Features
Visual drag-and-drop builder for AI workflows
Single-agent chatbots with RAG and tool calling
Multi-agent system orchestration
Human-in-the-loop review of agent actions
Execution traces and observability (Prometheus, OpenTelemetry)
Embedded chat widgets with customization
REST API for prediction and management
TypeScript and Python SDKs
100+ integrations with LLMs, embeddings, vector DBs
On-premises and cloud deployment options
Horizontal scaling with message queues and workers
Evaluation and metrics tools
Assistant API for custom agent configurations
Support for multiple data sources (PDF, TXT, CSV, SQL, etc.)
Community templates and examples
Fine-tune open-source LLMs (Llama 3, Mistral, Llama 2)
Automated hyperparameter optimization (Ludwig)
One-click deployment with autoscaling
Low-latency inference endpoints
Model evaluation and version comparison
Custom training data from S3/GCS
LoRA/QLoRA adapter-based fine-tuning
Per-request monitoring and logging
VPC deployment for data privacy
Support for multiple model architectures
