Utilize configurable_alternatives to provide alternate chat models

[carolinebridge]

Discovered while poking around documentation -- the .configurable_alternatives() method may be useful to permit the user to leverage different LLM's based on preference/configuration. Would replace current method in the codebase / might be cleaner. Code example from weblangchain repo:

if has_google_creds:
    llm = ChatOpenAI(
        model="gpt-3.5-turbo-16k",
        # model="gpt-4",
        streaming=True,
        temperature=0.1,
    ).configurable_alternatives(
        # This gives this field an id
        # When configuring the end runnable, we can then use this id to configure this field
        ConfigurableField(id="llm"),
        default_key="openai",
        anthropic=ChatAnthropic(
            model="claude-2",
            max_tokens=16384,
            temperature=0.1,
            anthropic_api_key=os.environ.get("ANTHROPIC_API_KEY", "not_provided"),
        ),
        googlevertex=ChatVertexAI(
            model_name="chat-bison-32k",
            temperature=0.1,
            max_output_tokens=8192,
            stream=True,
        ),
    )