fix(langchain): avoid patching libraries if not available [backport #…

…8339 to 2.8] (#8986)

Backport #8339 to 2.8.

This PR changes the langchain integration such that it will check for
partner libraries before attempting to patch them.

The langchain integration patches `langchain_openai.OpenAIEmbeddings.*`
and `langchain_pinecone.PineconeVectorStore.*`, which are partner
libraries that are not required to be installed. Currently if they are
not available, we raise `ModuleNotFoundError`. This PR fixes this so
that we'll skip patching those methods if the corresponding partner
library is not available.

Additionally, this PR also adds importing
`langchain_community.llm/chat_models` as those are not automatically
imported by importing `langchain_community`. This is important as we
reference those submodules in our patch code later on.


## Checklist

- [x] Change(s) are motivated and described in the PR description
- [x] Testing strategy is described if automated tests are not included
in the PR
- [x] Risks are described (performance impact, potential for breakage,
maintainability)
- [x] Change is maintainable (easy to change, telemetry, documentation)
- [x] [Library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
are followed or label `changelog/no-changelog` is set
- [x] Documentation is included (in-code, generated user docs, [public
corp docs](https://github.com/DataDog/documentation/))
- [x] Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))
- [x] If this PR changes the public interface, I've notified
`@DataDog/apm-tees`.

## Reviewer Checklist

- [x] Title is accurate
- [x] All changes are related to the pull request's stated goal
- [x] Description motivates each change
- [x] Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- [x] Testing strategy adequately addresses listed risks
- [x] Change is maintainable (easy to change, telemetry, documentation)
- [x] Release note makes sense to a user of the library
- [x] Author has acknowledged and discussed the performance implications
of this PR as reported in the benchmarks PR comment
- [x] Backport labels are set in a manner that is consistent with the
[release branch maintenance

policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

ddtrace/contrib/langchain/patch.py

@@ -779,7 +779,9 @@ def patch():
     # ref: https://github.com/DataDog/dd-trace-py/issues/7123
     if SHOULD_PATCH_LANGCHAIN_COMMUNITY:
         from langchain.chains.base import Chain  # noqa:F401
+        from langchain_community import chat_models  # noqa:F401
         from langchain_community import embeddings  # noqa:F401
+        from langchain_community import llms  # noqa:F401
         from langchain_community import vectorstores  # noqa:F401
 
         wrap("langchain_core", "language_models.llms.BaseLLM.generate", traced_llm_generate(langchain))
@@ -796,8 +798,10 @@ def patch():
         )
         wrap("langchain", "chains.base.Chain.invoke", traced_chain_call(langchain))
         wrap("langchain", "chains.base.Chain.ainvoke", traced_chain_acall(langchain))
-        wrap("langchain_openai", "OpenAIEmbeddings.embed_documents", traced_embedding(langchain))
-        wrap("langchain_pinecone", "PineconeVectorStore.similarity_search", traced_similarity_search(langchain))
+        if langchain_openai:
+            wrap("langchain_openai", "OpenAIEmbeddings.embed_documents", traced_embedding(langchain))
+        if langchain_pinecone:
+            wrap("langchain_pinecone", "PineconeVectorStore.similarity_search", traced_similarity_search(langchain))
     else:
         from langchain import embeddings  # noqa:F401
         from langchain import vectorstores  # noqa:F401
@@ -884,8 +888,10 @@ def unpatch():
         unwrap(langchain_core.language_models.chat_models.BaseChatModel, "agenerate")
         unwrap(langchain.chains.base.Chain, "invoke")
         unwrap(langchain.chains.base.Chain, "ainvoke")
-        unwrap(langchain_openai.OpenAIEmbeddings, "embed_documents")
-        unwrap(langchain_pinecone.PineconeVectorStore, "similarity_search")
+        if langchain_openai:
+            unwrap(langchain_openai.OpenAIEmbeddings, "embed_documents")
+        if langchain_pinecone:
+            unwrap(langchain_pinecone.PineconeVectorStore, "similarity_search")
 
     else:
         unwrap(langchain.llms.base.BaseLLM, "generate")

releasenotes/notes/fix-langchain-avoid-patching-partners-4c5fb04db6d083b0.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    langchain: This fix resolves an issue where the LangChain integration always attempted to patch LangChain partner
+     libraries, even if they were not available.

tests/contrib/langchain/test_langchain_community.py

@@ -487,7 +487,7 @@ def test_openai_math_chain_sync(langchain, langchain_openai, request_vcr):
 @pytest.mark.snapshot(token="tests.contrib.langchain.test_langchain_community.test_chain_invoke")
 def test_chain_invoke_dict_input(langchain, langchain_openai, request_vcr):
     prompt_template = "what is {base} raised to the fifty-fourth power?"
-    prompt = langchain.prompts.PromptTemplate(input_variables=["adjective"], template=prompt_template)
+    prompt = langchain.prompts.PromptTemplate(input_variables=["base"], template=prompt_template)
     chain = langchain.chains.LLMChain(llm=langchain_openai.OpenAI(temperature=0), prompt=prompt)
     with request_vcr.use_cassette("openai_math_chain_sync.yaml"):
         chain.invoke(input={"base": "two"})
@@ -496,7 +496,7 @@ def test_chain_invoke_dict_input(langchain, langchain_openai, request_vcr):
 @pytest.mark.snapshot(token="tests.contrib.langchain.test_langchain_community.test_chain_invoke")
 def test_chain_invoke_str_input(langchain, langchain_openai, request_vcr):
     prompt_template = "what is {base} raised to the fifty-fourth power?"
-    prompt = langchain.prompts.PromptTemplate(input_variables=["adjective"], template=prompt_template)
+    prompt = langchain.prompts.PromptTemplate(input_variables=["base"], template=prompt_template)
     chain = langchain.chains.LLMChain(llm=langchain_openai.OpenAI(temperature=0), prompt=prompt)
     with request_vcr.use_cassette("openai_math_chain_sync.yaml"):
         chain.invoke("two")