From 0d6db85dcd4dfd0eb15644ec4df31f6d539bfb4f Mon Sep 17 00:00:00 2001
From: Changyong Um <e7217@naver.com>
Date: Mon, 10 Feb 2025 22:56:37 +0900
Subject: [PATCH] community: Add configurable text key for indexing and the
 retriever in Pinecone Hybrid Search (#29697)

**issue**

In Langchain, the original content is generally stored under the `text`
key. However, the `PineconeHybridSearchRetriever` searches the `context`
field in the metadata and cannot change this key. To address this, I
have modified the code to allow changing the key to something other than
context.

In my opinion, following Langchain's conventions, the `text` key seems
more appropriate than `context`. However, since I wasn't sure about the
author's intent, I have left the default value as `context`.
---
 .../retrievers/pinecone_hybrid_search.py                  | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/libs/community/langchain_community/retrievers/pinecone_hybrid_search.py b/libs/community/langchain_community/retrievers/pinecone_hybrid_search.py
index a6e0f68002dde..cd3e3e96d080a 100644
--- a/libs/community/langchain_community/retrievers/pinecone_hybrid_search.py
+++ b/libs/community/langchain_community/retrievers/pinecone_hybrid_search.py
@@ -31,6 +31,7 @@ def create_index(
     ids: Optional[List[str]] = None,
     metadatas: Optional[List[dict]] = None,
     namespace: Optional[str] = None,
+    text_key: str = "context",
 ) -> None:
     """Create an index from a list of contexts.
 
@@ -69,7 +70,7 @@ def create_index(
         )
         # add context passages as metadata
         meta = [
-            {"context": context, **metadata}
+            {text_key: context, **metadata}
             for context, metadata in zip(context_batch, metadata_batch)
         ]
 
@@ -114,7 +115,7 @@ class PineconeHybridSearchRetriever(BaseRetriever):
     """Alpha value for hybrid search."""
     namespace: Optional[str] = None
     """Namespace value for index partition."""
-
+    text_key: str = "context"
     model_config = ConfigDict(
         arbitrary_types_allowed=True,
         extra="forbid",
@@ -135,6 +136,7 @@ def add_texts(
             ids=ids,
             metadatas=metadatas,
             namespace=namespace,
+            text_key=self.text_key,
         )
 
     @pre_init
@@ -174,7 +176,7 @@ def _get_relevant_documents(
         )
         final_result = []
         for res in result["matches"]:
-            context = res["metadata"].pop("context")
+            context = res["metadata"].pop(self.text_key)
             metadata = res["metadata"]
             if "score" not in metadata and "score" in res:
                 metadata["score"] = res["score"]