chatbot-rag-app: use Elastic Distribution of OpenTelemetry (EDOT) #369
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This updates the requirements.txt to include Elastic Distribution of OpenTelemetry (EDOT) Python.
When
OTEL_SDK_DISABLED=false
, logs, metrics and traces are exported to an OTLP endpoint, which by default points to the Elastic APM server port 8200.For example, this is a trace for OpenAI and if you click on the span circled, you can see underlying request/response data for the chat request
EDOT Python at the moment includes support for OpenAI, so will have portable data for requests using
ChatOpenAI
. Data is still collected for other options like bedrock and vertex, just not in a portable form.For example, this is a trace including bedrock, but doesn't have logs for the LLM request/response

Watch EDOT Python releases for updates which can expand this list.
Special thanks to @xrmx @joemcelroy @anuraaga @ezimuel @EvelienSchellekens @bshetti who all contributed to this in implementation or q/a