description |
---|
How OpenInference facilitates automatic instrumentation of applications. |
In order to make a system observable, it must be instrumented: That is, code from the system’s components must emit traces.
Phoenix natively supports collecting traces generated via OpenInference automatic instrumentation. Phoenix has pre-built auto-instrumentors for Python and TypeScript / JavaScript.
\
Python | LlamaIndex, LangChain, DSPy, OpenAI, Bedrock, Mistral and more | python.png | auto-instrument-python |
TypeScript / JavaScript | OpenAI, LangChainjs | javascript.png | auto-instrument-ts |