AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
Ollama now supports Jev-style decision models September 29, 2026 Ollama now supports decision models, based on TypeSafe’s Jev API for fast, typed decisions: No additional costs Lower latency when run locally Three new decision models available today via Ollama This new API is available as of Ollama 0.35 by using the new /v1/systemone endpoint. Send text as state with a set of named questions, and a model running on your machine answers them all in one request. This is great for tasks that require fast decisions, such as ticket triage, model routing, and content or safety moderation. Near-instant decisions Decision models on Ollama are fast, as requests don’t have to travel over a network. Nimble 9B averaged 91ms per decision in the Pac-Man example below when running locally on an M5 Max. That’s fast enough to make rapid decisions such as playing a game or processing content in real time: Move 1 Nimble 9B running on a MacBook Pro M5 Max, replayed at real-time speed. Available models Three new decision models are available to run via Ollama: nimble: open-source 9B parameter decision model developed by Bespoke Labs tev1: an experimental 4B decision model from Together AI tev1:0.8b: an experimental 0.8B decision model from Together AI More decision models are coming soon, including models served by Ollama’s cloud. Decision models on Ollama Bespoke Labs public benchmarks · accuracy, higher is better Mean accuracy across 13 public data sets with human labels, covering 3,880 decisions. Nimble and Tev1 were evaluated on Ollama; Jev 1.13 is from Bespoke Labs' published run on the same decisions. See the Ollama evaluation results and benchmark suite. Get started To get started, first download or upgrade to the latest version of Ollama. Next, download a decision model such as nimble: ollama pull nimble You can make a request via curl or via TypeSafe’s official Python SDK. Request curl http://localhost:11434/v1/systemone -d '{ "model": "nimble", "state": { "ticket": "I was charged twice. Please refund the extra payment." }, "questions": { "team": { "type": "choice", "instructions": "Which team should handle this ticket?", "criteria": { "billing": "Payments and refunds", "technical": "Bugs and integrations", "other": "None of the above" } }, "refund": { "type": "noul", "instructions": "Does the customer explicitly ask for a refund?" }, "urgency": { "type": "score", "instructions": "How urgent is this ticket?", "criteria": ["Routine", "Soon", "Urgent"] } } }' Response { "model": "nimble", "answers": { "team": { "type": "choice", "choice": "billing", "probabilities": {"billing": 0.985, "technical": 0.012, "other": 0.003}, "confidence": 0.922 }, "refund": {"type": "noul", "noul": 0.997}, "urgency": { "type": "score", "score": 0.815, "legend": {"0": "Routine", "1": "Soon", "2": "Urgent"}, "probabilities": {"0": 0.378, "1": 0.429, "2": 0.193}, "confidence": 0.046 } }, "usage": {"input_tokens": 841, "output_tokens": 4} } Setup uv add typesafe-sdk # or: pip install typesafe-sdk export TYPESAFE_BASE_URL=http://localhost:11434 export TYPESAFE_API_KEY=ollama export TYPESAFE_DEFAULT_MODEL=nimble Request from typesafe_sdk import Choice, Noul, Score, TypeSafeClient ticket = "I was charged twice. Please refund the extra payment." questions = { "team": Choice( instructions="Which team should handle this ticket?", criteria={ "billing": "Payments and refunds", "technical": "Bugs and integrations", "other": "None of the above", }, ), "refund": Noul( instructions="Does the customer explicitly ask for a refund?", ), "urgency": Score( instructions="How urgent is this ticket?", criteria=["Routine", "Soon", "Urgent"], ), } with TypeSafeClient(timeout=120) as client: result = client.system_one( state={"ticket": ticket}, questions=questions, ) print(result.choices["team"].choice) # billing print(result.nouls["refund"].noul) # 0.997 print(result.scores["urgency"].score) # 0.815 What’s next This is the first of many releases to come adding decision model support to Ollama. Future updates will include: Faster performance on Apple Silicon powered by MLX More models specializing in different kinds of decision making