DEV Community

artydev
artydev

Posted on

1

The smallest chatbot implementation using Langchain Ollama, and Python

Thanks to : Understand Ollama and LangChain Chat History in 10 minutes

from langchain_community.llms import Ollama
from langchain_core.messages import HumanMessage, AIMessage
from langchain_core.prompts import ChatPromptTemplate,  MessagesPlaceholder

llm = Ollama(model = "llama3")

chat_history = []

chat_history = [
    ("human","My name is John")
]

prompt_template = ChatPromptTemplate.from_messages([
    ("system","your name is HAL, greeet user and answer questions with simple responses"),
    MessagesPlaceholder(variable_name= "chat_history"),
    ("human","{input}")
])

chain = prompt_template | llm

def  main ():
    while True:
        question = input("You : ")
        if question == "done":
            return
        response = chain.invoke({"input" : question,  "chat_history": chat_history})
        chat_history.append(HumanMessage(content=question))
        chat_history.append(AIMessage(content=response))

        print("AI  : " + response)

if __name__ == "__main__":
    main()
Enter fullscreen mode Exit fullscreen mode

Example of discussion:

Image description

Image of Timescale

🚀 pgai Vectorizer: SQLAlchemy and LiteLLM Make Vector Search Simple

We built pgai Vectorizer to simplify embedding management for AI applications—without needing a separate database or complex infrastructure. Since launch, developers have created over 3,000 vectorizers on Timescale Cloud, with many more self-hosted.

Read full post →

Top comments (0)

Image of Docusign

🛠️ Bring your solution into Docusign. Reach over 1.6M customers.

Docusign is now extensible. Overcome challenges with disconnected products and inaccessible data by bringing your solutions into Docusign and publishing to 1.6M customers in the App Center.

Learn more