Kern-API

resp = client.chat.completions.create(
    model="nexevo/balanced",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user",   "content": "Explain quantum entanglement"},
    ],
    temperature=0.7,
    max_tokens=500,
)
print(resp.choices[0].message.content)

stream = client.chat.completions.create(
    model="nexevo/balanced",
    messages=[{"role": "user", "content": "Write a haiku."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    print(delta, end="", flush=True)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the weather for a city",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]

resp = client.chat.completions.create(
    model="nexevo/balanced",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools,
)
tool_call = resp.choices[0].message.tool_calls[0]
print(tool_call.function.name, tool_call.function.arguments)

# 1) 文生图(同步)— DALL-E 3 / Imagen 4 / FLUX
img = client.images.generate(
    model="nexevo/image-balanced",       # or "dall-e-3" / "imagen-4-ultra" / "flux-pro"
    prompt="a serene Japanese garden in cyberpunk style",
    n=1, size="1024x1024",
)
print(img["data"][0]["url"])

# 2) 文生视频(异步)— Sora 2 / Veo 3 / Wan 2.6
job = client.videos.generate_and_wait(
    model="sora-2",                          # or "veo-3" / "wan-2.6"
    prompt="a cat skating in neon Tokyo",
    duration_sec=5, aspect_ratio="16:9",
    poll_interval_sec=5, timeout_sec=600,
)
print(job["results"][0]["url"])              # OSS 24h signed URL

# 3) 3D 资产 — Hunyuan 3D 直连
asset = client.models3d.generate_and_wait(
    model="hunyuan-3d-2", prompt="a low-poly viking longboat",
    output_format="glb",
)
print(asset["results"][0]["url"])

# 4) 图生视频 — Runway Gen-4 需先上传参考图
with open("char.png", "rb") as f:
    up = client.generation.uploads.upload(
        f.read(), filename="char.png", content_type="image/png",
    )
job = client.videos.generate_and_wait(
    model="runway-gen4",
    prompt="zoom in slowly while waves crash",
    duration_sec=5,
    reference_image_url=up["url"],
)

# 完整 RAG 三段:embedding 召回 → rerank 精排 → chat 答题
# 总成本 ~$0.06 vs 直接塞 1 万篇文档给 chat ~$5+(差 100x)

from nexevo_ai import Nexevo
client = Nexevo()

# ── 1. 离线索引(只跑一次)──
all_docs = ["...", "...", ...]   # 1 万篇文档
emb_resp = client.embeddings.create(model="bge-m3", input=all_docs)
vectors = [d["embedding"] for d in emb_resp["data"]]
# (省略向量库存取代码 — 用 Pinecone / Milvus / pgvector 都行)

# ── 2. 用户提问时(每次请求触发)──
question = "如何重置员工 VPN?"

# 2a) embed 问题 → 检索 top-50
q_emb = client.embeddings.create(model="bge-m3", input=question)
top50 = vector_db.query(q_emb["data"][0]["embedding"], k=50)

# 2b) rerank top-50 → top-5 最相关
ranked = client.rerank.create(
    model="rerank-v3.5",
    query=question,
    documents=[d.text for d in top50],
    top_n=5,
)["results"]
top5 = [top50[r["index"]] for r in ranked]

# 2c) chat 用 top-5 答题
context = "\n\n".join(d.text for d in top5)
ans = client.chat.completions.create(
    model="nexevo/balanced",
    messages=[
        {"role": "system",
         "content": f"基于以下材料答题(只能用这些材料,不要编):\n\n{context}"},
        {"role": "user", "content": question},
    ],
)
print(ans.choices[0].message.content)

# 流式 — 实时拿每步事件,边跑边看
for ev in client.agents.run_stream(task="..."):
    if ev["type"] == "step":
        s = ev["step"]
        if s["type"] == "tool_call":
            print(f"→ 调用 {s['tool_name']}({s['tool_input']})")
        elif s["type"] == "tool_result":
            print(f"  ← {s['tool_output']}")
        elif s["type"] == "final_answer":
            print(f"\n答:{s['content']}")
    elif ev["type"] == "done":
        print(f"\n总 token: in={ev['job']['total_tokens_in']}, out={ev['job']['total_tokens_out']}")

from nexevo_ai import Nexevo
client = Nexevo()

# Self-Healing v2 — 任务自我修复闭环(Plan → Execute → Evaluate → Adjust)
result = client.tasks.submit(
    goal="调研 2025 Q2 全球生成式视频生成 Top 5 厂商,输出对比表(ARR/客户/技术亮点)",
    enable_planner=True,
    planner_n_candidates=3,         # 并行生成 3 个候选 plan,启发选优
    auto_repair_max_rounds=2,       # verifier 失败 → 反思 + 重 plan 最多 2 轮
    deadline_sec=600,               # 长任务给充裕时间
    wait=True,                       # 阻塞拿结果(或 wait=False 异步 poll)
    deliverables=[{"type": "email", "target": "you@company.com"}],
)

# response 含:plan(实际跑的)+ deliverables + verifier 多维分 + partial 标记
print(result["plan"]["nodes"])                  # 看 agent 怎么拆的
print(result["deliverables"][0]["content"])     # 主答
print(result["deliverables"][0]["metadata"])    # verifier 多维分
if result["partial"]:
    print("部分成功节点:", result["succeeded_node_ids"])
    print("失败节点:",   result["failed_node_ids"])