Mistral Small 4 for Low-Latency RAG and Function Calling

Mistral Small is optimized for low-latency workloads with strong capabilities in RAG-enablement, function calling, and JSON formatting.

System: Use the provided <rag_chunks> to answer the customer inquiry in JSON format. If a tool lookup is required, invoke the appropriate function. User: <rag_chunks>{{CHUNKS}}</rag_chunks>
Query: {{QUERY}}