連接MongoDB: 將訊息寫入

# 插入一筆資料
from dotenv import load_dotenv
import os
from pymongo import MongoClient

load_dotenv()

endpoint = os.environ["mongo_endpoint"]
mongo_client = MongoClient(endpoint)
collection = mongo_client["mydatabase"]["mycollection"]

data = {
    "text":"Curry is MVP!!!",
    "embedding": [0.123, 0.234, 0.345],
}

collection.insert_one(data)

成功寫入囉!!

InsertOneResult(ObjectId('66b89520a949ac25a8082508'), acknowledged=True)

將user query和ai response 寫入DB中

from langchain_openai import AzureChatOpenAI
from langchain_core.messages import HumanMessage, SystemMessage
from dotenv import load_dotenv
import os

chat_model = AzureChatOpenAI(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment="gpt-4o",
    openai_api_version="2023-03-15-preview",
)

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser

str_parser =  StrOutputParser()
test_prompt = ChatPromptTemplate.from_messages(
    [
        ("system","你會回答所有問題"),
        ("human","{input}"),
    ])

test_chain = test_prompt | chat_model | str_parser

question = input("請輸入問題:")
print('question:', question)
response = test_chain.invoke({"input":question})
print('response:', response)

data = {
    'user_query': question,
    'ai_response': response
}

collection.insert_one(data)

question: 
response: 我會盡力回答你的問題。如果你有任何問題或需要幫助，請隨時告訴我！





InsertOneResult(ObjectId('66b88f7ba949ac25a80824ec'), acknowledged=True)

成功寫入MongoDB囉!!
那我們要如何連接前面所學的
將有memory的問答功能寫入到我們的DB中呢
下一章將來探討!