Skip to content

13 LLM Frameworks

LangChain

  • Fully featured, powerful and heavyweight framework. 
    1
2
3
4
5
6
    from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model='gpt-5-mini')
response = llm.invoke(tell_a_joke)

display(Markdown(response.content))

LiteLLM

  • Quick and lightweight framework.
  • Has a built in pro feature call Prompt Caching where same / similar subsequent queries to the LLM will cost cheaper due to caching. 
     1
 2
 3
 4
 5
 6
 7
 8
 9
10
    from litellm import completion
response = completion(model='gpt-5-mini', messages=tell_a_joke)
response_content = response.choices[0].message.content
display(Markdown(response_content))

# Usage statistics
print(f'Input tokens: {response.usage.prompt_tokens}')
print(f'Output tokens: {response.usage.completion_tokens}')
print(f'Total tokens: {response.usage.total_tokens}')
print(f'Total cost: {response._hidden_params['response_cost']*100:.4f} cents.')