First Steps in AI Engineering: Building a Simple CLI Chatbot

Описание и применение

Минимальный CLI‑чат‑бот на Python с использованием Anthropic Claude, ограничением токенов и сохранением истории диалога.

Задача

Build a lightweight, turn‑based chatbot without heavy frameworks, while managing token usage and ensuring deterministic greetings.

Результат

A minimal, cost‑aware CLI chatbot that can converse with Claude‑Sonnet‑5, print responses, and maintain conversation history.

Рабочий процесс

• Install Anthropic Python library
• Import os and Anthropic
• Set ANTHROPIC_API_KEY in environment
• Define SYSTEM_PROMPT and STARTING_MESSAGE
• Prompt user for input
• Create messages list with assistant greeting and user question
• Instantiate Anthropic client with api_key
• Call client.messages.create with system, messages, model, max_tokens
• Iterate over response.content blocks to extract text
• Print assistant response
• Append assistant response to messages list for next turn

Доказательства

I wanted to organise myself by placing the constants in one area, and I knew I needed to starting directive for the client/chatbot to know the whole context

Источник

response = client.messages.create(max_tokens=1024, system=SYSTEM_PROMPT, messages=messages, model="claude-sonnet-5")

Источник