mirror of
https://github.com/langchain-ai/langchain.git
synced 2026-10-11 04:15:12 +03:00
Sheng Han Lim
0c6a3fdd6b
**Description:**
When initializing retrievers with `configurable_fields` as base
retriever, `ContextualCompressionRetriever` validation fails with the
following error:
```
ValidationError: 1 validation error for ContextualCompressionRetriever
base_retriever
Can't instantiate abstract class BaseRetriever with abstract method _get_relevant_documents (type=type_error)
```
Example code:
```python
esearch_retriever = VertexAISearchRetriever(
project_id=GCP_PROJECT_ID,
location_id="global",
data_store_id=SEARCH_ENGINE_ID,
).configurable_fields(
filter=ConfigurableField(id="vertex_search_filter", name="Vertex Search Filter")
)
# rerank documents with Vertex AI Rank API
reranker = VertexAIRank(
project_id=GCP_PROJECT_ID,
location_id=GCP_REGION,
ranking_config="default_ranking_config",
)
retriever_with_reranker = ContextualCompressionRetriever(
base_compressor=reranker, base_retriever=esearch_retriever
)
```
It seems like the issue stems from ContextualCompressionRetriever
insisting that base retrievers must be strictly `BaseRetriever`
inherited, and doesn't take into account cases where retrievers need to
be chained and can have configurable fields defined.
https://github.com/langchain-ai/langchain/blob/0a1e475a30ff66186125d57f9b01669a9783b3ed/libs/langchain/langchain/retrievers/contextual_compression.py#L15-L22
This PR proposes that the base_retriever type be set to `RetrieverLike`,
similar to how `EnsembleRetriever` validates its list of retrievers:
https://github.com/langchain-ai/langchain/blob/0a1e475a30ff66186125d57f9b01669a9783b3ed/libs/langchain/langchain/retrievers/ensemble.py#L58-L75