Add @spaces.GPU decorator to fix HF Spaces runtime error

Fix HF Spaces _griffe import error with truly lazy loading

Add HuggingFace Spaces deployment documentation

Add pre-computed embeddings for HF Spaces deployment

Fix HuggingFace Spaces deployment and add GPT-5 support

Implement proper async parallelism for multi-agent pipeline

Fix HuggingFace Spaces import error with lazy loading

Update README and enhance query processing with logging and error handling

Refactor Gradio UI components and add configuration class for improved maintainability

Add example query selection to trigger processing in Gradio UI

Add show_progress and run_on_click to fix subsequent query issues

Add GPU decorator with 60s duration to keep GPU alive

Remove GPU decorator to fix double-click issue on HuggingFace

Add Enter key trigger for query submission

Fix f-string backslash syntax error in explanation formatting

Fix Gradio button configuration to include outputs and function for query processing

Enhance query processing with detailed chunk explanations and improve UI layout

Add HuggingFace Spaces GPU decorator to suppress startup warning

Disable HF token for CrossEncoder to avoid auth errors with invalid tokens

Fix CrossEncoder API - use 'token' parameter instead of deprecated 'use_auth_token'

Add HuggingFace token support for cross-encoder model loading

Fix NameError in app_simple.py - use json_path instead of undefined doc_store_path

Force HuggingFace to pull latest __init__.py with optional OpenSearch imports

Trigger HuggingFace rebuild - ensure app.py uses app_simple

Fix imports to avoid OpenSearch dependencies in memory-only mode

Add app_multi.py for multi-agent pipeline and update README to document both versions

Update app.py to use fast simple version instead of multi-agent pipeline

Update UI title and description for the Gradio interface; change from "BFH Email Assistant (Fast Mode)" to "BFH Studadmin Assist" for clarity.

Update requirements and enhance MemoryRetriever with cross-encoder reranking; improve retrieval logic and logging

Refactor document ingestion and processing; update configurations for chunking and retrieval, enhance error logging, and implement markdown-aware chunking

Add SimpleFastAssistant for single LLM call processing; implement document loading, indexing, and Gradio UI for enhanced performance

Update dependencies and refactor agent initialization; add optional fact-check skipping for performance improvements

Refactor RAG Email Assistant for in-memory processing; update configurations, implement memory indexing and retrieval, enhance Gradio UI, and streamline document ingestion.

Implement modular RAG email assistant architecture

Add CLAUDE.md for project guidance and architecture overview

Create rag_email_assistant_haystack_2_pydantic_ai_gradio_modular_2025_baseline.py

Create RAG_Email_Assistant_Specifications_v1.0.md

Create .gitignore

Add administrative documents and forms with Git LFS

Add requirements.txt with initial package dependencies

Update README.md

initial commit

Duplicate from gradio-templates/chatbot