CustomRetriever has a signature that does not allow to pass arguments other than the input query.

[pasinit]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

@abstractmethod
def _get_relevant_documents(
        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    ) -> list[Document]:

Description

I want to be able to pass in additional information to my retriever in order to structure the query for my internal system with start and end date. However, this does not seem to be possible in any way as the interface to this method is very restrictive. Going for Runnable is an option but then i won't be able to use EnsambleRetriever nor any other utility classes build around BaseRetriever. Is there any way to work around this?

System Info

System Information

OS: Linux
OS Version: #1 SMP Mon Aug 12 08:47:01 UTC 2024
Python Version: 3.11.10 (main, Sep 9 2024, 13:09:35) [GCC 12.1.1 20220628 (Red Hat 12.1.1-3)]

Package Information

langchain_core: 0.3.12
langchain: 0.3.3
langsmith: 0.1.134
langchain_openai: 0.2.2
langchain_text_splitters: 0.3.0

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.10.10
async-timeout: Installed. No version info available.
httpx: 0.27.2
jsonpatch: 1.33
numpy: 1.26.4
openai: 1.45.0
orjson: 3.10.7
packaging: 24.1
pydantic: 2.9.2
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
tenacity: 8.5.0
tiktoken: 0.8.0
typing-extensions: 4.12.2