add slack bot

docs/chatGPT/CDDR.md

@@ -957,3 +957,116 @@ if __name__ == "__main__":
 ```
 
 以上代码示例为参考，其中某些变量名可能需要替换或者直接以 URL 给出，供参考。
+
+---
+
+You
+---
+
+
+
+I want to create a slack bot, when user @ this bot and send a message, this bot can response the user something text message, can u give me how to implement this bot?
+
+ChatGPT
+-------
+
+Certainly, I can help you with that! Here are the steps to create a Slack bot that responds to messages:
+
+1.  Create a new bot in Slack by going to [https://api.slack.com/apps](https://api.slack.com/apps) and clicking on "Create New App".
+2.  Give your app a name and select the workspace where you want to create the bot.
+3.  Click on "Bot" in the menu on the left-hand side, and then click on "Add a Bot User". This will create a bot user for your app.
+4.  Copy the bot user OAuth access token that Slack gives you. You will need this in order to authenticate your code when communicating with Slack.
+5.  Next, create a new file and name it something like `bot.py` or `slackbot.py`.
+6.  In your Python code, import the `slack-sdk` and `slack-bolt` packages:
+
+```python
+from slack_sdk import WebClient
+from slack_bolt import App
+```
+
+7.  Create a new instance of the `WebClient` class using the bot user OAuth access token:
+
+```python
+client = WebClient(token="YOUR_TOKEN_HERE")
+```
+
+8.  Create a new instance of the `App` class:
+
+```python
+app = App(token="YOUR_TOKEN_HERE")
+```
+
+9.  Define a function that the bot will use to respond to messages. This function should take in a `payload` argument containing information about the message that was sent to the bot. For example:
+
+```python
+def handle_message(payload):
+    message = payload["event"]["text"]
+    channel_id = payload["event"]["channel"]
+
+    if "hello" in message.lower():
+        response = "Hi there!"
+        client.chat_postMessage(channel=channel_id, text=response)
+```
+
+10.  Use the `App` class to define a route that the bot will use to listen for messages. The route should be triggered whenever a user sends a message that starts with the bot's name or mention, using the `@` symbol. For example:
+
+```python
+@app.event("app_mention")
+def handle_mention(payload):
+    handle_message(payload)
+```
+
+11.  Run the application using `app.run()`. This will start the bot and allow it to listen for messages.
+
+That's it! Your bot is now ready to respond to messages in Slack. Of course, you can modify the `handle_message` function to include any other logic you'd like your bot to have.
+
+You
+---
+
+
+
+actually I want to use flask to integrate with the slack event, how to do that?
+
+ChatGPT
+-------
+
+Sure, I can help you with that!
+
+Here's an overview of how to create a Slack bot using Flask:
+
+1.  Create a bot in your Slack Workspace: Go to [https://api.slack.com/apps](https://api.slack.com/apps) and create a new app or select an existing one. Then create a "Bot User" under the "Bot Users" section.
+
+2.  Install the Bot in your workspace: After creating the bot user, you should install the bot in one or more of your Slack channels. To do this go to the "Install App" section under settings.
+
+3.  Setup Flask environment: Open up your terminal or command prompt, and create a new folder for your project. Navigate into the folder, and create a virtual environment by running the command `python -m venv env`. Activate your virtual environment by running `source env/bin/activate` on Mac/Linux or `.\env\Scripts\activate` on Windows.
+
+4.  Install Dependencies: With your virtual environment activated, you need to install flask and slack-sdk modules. You can do that by running `pip install flask slack-sdk`
+
+5.  Implement Flask Application: Create a new python file (i.e., `app.py`) inside your project folder having the following code:
+
+
+```python
+from slack_bolt import App # Importing Slack Bolt
+
+app = App(token="xoxb-<your-bot-token>", signing_secret="<your-signing-secret>")
+
+@app.event("app_mention")
+def handle_mentions(context):
+    print(context)
+
+if __name__ == "__main__":
+    app.start(port=5000) # Run Flask server
+```
+
+Note: Replace `xoxb-<your-bot-token>` with your Bot User OAuth Access Token value, and `<your-signing-secret>` with your Signing Secret value which can be found in the Slack App Credentials.
+
+6.  Start Your Flask App: Run the application by executing `python app.py` in your terminal. This will start a Flask server listening on port 5000.
+
+7.  Configure Event Subscription: Go to your App's configuration page and enable `Event Subscriptions`. Using `Request URL`, enter your Ngrok URL concatenated with `/slack/events` (e.g., "[https://example.ngrok.io/slack/events](https://example.ngrok.io/slack/events)").
+
+8.  Subscribe to Bot Events: Under Event Subscription, subscribe to `app_mention` event.
+
+9.  Testing: Go to one of the Slack channels where you installed the bot and mention it in a message. The bot should respond with a message as handled in the `handle_mentions()` function.
+
+
+That's it! You have successfully created a Slack bot and integrated it with Flask. You can modify the `handle_mentions()` function to do something according to your requirements.

requirements.txt

@@ -4,4 +4,6 @@ llama-index==0.4.24
 httpx==0.23.3
 requests==2.28.2
 openai==0.27.1
-trafilatura==1.4.1
+trafilatura==1.4.1
+slackclient==2.9.4
+slackeventsapi==3.0.1

server.py

@@ -2,14 +2,21 @@
 import re
 import os
 import openai
+import slack
+from slackeventsapi import SlackEventAdapter
 from llama_index import GPTSimpleVectorIndex, LLMPredictor, TrafilaturaWebReader
 from langchain.chat_models import ChatOpenAI
 
+app = Flask(__name__)
+
 OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
 openai.api_key = OPENAI_API_KEY
 
-app = Flask(__name__)
+SLACK_TOKEN = os.environ.get('SLACK_TOKEN')
+SLACK_SIGNING_SECRET = os.environ.get('SLACK_SIGNING_SECRET')
+slack_event_adapter = SlackEventAdapter(SLACK_SIGNING_SECRET, '/slack/events', app)
 
+client = slack.WebClient(token=SLACK_TOKEN)
 
 def insert_space(text):
 
@@ -38,10 +45,7 @@ def extract_urls(text):
             urls.append(word)
     return urls
 
-
-@app.route('/chat', methods=['POST'])
-def chat():
-    message = request.json['message']
+def get_answer_from_chatGPT(message):
     message_normalized = insert_space(message)
     urls = extract_urls(message_normalized)
     if len(urls) > 0:
@@ -56,10 +60,22 @@ def chat():
         )
         print(completion.usage)
         response = completion.choices[0].message.content
+    return response
 
-    response = {"response": f"{response}"}
+@app.route('/chat', methods=['POST'])
+def chat():
+    response = {"response": f"{get_answer_from_chatGPT(request.json['message'])}"}
     return jsonify(response)
 
+@slack_event_adapter.on('app_mention')
+def handle_mentions(payload):
+    event = payload.get('event', {})
+    channel = event.get('channel')
+    user = event.get('user')
+    text = event.get('text')
+    user_message = text.replace('@my-gpt-reader-bot', '')
+    client.chat_postMessage(channel=channel, link_names=1, text=f'<@{user}>, ' + get_answer_from_chatGPT(user_message))
+
 
 if __name__ == '__main__':
     app.run(debug=True)