1. Agent Loop With LangChain
1.1. Resources
1.2. Set up env
- 添加依赖
uv add langchain langchain-ollama langchain-openai python-dotenv black isort
- Add
.env
OPENAI_API_KEY=xxxx
LANGSMITH_TRACING=true
LANGSMITH_API_KEY=xxxx
LANGSMITH_PROJECT=product-agent
Install qwen3 by ollama
- 打开qwen3,可以看到所有的models,我们选择下载
qwen3:1.7b - 命令行执行:
ollama pull qwen3:1.7b 运行
qwen3:1.7b:ollama run qwen3:1.7b>>> Hello Thinking... Okay, the user said "Hello" so I should respond politely. Let me check the previous messages to make sure I'm consistent. The user hasn't provided any specific context yet, so I should keep it general. Maybe start with a greeting and offer help. Let me make sure the tone is friendly and open-ended. I'll say something like, "Hello! How can I assist you today?" That sounds good. No need for any extra details unless the user mentions something specific. Keep it simple and welcoming. ...done thinking. Hello! How can I assist you today? >>> /bye- 启动
ollama:ollama serve
- 打开qwen3,可以看到所有的models,我们选择下载
1.3. Add tools
from langchain.tools import tool
# --- Tools (Langchain @tool decorator) ---
@tool
def get_product_price(product: str) -> float:
"""Look up the price of a product in the catalog."""
print(f" >> Executing get_product_price(product='{product}')")
prices = {"laptop": 1299.99, "headphones": 149.95, "keyboard": 89.50}
return prices.get(product, 0)
@tool
def apply_discount(price: float, discount_tier: str) -> float:
"""Apply a discount tier to a price and return the final price.
Available tiers: bronze, silver, gold."""
print(f" >> Executing apply_discount(price={price}, discount_tier='{discount_tier}')")
discount_percentages = {"bronze": 5, "silver": 12, "gold": 23}
discount = discount_percentages.get(discount_tier, 0)
return round(price * (1 - discount / 100), 2)
1.4. Using LangChain And Defensive Prompting
from langchain.chat_models import init_chat_model
from langchain_core.messages import HumanMessage, SystemMessage, ToolMessage
from langsmith import traceable
MAX_ITERATIONS = 10
MODEL = "qwen3:1.7b"
# --- Agent Loop ---
@traceable(name="LangChain Agent Loop")
def run_agent(question: str):
tools = [get_product_price, apply_discount]
tools_dict = {t.name: t for t in tools}
llm = init_chat_model(f"ollama:{MODEL}", temperature=0)
llm_with_tools = llm.bind_tools(tools)
print(f"Question: {question}")
print("=" * 60)
messages = [
SystemMessage(
content=(
"You are a helpful shopping assistant. "
"You have access to a product catalog tool "
"and a discount tool.\n\n"
"STRICT RULES — you must follow these exactly:\n"
"1. NEVER guess or assume any product price. "
"You MUST call get_product_price first to get the real price.\n"
"2. Only call apply_discount AFTER you have received "
"a price from get_product_price. Pass the exact price "
"returned by get_product_price — do NOT pass a made-up number.\n"
"3. NEVER calculate discounts yourself using math. "
"Always use the apply_discount tool.\n"
"4. If the user does not specify a discount tier, "
"ask them which tier to use — do NOT assume one."
)
),
HumanMessage(content=question),
]
for iteration in range(1, MAX_ITERATIONS + 1):
print(f"\n--- Iteration {iteration} ---")
ai_message = llm_with_tools.invoke(messages)
tool_calls = ai_message.tool_calls
# If no tool calls, this is the final answer
if not tool_calls:
print(f"\nFinal Answer: {ai_message.content}")
return ai_message.content
# Process only the FIRST tool call — force one tool per iteration
tool_call = tool_calls[0]
tool_name = tool_call.get("name")
tool_args = tool_call.get("args", {})
tool_call_id = tool_call.get("id")
print(f" [Tool Selected] {tool_name} with args: {tool_args}")
tool_to_use = tools_dict.get(tool_name)
if tool_to_use is None:
raise ValueError(f"Tool '{tool_name}' not found")
observation = tool_to_use.invoke(tool_args)
print(f" [Tool Result] {observation}")
messages.append(ai_message)
messages.append(
ToolMessage(content=str(observation), tool_call_id=tool_call_id)
)
print("ERROR: Max iterations reached without a final answer")
return None
if __name__ == "__main__":
print("Hello LangChain Agent (.bind_tools)!")
print()
result = run_agent("What is the price of a laptop after applying a gold discount?")
1.5. Run and View LangSmith

1.6. 工程代码
- git@gitee.com:learnany/langchain.git
- project/product-agent-loop-in-langchain
更新日期:11/17/2026