###### tags: `AWS Learning Group`

# 20221215 Line-bot + chatGPT

前言
> 12/1 OpenAI 釋出chatGPT，短短一週就破百萬用戶，使用者可以在OpenAI提供的Web聊天室跟chatGPT聊天，可想而知，這樣的模式不太方便，所以本次Lab要延續LineBot，教大家將chatGPT串在一起，讓使用者可以透過Line跟chatGPT聊天。

<!-- ABOUT THE PROJECT -->
## System Overview

本次目標:
* LINE bot + OpenAI **chatGPT**
* **Serverless Framework** = Cli for API Gateway + Lambda

<!-- GETTING STARTED -->
## Getting Started
準備以下
1. [Create a Line bot](https://developers.line.biz/en/)

Channel_access_token=
Channel_secret=

3. [Create an OpenAI Account](https://chat.openai.com/auth/login)

Email=
Password=

2. 點擊AWS右上角User / Security credentials / Access keys

AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=

## Development
1. Install **Serverless Framework**

export AWS_ACCESS_KEY_ID=
export AWS_SECRET_ACCESS_KEY=
npm install serverless -g

2. Use **Serverless Framework** to create a project based on AWS

serverless create --template aws-python --path aws-line-chatGPT-bot

3. Go to repository

in ```handler.py``` (Serverless Framework 主程式)

    line_bot_api = LineBotApi(__Channel_access_token__)
    handler = WebhookHandler(__Channel_secret__)

in ```config.json``` (放你的 OpenAI Email & Password)

    {
    "email": "",
    "password": ""
    }

in ```requirement.txt```
- line-bot dependency
- tls client dependency

in ```chatgpt.py```
- python API client for chatGPT

in ```error.py```
- define some error msg
4. First time need to upload config.json to S3
1. Go to IAM create a role for lambda to access s3
- create a role: load-from-s3

Add two official policy

        AWSXRayDaemonWriteAccess
        AWSLambdaBasicExecutionRole

Create a custom inline permission : read-write-from-chatgpt-config

        {
            "Version": "2012-10-17",
            "Statement": [
                {
                    "Sid": "ExampleStmt",
                    "Action": [
                        "s3:GetObject",
                        "s3:PutObject"
                    ],
                    "Effect": "Allow",
                    "Resource": [
                        "arn:aws:s3:::chatgpt-config/*"
                    ]
                }
            ]
        }

3. Go to s3
- create a bucket: chatgpt-config
- upload ```config.json```
5. Use **Serverless Framework** to pack python dependency

pip install -r requirement
sls plugin install -n serverless-python-requirements

6. Use **Serverless Framework** to deploy whole project to AWS
in ```severless.yml```

    service: aws-line-chatGPT-bot
    provider:
      name: aws
      stage: dev
      region: us-east-1
      runtime: python3.9
      role: arn:aws:iam::XXXXXXXXXXXXXXXXX

    functions:
      line_bot:
        handler: handler.webhook
        events:
          - http:
              path: /webhook
              method: POST

    plugins:
      - serverless-python-requirements

serverless deploy

## AWS Lambda
- Go to Lambda to set timeout: 1min
## Debug technique
CloudWatch
- Utilized ```print()``` in your code and you'll see on CloudWatch.
## Reference
1. [上週 LineAPI + aws](https://hackmd.io/@hjQzzIhhQLq_F0m9RyygQA/BJElmrewj)
2. [Serverless Framework](https://www.serverless.com/)
3. [labteral/chatgpt-python](https://github.com/labteral/chatgpt-python)