LangChain – Ollama Model Running On Local


LangChain – Ollama Model Installation

How To Install Ollama Model In Local ?

(2) How To Test The Installation

https://ollama.com/
ollama – version
ollama pull smollm:135m

(3) Making Of Agentic AI

from langchain.agents import create_agent

def get_weather(city:'str')->str:
    "Get The Weather Of The Given City"
    return f"Its Sunny In {city}"
    
agent = create_agent(
        model="ollama:smollm:135m",
        tools=[get_weather]
        system_prompt = "You are an helpful Assistant"
        )

result = agent.invoke(
{"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
    
print(result.content)

(4) Install qwen3:0.6b Model Which Support Tool Calling

ollama pull qwen3:0.6b
from langchain.agents import create_agent

def get_weather(city:str)->str:
    """Get The Weather Of The Given City"""
    return f"Its Always Sunny In {city}"

agent = create_agent(
        model="ollama:qwen3:0.6b"
        tools = [get_weather]
        system_prompt = "You Are An Helpful AI Assistant"
        )

response = agent.invoke({"message": ["role": "user", "content": "What Is The Weather Of  Bhubaneswar"]})

print(response['message'][-1].content_block)
[{'type': 'text', 'text': 'The weather in  Bhubaneswar is **Sunny**. Let me know if you need updates! 🌤️'}]

Leave a Reply

Your email address will not be published. Required fields are marked *