How rclalithkumar/prism works
PRISM is a local AI digital twin: users ask questions in the Streamlit chat, relevant saved memories are retrieved by semantic similarity, and Ollama generates a personalized-context answer. The sidebar also lets users add memories and clear chat. The main app keeps UI, retrieval, embedding, LLM requests, and JSON persistence in one file; prism_demo.py is a separate earlier prototype. Relationships reflect the sampled pp4.py implementation and README; the prototype’s internal wiring is not fully evidenced.
Main entry points: pp4.py Chat interface
Components 8
Chat application
- Chat interface
pp4.py
Memory and retrieval
- Memory retrieval
pp4.py - Text embeddings
pp4.py - Memory JSON
Local AI services
- Answer generation
pp4.py - Ollama
Earlier prototype
- Pipeline prototype
prism_demo.py
Other components
- User
Connections 9
- User → Chat interface: asks or adds
README.md - Chat interface → Memory retrieval: retrieves memories
pp4.py - Memory retrieval → Text embeddings: embeds query
pp4.py - Text embeddings → Ollama: requests vectors
pp4.py - Memory retrieval → Chat interface: returns memories
pp4.py - Chat interface → Answer generation: sends prompt
pp4.py - Answer generation → Ollama: requests response
pp4.py - Chat interface → Memory JSON: loads or saves
pp4.py - Chat interface → Text embeddings: embeds new memory
pp4.py