When I was testing how the ConversationBufferMemory() works in VSCode, I noticed I didn't get any output from the >Finished chain when I wasn't specifying any models in the llm variable, but when I did specify 'gpt-3.5-turbo' I got the following error
"This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?', 'type': 'invalid_request_error', 'param': 'model', 'code': None}}"
This is the code that I have written without specifying the llm model:
import os
from apikey import apikey
from langchain_openai import OpenAI
from langchain.chains.conversation.memory import ConversationBufferMemory
from langchain.chains import ConversationChain
os.environ['OPENAI_API_KEY'] = apikey
llm = OpenAI(
model="davinci-002",
temperature=0.9)
memory = ConversationBufferMemory()
conversation = ConversationChain(
llm=llm,
verbose=True,
memory=memory
)
conversation.predict(input="Hi, how are you?")
Any idea why I'm not getting any output from the
Finished Chain?