refactor!: Simplify Output Parsers

[davidmigloz]

Relates to #266

The BaseOutputParser class has been reworked. Before it was strongly coupled to LLMs/ChatModels and they could not be used with other types of Runnables. You couldn't pass options to the parser either.

Now the BaseOutputParser takes 3 generic parameters:

• ParserInput (extends Object?): the type of the input to the parser.
• CallOptions (extends OutputParserOptions): the type of the options to pass to the parser.
• ParserOutput (extends Object?): the type of the output of the parser.

Migration guide

StringOutputParser

You now have to specify in input type in the generic parameter of StringOutputParser.

If you were using a StringOutputParser with an llm (e.g. OpenAI):

Before:

const outputParser = StringOutputParser<String>();

After:

const outputParser = StringOutputParser<LLMResult>();

If you were using a StringOutputParser with a Chat Model (e.g. ChatOpenAI):

Before:

const outputParser = StringOutputParser<AIChatMessage>();

After:

const outputParser = StringOutputParser<ChatResult>();

If you were using a StringOutputParser defined inside the chain, the generic type will still be inferred automatically:

final chain = promptTemplate.pipe(model).pipe(StringOutputParser());