You can use the chat completion endpoint with LangChain’s ChatOpenAI LLM under two lines of code change.

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.keywordsai.co/api/",
    api_key="<Your Keywords AI API Key>",
    model="gpt-3.5-turbo",
    streaming=True,
    extra_body={
        "customer_identifier": "customer_11"
    }
)
response = llm.invoke(
    input="Hi"
)
print(response)

In extra_body, you can pass in any OpenAI parameters.

To use Keywords AI parameters, you can specify an extra_body object within model_kwargs. In the above example, customer_identifier is the Keywords AI parameter. These parameters will take precedence over the OpenAI parameters if they are conflicting.