ai

#ai #llm #benchmark #evaluation

#ai #llm #prompting #in-context-learning

#ai #llm #prompting #instruction-tuning

#voice-rag #rag #vector-db #latency #prefetch

#ai #llm #prompting #in-context-learning

#ai #llm #function-calling #agent #mcp #json-schema

#ai #llm #rag #retrieval #vector-db #embedding

#ai #llm #prompting #reasoning #inference

#ai #llm #evaluation #benchmark

#agent #multi-agent #supervisor #handoff #react #hitl

#llm-serving #vllm #paged-attention #kv-cache #ttft

#pipecat #livekit #voice-framework #agent #sfu

#voice-agent #architecture #latency #streaming #cascading #s2s

#prompt #function-calling #structured-output #voice-llm