Skip to content

Added span support for genAI langchain llm invocation #3665

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 21 commits into
base: main
Choose a base branch
from
Open

Added span support for genAI langchain llm invocation #3665

wants to merge 21 commits into from
+1,086 −4

Conversation

wrisa
Copy link
Contributor

@wrisa wrisa commented Jul 30, 2025 •
edited
Loading

Description

Taking inspiration from traceloop's openllmetry support for langchain instrumentation, added callback handler support for llm start and end to generate span with attributes listed here.

Attributes added on span:
-> gen_ai.operation.name: Str(chat)
-> gen_ai.system: Str(ChatOpenAI)
-> gen_ai.request.model: Str(gpt-3.5-turbo)
-> gen_ai.request.top_p: Double(0.9)
-> gen_ai.request.frequency_penalty: Double(0.5)
-> gen_ai.request.presence_penalty: Double(0.5)
-> gen_ai.request.stop_sequences: Slice(["\n","Human:","AI:"])
-> gen_ai.request.seed: Int(100)
-> gen_ai.request.max_tokens: Int(100)
-> gen_ai.provider.name: Str(openai)
-> gen_ai.request.temperature: Double(0.1)
-> gen_ai.response.finish_reasons: Slice(["stop"])
-> gen_ai.response.model: Str(gpt-3.5-turbo-0125)
-> gen_ai.response.id: Str(chatcmpl-Bz8yrvPnydD9pObv625n2CGBPHS13)
-> gen_ai.usage.input_tokens: Int(24)
-> gen_ai.usage.output_tokens: Int(7)

Please refer complete span attributes o/p: https://docs.google.com/document/d/13SXuf4iZSl2MqWUJtmoDEqFxuHZ1Y8hykW_ctlykcDE/edit?tab=t.0

We have just added span support in this PR for now to keep this PR concise and in future we will have metric and log support PRs.

Fixes # (issue)

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

  • From test folder /opentelemetry-python-contrib/instrumentation-genai/opentelemetry-instrumentation-langchain/tests run pytest -rP test_llm_call.py

Does This PR Require a Core Repo Change?

  • Yes. - Link to PR:
  • No.

Checklist:

See contributing.md for styleguide, changelog guidelines, and more.

  • Followed the style guidelines of this project
  • Changelogs have been updated
  • Unit tests have been added
  • Documentation has been updated

@wrisa wrisa marked this pull request as ready for review August 1, 2025 01:50
@wrisa wrisa requested a review from a team as a code owner August 1, 2025 01:50
pmcollins
pmcollins reviewed Aug 1, 2025
View reviewed changes
Copy link
Member

@pmcollins pmcollins left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for putting this together. Added some comments.

@wrisa wrisa force-pushed the genai-instrumentation-langchain-spans branch from 3940934 to 072b0fd Compare August 4, 2025 21:43
@wrisa wrisa force-pushed the genai-instrumentation-langchain-spans branch 3 times, most recently from fed5254 to 01caea4 Compare August 18, 2025 15:26
xrmx
xrmx reviewed Aug 19, 2025
View reviewed changes
instrumentation-genai/opentelemetry-instrumentation-langchain/tests/test_llm_call.py Outdated
def test_langchain_call(
span_exporter, chatOpenAI_client, start_instrumentation
):
llm = ChatOpenAI(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would it be possible to move the provider as fixture and provide another one for the same test? just to make sure there's nothing openai dependent on the instrumentation side

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have moved the provider as fixture. But when I tried other providers like AWS bedrock and Gemini I see that the attributes are listed differently. For openAI -> invocation_params.get("model_name") please see callback_handler.py ln:57

aws bedrock -> invocation_params.get("model_id")
gemini -> invocation_params.get("model")

What does this mean? Would the ownership of handling various providers will be on instrumentation implementors or is it ok to say that providers supporting langchain(eg: langchain_openai, langchain_google_genai) should be consistent with the attributes?

...emetry-instrumentation-langchain/src/opentelemetry/instrumentation/langchain/span_manager.py

def _create_span(
self,
run_id: UUID,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

run_id is a langtrace specific concept right? So this code is not supposed to move to the genai utils package right?

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In genAI utils we can have run_id optional. For this PR we can keep as is.

@wrisa wrisa force-pushed the genai-instrumentation-langchain-spans branch from 7c0e8bf to 8502753 Compare August 28, 2025 16:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@xrmx xrmx xrmx left review comments

@pmcollins pmcollins pmcollins approved these changes

+3 more reviewers

@singankit singankit singankit left review comments

@keith-decker keith-decker keith-decker left review comments

@ridhima-splunk ridhima-splunk ridhima-splunk left review comments

Reviewers whose approvals may not affect merge requirements
Assignees

@codefromthecrypt codefromthecrypt

@nirga nirga

@lzchen lzchen

@karthikscale3 karthikscale3

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
10 participants
@wrisa @xrmx @pmcollins @singankit @keith-decker @ridhima-splunk @codefromthecrypt @nirga @lzchen @karthikscale3