Click Below to Get the Code

Browse, clone, and build from real-world templates powered by Harper.
Repo
GitHub Logo

Semantic Cache Example

A demo project using Harper and Ollama for semantic search with a vector-based cache, storing similar queries to cut redundant LLM calls.
JavaScript
Repo
JavaScript

Semantic Cache Example

Kyle Bernhardy
CTO & Co-Founder
at Harper
September 12, 2025
Kyle Bernhardy
CTO & Co-Founder
at Harper
September 12, 2025
Kyle Bernhardy
CTO & Co-Founder
at Harper
September 12, 2025
September 12, 2025
A demo project using Harper and Ollama for semantic search with a vector-based cache, storing similar queries to cut redundant LLM calls.
Kyle Bernhardy
CTO & Co-Founder
A demo project using Harper and Ollama for semantic search with a vector-based cache, storing similar queries to cut redundant LLM calls.

Download

White arrow pointing right
A demo project using Harper and Ollama for semantic search with a vector-based cache, storing similar queries to cut redundant LLM calls.

Download

White arrow pointing right
A demo project using Harper and Ollama for semantic search with a vector-based cache, storing similar queries to cut redundant LLM calls.

Download

White arrow pointing right

Explore Recent Resources

Media Coverage
GitHub Logo

Harper Argues Against the Multi-System Stack and Releases 5.2

InfoQ examines benchmark results comparing co-located and serverless architectures, highlighting faster personalized-data paths, serverless advantages under heavy fan-out, and the performance implications of eliminating network hops between services at scale.
Media Coverage
InfoQ examines benchmark results comparing co-located and serverless architectures, highlighting faster personalized-data paths, serverless advantages under heavy fan-out, and the performance implications of eliminating network hops between services at scale.
Renato Losio, Staff Editor at InfoQ
Renato Losio
InfoQ Staff Editor
Media Coverage

Harper Argues Against the Multi-System Stack and Releases 5.2

InfoQ examines benchmark results comparing co-located and serverless architectures, highlighting faster personalized-data paths, serverless advantages under heavy fan-out, and the performance implications of eliminating network hops between services at scale.
Renato Losio
Aug 2026
Media Coverage

Harper Argues Against the Multi-System Stack and Releases 5.2

InfoQ examines benchmark results comparing co-located and serverless architectures, highlighting faster personalized-data paths, serverless advantages under heavy fan-out, and the performance implications of eliminating network hops between services at scale.
Renato Losio
Media Coverage

Harper Argues Against the Multi-System Stack and Releases 5.2

InfoQ examines benchmark results comparing co-located and serverless architectures, highlighting faster personalized-data paths, serverless advantages under heavy fan-out, and the performance implications of eliminating network hops between services at scale.
Renato Losio