I'm looking for a simple chat example

[jsmith173]

Hi,

I'm looking for a simple chat example without streaming mode in Python.

[dosubot[bot]]

from langchain_core.messages import HumanMessage, SystemMessage
from langchain_community.chat_models import ChatPremAI
import os
import getpass

# Set up API key
if "PREMAI_API_KEY" not in os.environ:
    os.environ["PREMAI_API_KEY"] = getpass.getpass("PremAI API Key:")

# Initialize the chat client
chat = ChatPremAI(project_id=1234, model_name="gpt-4o")

# Create messages
system_message = SystemMessage(content="You are a friendly assistant.")
human_message = HumanMessage(content="Who are you?")

# Invoke the chat model
response = chat.invoke([system_message, human_message])
print(response.content)

^[1]

To continue talking to Dosu, mention @dosu.

[jsmith173]

@dosu I want to use Ollama

[dosubot[bot]]

To use Ollama for a simple chat example in Python, you can follow this code snippet:

from langchain_community.chat_models import ChatOllama

# Initialize the chat client
llm = ChatOllama(model="llama3-groq-tool-use")

# Create messages
messages = [
    ("system", "You are a friendly assistant."),
    ("human", "Who are you?")
]

# Invoke the chat model
response = llm.invoke(messages)
print(response)

Make sure you have the Ollama server running locally. You can download it here ^[1][2].

To continue talking to Dosu, mention @dosu.

[jsmith173]

@dosu I'm using

model = Ollama(model='llama3.1')

Please modify your code

[dosubot[bot]]

from langchain_community.chat_models import Ollama

# Initialize the chat client
model = Ollama(model='llama3.1')

# Create messages
messages = [
    ("system", "You are a friendly assistant."),
    ("human", "Who are you?")
]

# Invoke the chat model
response = model.invoke(messages)
print(response)

To continue talking to Dosu, mention @dosu.

[jsmith173]

@dosu : I'd like to use OpenAI also. Please modify the code so I can use OpenAI also.

[dosubot[bot]]

To use both OpenAI and Ollama in your chat example, you can modify the code as follows:

from langchain_community.chat_models import Ollama
from langchain_openai import ChatOpenAI
import os

# Ensure API keys are set in environment variables
if "OPENAI_API_KEY" not in os.environ:
    raise ValueError("OpenAI API key must be set in environment variables.")

# Initialize the chat clients
ollama_model = Ollama(model='llama3.1')
openai_model = ChatOpenAI(model="gpt-3.5-turbo")

# Create messages
messages = [
    ("system", "You are a friendly assistant."),
    ("human", "Who are you?")
]

# Invoke the Ollama chat model
ollama_response = ollama_model.invoke(messages)
print("Ollama response:", ollama_response)

# Convert messages to OpenAI format
openai_messages = [
    {"role": role, "content": content} for role, content in messages
]

# Invoke the OpenAI chat model
openai_response = openai_model.invoke(openai_messages)
print("OpenAI response:", openai_response)

Make sure you have the langchain-openai package installed and your OpenAI API key set as an environment variable (OPENAI_API_KEY) ^[1][2][3].

To continue talking to Dosu, mention @dosu.