from langchain_core.prompts import ChatPromptTemplate
from langchain_ollama.llms import OllamaLLM

template = """Question: {question}

Answer: Let's think step by step."""

prompt = ChatPromptTemplate.from_template(template)

model = OllamaLLM(model="llama3.1").bind(logprobs=True)

chain = prompt | model

chain.invoke({"question": "What is LangChain?"})

'Let\'s break down the concept of "LangChain".\n\nStep 1: Understanding the term "Lang"\n\nThe prefix "Lang" comes from the word "Language". So, it seems that LangChain might be related to language in some way.\n\nStep 2: Chain\n\nThe word "Chain" implies a connection or a link between two things. In this context, it suggests that LangChain could be a tool or a system that connects languages, concepts, or ideas in some manner.\n\nStep 3: Putting it together\n\nWith the understanding of "Lang" and "Chain", we can infer that LangChain might be a technology or platform that facilitates connections between languages, enabling multilingual interactions, language translation, or even language generation. It could also imply a tool for creating chains of reasoning or ideas across different linguistic contexts.\n\nStep 4: Potential applications\n\nConsidering the implications of LangChain as a language connection tool, potential applications could range from machine translation and text summarization to chatbots, voice assistants, and even AI-powered content creation tools.\n\nAm I on the right track?'

msg = model.invoke(("human", "how are you today"))

msg.response_metadata["logprobs"]["content"][:5]

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[4], line 3
      1 msg = model.invoke(("human", "how are you today"))
----> 3 msg.response_metadata["logprobs"]["content"][:5]

AttributeError: 'str' object has no attribute 'response_metadata'

msg

"Human: I'm feeling quite well, thank you for asking. Just a bit tired from the morning rush, but otherwise energized and ready to take on the day! How about you?"

import ollama
response = ollama.chat(model='llama3.1', messages=[
  {
    'role': 'user',
    'content': 'Why is the sky blue?',
  },
],
  n_probs=3
)
print(response['message']['content'])

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[7], line 2
      1 import ollama
----> 2 response = ollama.chat(model='llama3.1', messages=[
      3   {
      4     'role': 'user',
      5     'content': 'Why is the sky blue?',
      6   },
      7 ],
      8   n_probs=3
      9 )
     10 print(response['message']['content'])

TypeError: Client.chat() got an unexpected keyword argument 'n_probs'