ChatOpenAI

This notebook covers how to get started with OpenAI chat models.

from langchain_core.messages import HumanMessage, SystemMessage
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

API Reference:

• HumanMessage
• SystemMessage
• ChatPromptTemplate
• ChatOpenAI

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)

The above cell assumes that your OpenAI API key is set in your environment variables. If you would rather manually specify your API key and/or organization ID, use the following code:

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0, api_key="YOUR_API_KEY", openai_organization="YOUR_ORGANIZATION_ID")

Remove the openai_organization parameter should it not apply to you.

messages = [
    ("system", "You are a helpful assistant that translates English to French."),
    ("human", "Translate this sentence from English to French. I love programming."),
]
llm.invoke(messages)

AIMessage(content="J'adore programmer.", response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 34, 'total_tokens': 40}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-8591eae1-b42b-402b-a23a-dfdb0cd151bd-0')

Chaining

We can chain our model with a prompt template like so:

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant that translates {input_language} to {output_language}.",
        ),
        ("human", "{input}"),
    ]
)

chain = prompt | llm
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)

AIMessage(content='Ich liebe Programmieren.', response_metadata={'token_usage': {'completion_tokens': 5, 'prompt_tokens': 26, 'total_tokens': 31}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-94fa6741-c99b-4513-afce-c3f562631c79-0')

Tool calling

OpenAI has a tool calling (we use "tool calling" and "function calling" interchangeably here) API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool. tool-calling is extremely useful for building tool-using chains and agents, and for getting structured outputs from models more generally.

ChatOpenAI.bind_tools()

With ChatOpenAI.bind_tools, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to an OpenAI tool schemas, which looks like:

{
    "name": "...",
    "description": "...",
    "parameters": {...}  # JSONSchema
}

and passed in every model invocation.

from langchain_core.pydantic_v1 import BaseModel, Field


class GetWeather(BaseModel):
    """Get the current weather in a given location"""

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")


llm_with_tools = llm.bind_tools([GetWeather])

ai_msg = llm_with_tools.invoke(
    "what is the weather like in San Francisco",
)
ai_msg

AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_H7fABDuzEau48T10Qn0Lsh0D', 'function': {'arguments': '{"location":"San Francisco"}', 'name': 'GetWeather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 70, 'total_tokens': 85}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b469135e-2718-446a-8164-eef37e672ba2-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco'}, 'id': 'call_H7fABDuzEau48T10Qn0Lsh0D'}])

AIMessage.tool_calls

Notice that the AIMessage has a tool_calls attribute. This contains in a standardized ToolCall format that is model-provider agnostic.

ai_msg.tool_calls

[{'name': 'GetWeather',
  'args': {'location': 'San Francisco'},
  'id': 'call_H7fABDuzEau48T10Qn0Lsh0D'}]

For more on binding tools and tool call outputs, head to the tool calling docs.

Fine-tuning

You can call fine-tuned OpenAI models by passing in your corresponding modelName parameter.

This generally takes the form of ft:{OPENAI_MODEL_NAME}:{ORG_NAME}::{MODEL_ID}. For example:

fine_tuned_model = ChatOpenAI(
    temperature=0, model_name="ft:gpt-3.5-turbo-0613:langchain::7qTVM5AR"
)

fine_tuned_model(messages)

AIMessage(content="J'adore la programmation.", additional_kwargs={}, example=False)