caelum0x 4847e35451 OpenJev: open-source typed decision service
Typed decision/classification service with an in-process gte-small ONNX
embedding engine and lexical fallback, JS/Python SDKs, adapters, and the
otsone model family. Apache-2.0 (sub-packages keep their MIT licenses).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 00:12:36 +03:00
..

OpenJev Python SDK

openjev is an open Python client for OpenJev — a self-hostable decision engine that speaks the same System One /v1 wire protocol as the upstream TypeSafe AI API, so a single client works unchanged against:

  • a self-hosted OpenJev deployment (default base URL: http://localhost:8080)
  • the hosted TypeSafe AI API at https://api.typesafe.ai

This SDK is derived from @typesafe-ai/typesafe-sdk-python (MIT). See NOTICE for attribution. The request/response shapes (model + state + questions-as-dict) and the public class names (TypeSafeClient, AsyncTypeSafeClient, …) are kept identical so existing TypeSafe code is drop-in compatible.

Quickstart

Install the SDK:

Not published to PyPI. Note that the PyPI name openjev currently belongs to an unrelated project, so do not pip install openjev. Install from a clone instead:

git clone https://github.com/caelum0x/openjev
pip install ./openjev/sdk/python
# or: uv add ./openjev/sdk/python

Set OPENJEV_API_KEY (and optionally OPENJEV_BASE_URL) in your environment, then instantiate and use the client:

from openjev import Choice, TypeSafeClient

with TypeSafeClient() as client:
    response = client.system_one(
        state={"document": "I was charged twice. Please fix this ASAP."},
        questions={
            "category": Choice(
                instructions="What is this ticket about?",
                criteria={"billing": None, "technical": None, "other": None},
            ),
        },
    )

print(response.choices["category"].choice)

Configuration

Point the SDK at a self-hosted OpenJev endpoint or the upstream TypeSafe AI API by setting environment variables or passing arguments to the client constructor.

Purpose Primary (OpenJev) Back-compat alias (legacy)
API key OPENJEV_API_KEY TYPESAFE_API_KEY
Base URL OPENJEV_BASE_URL TYPESAFE_BASE_URL
Default model OPENJEV_DEFAULT_MODEL TYPESAFE_DEFAULT_MODEL
Log level OPENJEV_LOG_LEVEL TYPESAFE_LOG_LEVEL

The primary OPENJEV_* variable is checked first; the TYPESAFE_* alias is consulted only when the primary variable is absent so that callers already using TYPESAFE_* continue to work without changes.

Default base URL when no variable is set: http://localhost:8080.

Example — point at a self-hosted deployment:

export OPENJEV_BASE_URL="https://systemone.internal.example.com"
export OPENJEV_API_KEY="your-self-hosted-key"

Example — point at the upstream TypeSafe AI API using the back-compat alias:

export TYPESAFE_BASE_URL="https://api.typesafe.ai"
export TYPESAFE_API_KEY="ts_live_..."
from openjev import TypeSafeClient

# Explicit override also works and takes precedence over the environment:
client = TypeSafeClient(
    base_url="https://systemone.internal.example.com", api_key="..."
)

Trust layer (OpenJev servers)

from openjev import Choice, TypeSafeClient

with TypeSafeClient() as client:
    questions = {
        "intent": Choice(
            instructions="What does the customer want?",
            criteria={"refund": None, "status": None},
            abstain=True,
        )
    }
    result = client.system_one(
        "Where is my order?",
        questions,
        model="auto",                 # local first, LLM only for low-confidence questions
        calibration_id="cal_...",     # confidence fitted on your own labels
    )
    intent = result.choices["intent"]
    if intent.abstained:
        print("out of scope", intent.ood)

    # Shadow mode: compare with your production LLM or human labels.
    client.shadow.run(
        "Where is my order?",
        questions,
        incumbent={"kind": "label", "answers": {"intent": "status"}},
    )
    summary = client.shadow.summary(days=7)

License

MIT — see LICENSE and NOTICE.