index_slack.py

import json
import os
import sys
from datetime import datetime, timedelta

import requests
from llama_index import VectorStoreIndex, StorageContext, download_loader

from channel_id_mapper import ChannelIdMapper

token = os.environ.get('SLACK_API_TOKEN')  # Retrieve your Slack API token from environment variables
fromDate = datetime.now() - timedelta(90)
index_root = './index'



def index_channels(channels, name_id_map):
    SlackReader = download_loader("SlackReader")
    loader = SlackReader(token, earliest_date=fromDate)
    for channel in channels:
        save_location = f"{index_root}/{channel}"
        if not os.path.exists(save_location):
            os.makedirs(save_location)
        documents = loader.load_data([name_id_map[channel]], reverse_chronological=True)
        storage_context = StorageContext.from_defaults()
        index = VectorStoreIndex.from_documents(documents=documents, storage_context=storage_context)
        storage_context.persist(save_location)


def main():
    if len(sys.argv) < 2:
        print('Usage: python3 index_slack.py channel1,channel2,channel3')
        exit(1)
    slack_token = os.environ.get('SLACK_API_TOKEN')
    if not slack_token:
        print('Please set the SLACK_API_TOKEN environment variable.')
        exit(1)
    channel_id_mapping = ChannelIdMapper(slack_token)
    channel_ids_to_index = []
    channels = sys.argv[1].split(',')
    for channel in channels:
        if channel not in channel_dict:
            print(f'Channel {channel} not found. Available channels: {channel_dict.keys()}')
            exit(1)
        channel_ids_to_index.append(channel_dict[channel])
    index_channels(channels, channel_dict)




if __name__ == '__main__':
    main()