LangSmith supports OpenTelemetry-based tracing, allowing you to send traces from any OpenTelemetry-compatible application. This guide covers both automatic instrumentation for LangChain applications and manual instrumentation for other frameworks.| docs.smith.langchain.com
Before diving into this content, it might be helpful to read the following:| docs.smith.langchain.com
Before diving into this content, it might be helpful to read the following:| docs.smith.langchain.com
Evaluations | Evaluators | Datasets| docs.smith.langchain.com
Annotation queues are a powerful LangSmith feature that provide a streamlined, directed view for human annotators to attach feedback to specific runs.| docs.smith.langchain.com
These guides answer “How do I…?” format questions.| docs.smith.langchain.com
The quality and development speed of AI applications is often limited by high-quality evaluation datasets and metrics, which enable you to both optimize and test your applications.| docs.smith.langchain.com
This conceptual guide covers topics that are important to understand when logging traces to LangSmith. A Trace is essentially a series of steps that your application takes to go from input to output. Each of these individual steps is represented by a Run. A Project is simply a collection of traces. The following diagram displays these concepts in the context of a simple RAG app, which retrieves documents from an index and generates an answer.| docs.smith.langchain.com
