Add ChatGPT RAG support - resolves #40

Browse Source

- Implement ChatGPTReader for parsing HTML/ZIP exports from ChatGPT
- Add chatgpt_rag.py following BaseRAGExample pattern
- Support both concatenated conversations and individual messages
- Handle multiple input formats (.html, .zip, directories)
- Include comprehensive error handling and user guidance
- Add metadata extraction (titles, timestamps, roles)
- Integrate with existing LEANN chunking and embedding systems

Features:
✅ HTML parsing from ChatGPT exports
✅ ZIP file extraction support
✅ Conversation detection and structuring
✅ Message role identification (user/assistant)
✅ Metadata extraction and preservation
✅ Dual processing modes
✅ Command-line interface with all LEANN options
✅ Comprehensive error handling
✅ Multiple input format support

Usage:
python -m apps.chatgpt_rag --export-path chatgpt_export.html
python -m apps.chatgpt_rag --export-path chatgpt_export.zip --query 'Python help'

...

This commit is contained in:

aakash

2025-09-29 01:44:32 -07:00

parent 5f7806e16f

commit be17980114

3 changed files with 599 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

apps/chatgpt_data/__init__.py Normal file