for ai
Use Cases
Frameworks
GitHub
Interactive
RAG Pipeline
Demo
Explore semantic caching, vector search, and RAG patterns - all simulated in your browser.
🤖 FAQ Bot
📚 RAG Pipeline
⚡ Semantic Cache
❓
Sample FAQs
Similarity Threshold
0.90
Ask a Question
⚡ Search FAQ
0
Cache Hits
0
Misses
0
Total
0%
Hit Rate
Question
→
Embed
→
KNN Search
→
Match
Request Log
Ask a question to begin...
📄
Document Ingestion
Document Content
## Valkey Vector Search Valkey supports HNSW and FLAT indexes for vector similarity search. ### Creating an Index Use FT.CREATE to define your schema with vector fields. ### Querying Use FT.SEARCH with KNN queries for nearest neighbor search.
📥 Ingest Document
Chunk Size
200
🔍
Query
Question
🔍 Query RAG
0
Chunks
0
Cache Hits
0
Misses
0ms
Latency
Query
→
Cache Check
→
Retrieve
→
Generate
→
Cache Store
Valkey Commands
// Commands will appear here...
⚡
Semantic Cache Simulator
Query
Cache TTL (seconds)
3600
Similarity Threshold
0.92
⚡ Query with Cache
🗑️ Clear Cache
0
Hits
0
Misses
0
Entries
0ms
Time Saved
Cache Entries
Cache is empty. Make a query to populate.