- Published on
I've been playing with a new approach to RAG systems - combining vector search with knowledge graphs for more contextual, relationship-aware answers. Here's what I've built, how it works, and why you might want to try it yourself.
Rag
All Posts
- generative-ai (13)
- conversational-ai (11)
- nextjs (9)
- chatbot (7)
- material-ui (6)
- reactjs (6)
- typescript (6)
- openai (4)
- titanium (3)
- oauth (3)
- assistants (2)
- streaming-chat (2)
- ui-ux (2)
- authentication (2)
rag (2)
- guide (2)
- grafana (2)
- prometheus (2)
- telemetry (2)
- blog (1)
- learning (1)
- ai (1)
- aiethics (1)
- article (1)
- gpt-4 (1)
- github (1)
- google (1)
- vision (1)
- retrieval-augmented-generation (1)
- pinecone-serverless (1)
- unstructured (1)
- embeddings (1)
- knowledge-graphs (1)
- neo4j (1)
- vector-search (1)
- llm (1)
- python (1)
- video-to-text (1)
- alloy (1)
- mimir (1)
- pyroscope (1)
- loki (1)
- tempo (1)
- opentelemetry (1)
- persistent-memory (1)
- nosql (1)
- Published on
A simple experiment to calculate the cost of storing a 1 hour, 60fps 4k Video in a RAG model. For no practical reason, whatsoever.