Hello guys, if I use LangChainInstrumentor, how I can https://docs.arize.com/phoenix/tracing/how-to-tracing/feedback-and-annotations/capture-feedback capture user feedback? The problem is I'm not able to get span id by using LangChainInstrumentor. 馃ズ
馃挕聽Hint: Mention RunLLM in the thread for followups.
Hey Junqi, this should be better documented (cc John G. when you are back) - but runllm is correct in that you can get the current span of a run using a utility in the langchain instrumentor. See https://github.com/Arize-ai/openinference/blob/2c7bd4af321504cdd7261411fe62d889c37[鈥ngchain/src/openinference/instrumentation/langchain/__init__.py
so if you have the run_id, you can get the span
the Send Annotations to Phoenix section in the doc page above has a code snippet for LangChain regarding span_id
from opentelemetry.trace import format_span_id
from openinference.instrumentation.langchain import get_current_span
span = get_current_span()
if span is not None:
span_id = format_span_id(span.get_span_context().span_id)
from opentelemetry.trace import format_span_id
from openinference.instrumentation.langchain import get_current_span
span = get_current_span()
if span is not None:
span_id = format_span_id(span.get_span_context().span_id)I actually had this snippet in code. It neither works inside langgraph nor works outside.