- Updated slack-setup-guide.md with comprehensive Ollama setup instructions
- Added 6 new screenshots showing complete RAG workflow:
- Command setup, search results, and LLM responses for both queries
- Removed simulated LLM references, now uses real Ollama with llama3.2:1b
- Enhanced documentation with step-by-step Ollama installation
- Updated troubleshooting checklist to include Ollama-specific checks
- Fixed command syntax and added proper Ollama configuration
- Demonstrates working Slack RAG with real AI-generated responses
- Fixed CSV message parsing in slack_mcp_reader.py to properly handle individual messages
- Updated slack_rag.py to filter empty channel strings
- Enhanced slack-setup-guide.md with two new query examples:
- Advisor Models query: 'train black-box models to adopt to your personal data'
- Barbarians at the Gate query: 'AI-driven research systems ADRS'
- Replaced old screenshots with four new ones showing both query examples
- Updated documentation to use User OAuth Token (xoxp-) instead of Bot Token (xoxb-)
- Added proper command examples with --no-concatenate-conversations and --force-rebuild flags
- Change query from 'PUBPOL 290' to 'What is LEANN about?' for more challenging retrieval
- Update command to use python -m apps.slack_rag instead of test script
- Add expected response showing Yichuan Wang's LEANN announcement message
- Emphasize this demonstrates ability to find specific announcements in conversation history
- Update description to highlight challenging query capabilities
- Fix SlackMCPReader to use conversations_history instead of channels_list
- Add fallback imports for leann.interactive_utils and leann.settings
- Update slack-setup-guide.md with real screenshots and improved text
- Remove old screenshot files
- Embed screenshot videos/rag-sky-random.png
- Add step-by-step commands and notes
- Include helper test script tests/test_channel_by_id_or_name.py
- Redact example tokens from docs
- Add important section about inviting bot to channels before RAG queries
- Explain the 'not_in_channel' errors and their meaning
- Provide clear steps for bot invitation process
- Document realistic scenario where bot needs explicit channel access
- Update documentation to be more professional and less cursor-style
- Add detailed example of asking 'What is LEANN about?'
- Show retrieved messages from Slack channels
- Demonstrate intelligent answer generation based on context
- Add command example for running real RAG queries
- Explain the 4-step process: retrieve, index, generate, cite
- Create detailed setup guide with step-by-step instructions
- Add troubleshooting section for common issues like cache sync errors
- Include real terminal output example from successful integration
- Add screenshot showing VS Code interface with Slack channel data
- Remove excessive emojis for more professional documentation
- Document retry logic improvements and CLI arguments
- Add retry mechanism with exponential backoff for cache sync issues
- Handle 'users cache is not ready yet' errors gracefully
- Add max-retries and retry-delay CLI arguments for better control
- Create comprehensive Slack setup guide with troubleshooting
- Update README with link to detailed setup guide
- Improve error messages and user experience
