langchain - 💡(How to fix) Fix bug: RePhraseQueryRetriever._aget_relevant_documents raises NotImplementedError

Submission checklist

• This is a bug, not a usage question.
• I added a clear and descriptive title that summarizes this issue.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
• This is not related to the langchain-community package.
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-openrouter
• langchain-perplexity
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Related Issues / PRs

#37620

Reproduction Steps / Example Code (Python)

from langchain_core.documents import Document
from langchain_core.retrievers import BaseRetriever
from langchain_core.runnables import RunnableLambda
from langchain_classic.retrievers.re_phraser import RePhraseQueryRetriever


class FakeRetriever(BaseRetriever):
    def _get_relevant_documents(self, query, *, run_manager=None):
        return [Document(page_content=f"relevant: {query}")]

    async def _aget_relevant_documents(self, query, *, run_manager=None):
        return [Document(page_content=f"relevant: {query}")]


chain = RunnableLambda(lambda q: "rephrased query")
retriever = RePhraseQueryRetriever(retriever=FakeRetriever(), llm_chain=chain)

# ✅ Sync works fine
result = retriever.invoke("what is langchain?")
print(f"Sync OK: {len(result)} doc(s)")

# ❌ Async raises NotImplementedError
import asyncio
result = asyncio.run(retriever.ainvoke("what is langchain?"))

Error Message and Stack Trace (if applicable)

Description

The sync method _get_relevant_documents (line 61) has a full implementation — it invokes the LLM chain to rephrase the query, then calls the inner retriever. However, _aget_relevant_documents (line 86–92) is just a stub:

https://github.com/langchain-ai/langchain/blob/a1e2daf098a96699d3b8a191698e67c4137f79c9/libs/langchain/langchain_classic/retrievers/re_phraser.py#L86-L92

Suggested fix: Mirror the sync implementation using ainvoke:

async def _aget_relevant_documents(self, query, *, run_manager):
    re_phrased_question = await self.llm_chain.ainvoke(
        query, {"callbacks": run_manager.get_child()}
    )
    return await self.retriever.ainvoke(
        re_phrased_question,
        config={"callbacks": run_manager.get_child()},
    )

I have a fix ready with tests and would be happy to open a PR if confirmed. Thanks!

System Info

OS: Darwin OS Version: Darwin Kernel Version 25.5.0 Python Version: 3.12.11

Package Information

langchain_core: 1.4.0 langchain_classic: 1.0.7