-
Notifications
You must be signed in to change notification settings - Fork 41
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: llama-index instrumentor using callback handler #121
Conversation
|
||
resource = Resource(attributes={}) | ||
tracer_provider = trace_sdk.TracerProvider(resource=resource) | ||
span_exporter = OTLPSpanExporter(endpoint="http://127.0.0.1:6006/v1/traces") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is there a simple way for the user to see the contents of the exported trace or span in this example?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There's the in-memory-exporter. but that's kind of advanced usage. On the other hand the examples are meant to demonstrate phoenix as a collector.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There's no Phoenix instance running as a collector in these examples, though, and they should probably be independent of Phoenix.
Small nit, would just be nice if there is a simple collector we could run to display the spans as they come in.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
good point. probably worth a group discussion on how to do that
...instrumentation-llama-index/tests/openinference/instrumentation/llama_index/test_callback.py
Show resolved
Hide resolved
...instrumentation-llama-index/tests/openinference/instrumentation/llama_index/test_callback.py
Show resolved
Hide resolved
...instrumentation-llama-index/tests/openinference/instrumentation/llama_index/test_callback.py
Outdated
Show resolved
Hide resolved
...instrumentation-llama-index/tests/openinference/instrumentation/llama_index/test_callback.py
Outdated
Show resolved
Hide resolved
...instrumentation-llama-index/tests/openinference/instrumentation/llama_index/test_callback.py
Show resolved
Hide resolved
...erence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/__init__.py
Show resolved
Hide resolved
...erence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/__init__.py
Show resolved
Hide resolved
...instrumentation-llama-index/tests/openinference/instrumentation/llama_index/test_callback.py
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Outdated
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Outdated
Show resolved
Hide resolved
...rence-instrumentation-llama-index/src/openinference/instrumentation/llama_index/_callback.py
Show resolved
Hide resolved
…ex/src/openinference/instrumentation/llama_index/_callback.py Co-authored-by: Xander Song <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great job, @RogerHYang. This was a big one.
Do we have type checking turned on in the unit tests? That would be nice. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm!
resolves Arize-ai/phoenix#1957
based on the callback handler from Phoenix