Ram-Dass-Love-Serve-Remember-Foundation/ramdass.io-dam-mcp
3.1
If you are the rightful owner of ramdass.io-dam-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Digital Asset Management Repository and Model Context Protocol Server for ramdass.io
ramdass.io DAM Repo / MCP Server
Digital Asset Management Repository and Model Context Protocol Server for ramdass.io
🆕 RAG System (Retrieval Augmented Generation)
Status: Phase 1 foundation complete, ready for deployment
The RAG system enables natural language search and Q&A across 22,978+ Intelligence Bank assets using AWS Bedrock.
- Architecture: 100% AWS-native (Titan embeddings + Claude Sonnet 4.5)
- Cost: FREE TIER embeddings, $0.16-$3.60 per query
- Context Window: 1M tokens (analyze 100-200+ assets simultaneously)
- Documentation: |
Quick Start
# 1. Verify prerequisites
python3 scripts/verify_rag_prerequisites.py
# 2. Apply database migration
psql -h $RDS_HOST -U $RDS_USER -d $RDS_DATABASE -f db/migrations/008_vector_tables.sql
# 3. Generate embeddings (one-time, ~30 minutes)
python3 scripts/generate_embeddings.py
# 4. Search assets
python3 scripts/semantic_search.py "meditation teachings"
# 5. Ask questions (RAG)
python3 scripts/rag_query.py "What did Ram Dass teach about service?"
Scripts
scripts/generate_embeddings.py- Generate vector embeddings via AWS Bedrock Titanscripts/semantic_search.py- Natural language search using vector similarityscripts/rag_query.py- Q&A using Claude Sonnet 4.5 with retrieved contextscripts/verify_rag_prerequisites.py- Check system prerequisites
See for complete implementation roadmap.