Features
Multi-turn conversational assistants with session management
Retrieval-Augmented Generation (RAG) with built-in vector stores
Supports OpenAI, Anthropic, Google, and local models via LiteLLM
Django admin integration for managing assistants and data sources
Key-value and summary memory types for conversations
File upload and processing for context injection
Streaming response support
Built-in vector store backends: Chroma, Pinecone, Qdrant, PGVector
Tool/function calling integration with Django ORM
Customizable system prompts and assistant personality
Conversation history persistence via Django models
Asynchronous support for high-concurrency scenarios
Trace agent executions step by step
Monitor real-time dashboards with cost tracking
Online LLM-as-judge evals for quality scoring
Automated insights with unsupervised topic clustering
SmithDB purpose-built for agent traces
Sub-second query performance across millions of traces
Full-text search with inverted index
JSON key-path filtering and trajectory queries
Self-host SmithDB inside your VPC
LangSmith Engine for autonomous issue detection and fixes
Deploy and scale agents with LangSmith Deployment
Sandboxes for safe agent-generated code execution
Fleet agents for no-code agent creation
Supports Python, TypeScript, Go, Java SDKs
