记录 LLM 调用

 inputs = {
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "你好，你能告诉我法国的首都是哪里吗？"
        }
      ]
    }
  ]
}

outputs = {
  "messages": [
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "法国的首都是巴黎。"
        },
        {
          "type": "reasoning",
          "text": "用户正在询问关于..."
        }
      ]
    }
  ]
}

input = {
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "旧金山的天气怎么样？"
        }
      ]
    }
  ]
}

outputs = {
  "messages": [
    {
      "role": "assistant",
      "content": [{"type": "tool_call", "name": "get_weather", "args": {"city": "San Francisco"}, "id": "call_1"}],
    },
    {
      "role": "tool",
      "tool_call_id": "call_1",
      "content": [
        {
          "type": "text",
          "text": "{\"temperature\": \"18°C\", \"condition\": \"Sunny\"}"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "旧金山的天气是 18°C，晴朗。"
        }
      ]
    }
  ]
}

inputs = {
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "这只狗是什么品种？"
        },
        {
          "type": "image",
          "url": "https://fastly.picsum.photos/id/237/200/300.jpg?hmac=TmmQSbShHz9CdQm0NkEjx1Dyh_Y984R9LpNrpvH2D_U",
          # 除了 url，你也可以提供 base64 编码的图片
          # "base64": "<base64 编码的图片>",
          "mime_type": "image/jpeg",
        }
      ]
    }
  ]
}

outputs = {
  "messages": [
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "这看起来像一只黑色拉布拉多犬。"
        }
      ]
    }
  ]
}

input = {
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "AAPL 的价格是多少？"
        }
      ]
    }
  ]
}

output = {
  "messages": [
    {
      "role": "assistant",
      "content": [
        {
          "type": "server_tool_call",
          "name": "web_search",
          "args": {
            "query": "price of AAPL",
            "type": "search"
          },
          "id": "call_1"
        },
        {
          "type": "server_tool_result",
          "tool_call_id": "call_1",
          "status": "success"
        },
        {
          "type": "text",
          "text": "AAPL 的价格是 $150.00"
        }
      ]
    }
  ]
}

from langsmith import traceable

inputs = [
    {"role": "system", "content": "你是一个乐于助人的助手。"},
    {"role": "user", "content": "我想预订一张两人桌。"},
]
output = {
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "当然，请问您想预订几点的桌子？"
            }
        }
    ]
}

@traceable(
    run_type="llm",
    metadata={"ls_provider": "my_provider", "ls_model_name": "my_model"}
)
def chat_model(messages: list):
    return output

chat_model(inputs)

import { traceable } from "langsmith/traceable";

const messages = [
    { role: "system", content: "你是一个乐于助人的助手。" },
    { role: "user", content: "我想预订一张两人桌。" }
];
const output = {
    choices: [
        {
            message: {
                role: "assistant",
                content: "当然，请问您想预订几点的桌子？",
            },
        },
    ],
    usage_metadata: {
        input_tokens: 27,
        output_tokens: 13,
        total_tokens: 40,
    },
};

// 也可以使用以下之一：
// const output = {
//     message: {
//         role: "assistant",
//         content: "当然，请问您想预订几点的桌子？"
//     }
// };
//
// const output = {
//     role: "assistant",
//     content: "当然，请问您想预订几点的桌子？"
// };
//
// const output = ["assistant", "当然，请问您想预订几点的桌子？"];

const chatModel = traceable(
    async ({ messages }: { messages: { role: string; content: string }[] }) => {
        return output;
    },
    {
        run_type: "llm",
        name: "chat_model",
        metadata: {
            ls_provider: "my_provider",
            ls_model_name: "my_model"
        }
    }
);

await chatModel({ messages });

from langsmith.run_trees import RunTree
run_tree = RunTree(
    name="CustomChatModel",
    run_type="llm",
    inputs={ ... }
)
run_tree.post()
llm_stream = ...
first_token = None
for token in llm_stream:
    if first_token is None:
      first_token = token
      run_tree.add_event({
        "name": "new_token"
      })
run_tree.end(outputs={ ... })
run_tree.patch()

import { RunTree } from "langsmith";
const runTree = new RunTree({
    name: "CustomChatModel",
    run_type: "llm",
    inputs: { ... },
});
await runTree.postRun();
const llmStream = ...;
let firstToken;
for (const token of llmStream) {
    if (firstToken == null) {
        firstToken = token;
        runTree.addEvent({ name: "new_token" });
    }
}
await runTree.end({
    outputs: { ... },
});
await runTree.patchRun();