SUMMARY API Reference providers 📦 OpenAI endpoint provider anthropic endpoint provider 📦 HuggingFace endpoint provider 📦 LangChain endpoint provider 📦 Snowflake Cortex endpoint provider 📦 LiteLLM endpoint provider 📦 Amazon Bedrock endpoint provider google endpoint provider apps app basic custom virtual gepa fitness 📦 NeMo Guardrails tru_rails 📦 LangChain guardrails langchain tru_chain 📦 LlamaIndex guardrails llama tru_llama tru_llama_workflow rl reward langgraph inline_evaluations trace_provider tru_graph connectors 📦 Snowflake connector otel_exporter snowflake_event_table_db sqlalchemy_db utils server_side_evaluation_artifacts server_side_evaluation_stored_procedure sis_dashboard_artifacts ❌ trulens_eval core app dao default_run run database base connector base default exceptions legacy migration migrations data env orm sqlalchemy utils enums experimental feedback custom_metric endpoint feedback feedback_function_input provider selector guardrails base instruments metric metric selector run sampling schema app base conversation dataset event feedback groundtruth record select types session utils asynchro constants containers deprecation evaluator imports json keys pace pyschema python serial signature text threading trace_compression trace_provider trulens feedback computer dummy endpoint provider embeddings feedback generated groundtruth jury llm_provider optimize output_schemas prompts schema_validator templates agent base conversation quality rag safety v2 feedback dashboard appui components record_viewer record_viewer_otel constants display main run streamlit tabs Compare Leaderboard Records utils dashboard_utils metadata_utils notebook_utils records_utils sis_utils streamlit_compat ux components styles benchmark alignment_report benchmark_frameworks tru_benchmark_experiment criteria_ab_test cross_model_alignment generate generate_test_set golden_set_generator score_distribution test_cases