Haystack + Valkey RAG Demo

Valkey's sub-millisecond vector retrieval powers RAG pipelines that return grounded answers without the latency cost. Ask a question and see how fast context lands.

💬 Ask a Question

3

💡 Answer gpt-4o

Run a query to see the generated answer.

📄 Retrieved Documents

Run a query to see retrieved documents.

🗃️ Valkey Document Store ValkeyDocumentStore

10 documents indexed · 1536-dim embeddings · cosine similarity
Queries
0
Avg Retrieval
-

⚙️ Pipeline Execution

🔤TextEmbedder-
🔍ValkeyEmbeddingRetriever-
📝ChatPromptBuilder-
🤖OpenAIChatGenerator-

🖥️ Query Log live

-- Waiting for query...