fix(langchain): use correct class names for pinecone vectorstore check

[Yun-Kim]

This PR fixes the class names used to check for Pinecone vectorstore instances in the langchain integration. Previously the incorrect base class for all vectorstores was being used, which would mean all vectorstores would return true for this check.

This PR also marks langchain community llmobs tests as flaky due to the vcrpy issue as described in #9768.

Notes

Langchain has a tricky versioning system with tons of deprecations and removals (even between minor versions):

• langchain<0.1: Uses the base langchain module to access langchain.vectorstores.Pinecone (note this indirectly imports from langchain_community.
• langchain>=0.1: Uses the langchain_community module to access langchain_community.vectorstores.Pinecone
• langchain>=0.1 but if users have langchain-pinecone installed: Uses langchain_pinecone module to access langchain_pinecone.vectorstores.Pinecone (deprecated, subclass of PineconeVectorStore) or langchain_pinecone.vectorstores.PineconeVectorStore.

We use the above information to use as the logic to check if an instance is a pinecone vectorstore.

Checklist

• The PR description includes an overview of the change
• The PR description articulates the motivation for the change
• The change includes tests OR the PR description describes a testing strategy
• The PR description notes risks associated with the change, if any
• Newly-added code is easy to change
• The change follows the library release note guidelines
• The change includes or references documentation updates if necessary
• Backport labels are set (if applicable)

Reviewer Checklist

• Title is accurate
• All changes are related to the pull request's stated goal
• Avoids breaking API changes
• Testing strategy adequately addresses listed risks
• Newly-added code is easy to change
• Release note makes sense to a user of the library
• If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment
• Backport labels are set in a manner that is consistent with the release branch maintenance policy

[datadog-dd-trace-py-rkomorn]

Datadog Report

Branch report: yunkim/langchain-pinecone-vectorstore-fix
Commit report: 20653e4
Test service: dd-trace-py

✅ 0 Failed, 117508 Passed, 59424 Skipped, 3h 46m 11.81s Total duration (5h 43m 26.16s time saved)

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 0% with 19 lines in your changes missing coverage. Please review.

Project coverage is 10.53%. Comparing base (c728c68) to head (20653e4).
Report is 34 commits behind head on main.

Files	Patch %	Lines
...ests/contrib/langchain/test_langchain_community.py	0.00%	13 Missing ⚠️
ddtrace/contrib/langchain/patch.py	0.00%	3 Missing ⚠️
tests/contrib/langchain/test_langchain_llmobs.py	0.00%	3 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #9759       +/-   ##
===========================================
- Coverage   74.30%   10.53%   -63.77%     
===========================================
  Files        1398     1367       -31     
  Lines      129930   127822     -2108     
===========================================
- Hits        96541    13466    -83075     
- Misses      33389   114356    +80967     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[pr-commenter]

Benchmarks

Benchmark execution time: 2024-07-17 21:07:08

Comparing candidate commit 02c34b2 in PR branch yunkim/langchain-pinecone-vectorstore-fix with baseline commit 677fef9 in branch main.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 214 metrics, 2 unstable metrics.

[emmettbutler]

Deferring to other reviewers

[Yun-Kim]

Note: there is a cassette file issue with the dependency updates, will look into this

[github-actions]

CODEOWNERS have been resolved as:

releasenotes/notes/fix-langchain-pinecone-vectorstore-082c023ccae268e1.yaml  @DataDog/apm-python
tests/contrib/langchain/cassettes/langchain_community/openai_retrieval_embedding.yaml  @DataDog/ml-observability
tests/snapshots/tests.contrib.langchain.test_langchain_community.test_faiss_vectorstore_retrieval.json  @DataDog/apm-python
.riot/requirements/1598e9b.txt                                          @DataDog/apm-python
.riot/requirements/1810353.txt                                          @DataDog/apm-python
.riot/requirements/1dca1e6.txt                                          @DataDog/apm-python
.riot/requirements/7aeeb05.txt                                          @DataDog/apm-python
.riot/requirements/8fdfb07.txt                                          @DataDog/apm-python
.riot/requirements/b26ea62.txt                                          @DataDog/apm-python
.riot/requirements/b5852df.txt                                          @DataDog/apm-python
.riot/requirements/ccc7691.txt                                          @DataDog/apm-python
.riot/requirements/fd7ae89.txt                                          @DataDog/apm-python
ddtrace/contrib/langchain/patch.py                                      @DataDog/ml-observability
riotfile.py                                                             @DataDog/apm-python
tests/contrib/langchain/test_langchain_community.py                     @DataDog/ml-observability
tests/contrib/langchain/test_langchain_llmobs.py                        @DataDog/ml-observability
.riot/requirements/150eea5.txt                                          @DataDog/apm-python
.riot/requirements/9946322.txt                                          @DataDog/apm-python
.riot/requirements/9b67887.txt                                          @DataDog/apm-python

[github-actions]

The backport to 2.9 failed:

The process '/usr/bin/git' failed with exit code 1

To backport manually, run these commands in your terminal:

# Fetch latest updates from GitHub
git fetch
# Create a new working tree
git worktree add .worktrees/backport-2.9 2.9
# Navigate to the new working tree
cd .worktrees/backport-2.9
# Create a new branch
git switch --create backport-9759-to-2.9
# Cherry-pick the merged commit of this pull request and resolve the conflicts
git cherry-pick -x --mainline 1 ab3d2ce4fcb10e6e18646656c046ad37f67f85b4
# Push it to GitHub
git push --set-upstream origin backport-9759-to-2.9
# Go back to the original working tree
cd ../..
# Delete the working tree
git worktree remove .worktrees/backport-2.9

Then, create a pull request where the base branch is 2.9 and the compare/head branch is backport-9759-to-2.9.

[github-actions]

The backport to 2.10 failed:

The process '/usr/bin/git' failed with exit code 1

To backport manually, run these commands in your terminal:

# Fetch latest updates from GitHub
git fetch
# Create a new working tree
git worktree add .worktrees/backport-2.10 2.10
# Navigate to the new working tree
cd .worktrees/backport-2.10
# Create a new branch
git switch --create backport-9759-to-2.10
# Cherry-pick the merged commit of this pull request and resolve the conflicts
git cherry-pick -x --mainline 1 ab3d2ce4fcb10e6e18646656c046ad37f67f85b4
# Push it to GitHub
git push --set-upstream origin backport-9759-to-2.10
# Go back to the original working tree
cd ../..
# Delete the working tree
git worktree remove .worktrees/backport-2.10

Then, create a pull request where the base branch is 2.10 and the compare/head branch is backport-9759-to-2.10.