
    timeout=60,
)
print(resp.json()["row_count"], "rows")

5 rows

decimalai datasets pull <DATASET_ID> -o ./training_data.jsonl

  Pulling dataset ... (version: latest)...

  ✓ Downloaded successfully
    File:    ./training_data.jsonl
    Format:  jsonl
    Rows:    5
    Size:    2.5 KB

import decimalai
decimalai.init()

result = decimalai.pull_dataset("<DATASET_ID>", "./training_data.jsonl", version="latest")
print(f"Wrote {result['row_count']} rows")

pip install huggingface_hub datasets

import decimalai
decimalai.init()

decimalai.push_to_hub("<DATASET_ID>", "my-org/support-agent-sft")

# CLI equivalent
decimalai datasets push-to-hub <DATASET_ID> my-org/support-agent-sft