Chat with OpenAI in LangChain - #5

With the advent of OpenAI's Chat-GPT API endpoint (ChatCompletion), LangChain quickly added support for the new endpoint. Unlike previous LLM endpoints, the chat endpoint takes multiple inputs and so has its own unique set of objects and methods.

OpenAI's `ChatCompletion` endpoint consumes three types of input:

- System message — this acts as an initial prompt to "setup" the behavior of the chat completion.
- Human messages — these are human prompts (both current and past) that are fed into …

api behavior chat endpoints gpt human langchain llm messages multiple objects openai prompt responses set setup support types