Skip to content

Conversation

obinnascale3
Copy link
Contributor

Description

Please include a summary of the changes and the related issue to help is review the PR better and faster.

Checklist for adding new integration:

  • Defined APIS in constants folder.
  • Updated SERVICE_PROVIDERS in common.py
  • Created a folder under instrumentation with the name of the integration with atleast patch.py and instrumentation.py files.
  • Added instrumentation in all_instrumentations in langtrace.py and to the InstrumentationType in types.py files.
  • Added examples for the new integration in the examples folder.
  • Updated pyproject.toml to install new dependencies
  • Updated the README.md of langtrace-python-sdk to include the new integration in the supported integrations table.
  • Updated the README.md of Langtrace's repository to include the new integration in the supported integrations table.
  • Added new integration page to supported integrations in Langtrace Docs

karthikscale3
karthikscale3 previously approved these changes Jun 4, 2025
@karthikscale3 karthikscale3 merged commit cc95a5a into development Jun 5, 2025
4 checks passed
@karthikscale3 karthikscale3 deleted the obinna/fix-awsbedrock-streaming-response branch June 5, 2025 16:02
karthikscale3 added a commit that referenced this pull request Jul 24, 2025
* capture different types of google genai inputs (#534)

Co-authored-by: Obinna Okafor <obinna.okafor01@gmail.com>

* Read stream before saving attributes. Parse modelId in a more robust way.

* Decide based on model name on the set of attributes tracked.

* Added basic test for model ID parsing.

* Added replay tests for AWS Bedrock.

* Added test for streaming requests too.

* Obinna/fix awsbedrock streaming response (#538)

* fix aws bedrock streaming bug

* bump version

* add deprecated dependency

* restrict current pinecone instrumentation to v6.0.2

* hard code boto3 dependency version

* fix duplicate event stream

* set test aws key

* Fix AWS Bedrock ARN parsing issue in converse methods (#544)

* Fix AWS Bedrock ARN parsing issue in converse methods

- Replace modelId.split('.') with parse_vendor_and_model_name_from_model_id
- Fixes crash when using ARN or cross-region model IDs with multiple dots
- Makes patch_converse and patch_converse_stream consistent with other methods

Resolves ValueError: too many values to unpack (expected 2) when using:
- ARN format: arn:aws:bedrock:us-east-1:<account_id>:inference-profile/us.anthropic.claude-3-haiku-20240307-v1:0
- Cross-region format: us.anthropic.claude-sonnet-4-20250514-v1:0

Co-Authored-By: karthik@scale3labs.com <karthik@scale3labs.com>

* Bump version to 3.8.21 for ARN parsing bug fix

Co-Authored-By: karthik@scale3labs.com <karthik@scale3labs.com>

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: karthik@scale3labs.com <karthik@scale3labs.com>

---------

Co-authored-by: obinnascale3 <109410793+obinnascale3@users.noreply.github.com>
Co-authored-by: Obinna Okafor <obinna.okafor01@gmail.com>
Co-authored-by: m1kl0sh <miklos.erdelyi@moduscreate.com>
Co-authored-by: Obinna Okafor <obinna@scale3labs.com>
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: karthik@scale3labs.com <karthik@scale3labs.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants