Quickstart: Set up custom agent observability

// Set WANDB_API_KEY, OPENAI_API_KEY in your environment before running this project
import * as weave from 'weave';

await weave.init(`[YOUR-TEAM]/[YOUR-PROJECT]`);

from openai import OpenAI

openai_client = OpenAI()
MODEL = "gpt-4o-mini"

def run_turn(history, user_message):
    history.append({"role": "user", "content": user_message})

    with weave.start_turn(user_message=user_message, model=MODEL):
        # LLM call 1: the model might decide to use a tool.
        with weave.start_llm(model=MODEL, provider_name="openai") as llm:
            resp = openai_client.chat.completions.create(
                model=MODEL, messages=history, tools=[wikipedia_tool_schema],
            )
            msg = resp.choices[0].message
            llm.output(msg.content or "")
            llm.usage = weave.Usage(
                input_tokens=resp.usage.prompt_tokens,
                output_tokens=resp.usage.completion_tokens,
            )
            history.append(msg.model_dump(exclude_none=True))

        # If no tool was requested, the first LLM response is the answer.
        if not msg.tool_calls:
            return msg.content

        # Execute each requested tool call.
        for tc in msg.tool_calls:
            with weave.start_tool(
                name=tc.function.name,
                arguments=tc.function.arguments,
                tool_call_id=tc.id,
            ) as tool:
                tool.result = wikipedia_search(**json.loads(tc.function.arguments))
                history.append({
                    "role": "tool",
                    "tool_call_id": tc.id,
                    "content": tool.result,
                })

        # LLM call 2: synthesize the final answer.
        with weave.start_llm(model=MODEL, provider_name="openai") as llm:
            resp = openai_client.chat.completions.create(model=MODEL, messages=history)
            msg = resp.choices[0].message
            llm.output(msg.content)
            llm.usage = weave.Usage(
                input_tokens=resp.usage.prompt_tokens,
                output_tokens=resp.usage.completion_tokens,
            )
            history.append({"role": "assistant", "content": msg.content})
            return msg.content

with weave.start_conversation(agent_name="research-bot") as conversation:
    history = []
    for question in [
        "Who founded Anthropic?",
        "What is Claude (the AI assistant)?",
        "Summarize what we discussed in one sentence.",
    ]:
        print(f"USER: {question}")
        print(f"AGENT: {run_turn(history, question)}\n")

import OpenAI from 'openai';

const openaiClient = new OpenAI();
const MODEL = 'gpt-4o-mini';

// history is a list of OpenAI chat messages; typed loosely for brevity.
async function runTurn(history: any[], userMessage: string): Promise<string | null> {
  history.push({ role: 'user', content: userMessage });

  const turn = weave.startTurn({ model: MODEL });
  try {
    // LLM call 1: the model might decide to use a tool.
    const llm1 = weave.startLLM({ model: MODEL, providerName: 'openai' });
    let msg;
    try {
      const resp = await openaiClient.chat.completions.create({
        model: MODEL,
        messages: history,
        tools: [wikipediaToolSchema],
      });
      msg = resp.choices[0].message;
      llm1.output(msg.content ?? '');
      llm1.usage = {
        inputTokens: resp.usage?.prompt_tokens,
        outputTokens: resp.usage?.completion_tokens,
      };
      history.push(msg);
    } finally {
      llm1.end();
    }

    // If no tool was requested, the first LLM response is the answer.
    if (!msg.tool_calls?.length) {
      return msg.content ?? null;
    }

    // Execute each requested tool call.
    for (const tc of msg.tool_calls) {
      if (tc.type !== 'function') continue;
      const tool = weave.startTool({
        name: tc.function.name,
        args: tc.function.arguments,
        toolCallId: tc.id,
      });
      try {
        const { query } = JSON.parse(tc.function.arguments);
        tool.result = await wikipediaSearch(query);
        history.push({ role: 'tool', tool_call_id: tc.id, content: tool.result });
      } finally {
        tool.end();
      }
    }

    // LLM call 2: synthesize the final answer.
    const llm2 = weave.startLLM({ model: MODEL, providerName: 'openai' });
    try {
      const resp = await openaiClient.chat.completions.create({
        model: MODEL,
        messages: history,
      });
      const msg2 = resp.choices[0].message;
      llm2.output(msg2.content ?? '');
      llm2.usage = {
        inputTokens: resp.usage?.prompt_tokens,
        outputTokens: resp.usage?.completion_tokens,
      };
      history.push({ role: 'assistant', content: msg2.content });
      return msg2.content ?? null;
    } finally {
      llm2.end();
    }
  } finally {
    turn.end();
  }
}

const conversation = weave.startConversation({ agentName: 'research-bot' });
try {
  const history: any[] = [];
  for (const question of [
    'Who founded Anthropic?',
    'What is Claude (the AI assistant)?',
    'Summarize what we discussed in one sentence.',
  ]) {
    console.log(`USER: ${question}`);
    console.log(`AGENT: ${await runTurn(history, question)}\n`);
  }
} finally {
  conversation.end();
}