Loading video player...
Monitor LLM applications in production with complete visibility into tokens, latency, costs, and RAG pipeline performance. Key Features: ✅ Auto-instrumentation for OpenAI, Anthropic, LangChain ✅ Token tracking with cost analytics ✅ Latency percentiles & Time-to-First-Token metrics ✅ RAG pipeline tracing ✅ Vector database monitoring (Pinecone, ChromaDB) ✅ Multi-backend support (Splunk, Elasticsearch, Datadog) ✅ Production-ready dashboards included Splunk App- https://github.com/rootiq-ai/splunk_genai_observability GenAI telemetry Python SDK - https://github.com/genai-telemetry/genai-telemetry