From 0c6a3fdd6bc8082ec09db63f65a8d3d0d1173e43 Mon Sep 17 00:00:00 2001
From: Sheng Han Lim <shenghan@gmail.com>
Date: Mon, 22 Jul 2024 02:23:19 +0800
Subject: [PATCH] langchain: Update ContextualCompressionRetriever
 base_retriever type to RetrieverLike (#24192)

**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
---
 libs/langchain/langchain/retrievers/contextual_compression.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/libs/langchain/langchain/retrievers/contextual_compression.py b/libs/langchain/langchain/retrievers/contextual_compression.py
index d41ea489ded..9f5c09e3d1c 100644
--- a/libs/langchain/langchain/retrievers/contextual_compression.py
+++ b/libs/langchain/langchain/retrievers/contextual_compression.py
@@ -5,7 +5,7 @@ from langchain_core.callbacks import (
     CallbackManagerForRetrieverRun,
 )
 from langchain_core.documents import Document
-from langchain_core.retrievers import BaseRetriever
+from langchain_core.retrievers import BaseRetriever, RetrieverLike
 
 from langchain.retrievers.document_compressors.base import (
     BaseDocumentCompressor,
@@ -18,7 +18,7 @@ class ContextualCompressionRetriever(BaseRetriever):
     base_compressor: BaseDocumentCompressor
     """Compressor for compressing retrieved documents."""
 
-    base_retriever: BaseRetriever
+    base_retriever: RetrieverLike
     """Base Retriever to use for getting relevant documents."""
 
     class Config: