diff --git a/templates/rag-conversation/README.md b/templates/rag-conversation/README.md
index 29e85483c4878..43f4a12e3b520 100644
--- a/templates/rag-conversation/README.md
+++ b/templates/rag-conversation/README.md
@@ -1,4 +1,4 @@
-# Conversational RAG 
+# Conversational RAG
 
 This template performs [conversational](https://python.langchain.com/docs/expression_language/cookbook/retrieval#conversational-retrieval-chain) [retrieval](https://python.langchain.com/docs/use_cases/question_answering/), which is one of the most popular LLM use-cases.
 
@@ -10,4 +10,4 @@ Be sure that `OPENAI_API_KEY` is set in order to use the OpenAI models.
 
 ##  Pinecone
 
-Be sure that `PINECONE_API_KEY` is set in order to use Pinecone.
+This template uses Pinecone as a vectorstore and requires that `PINECONE_API_KEY`, `PINECONE_ENVIRONMENT`, and `PINECONE_INDEX` are set.
diff --git a/templates/rag-conversation/rag_conversation/chain.py b/templates/rag-conversation/rag_conversation/chain.py
index f6ad06164d2f6..a0f0be1ba4c9c 100644
--- a/templates/rag-conversation/rag_conversation/chain.py
+++ b/templates/rag-conversation/rag_conversation/chain.py
@@ -1,3 +1,4 @@
+import os
 from typing import Tuple, List
 from pydantic import BaseModel
 from operator import itemgetter
@@ -10,6 +11,14 @@
 from langchain.schema.output_parser import StrOutputParser
 from langchain.schema.runnable import RunnablePassthrough, RunnableBranch, RunnableLambda, RunnableMap
 
+if os.environ.get("PINECONE_API_KEY", None) is None:
+    raise Exception("Missing `PINECONE_API_KEY` environment variable.")
+
+if os.environ.get("PINECONE_ENVIRONMENT", None) is None:
+    raise Exception("Missing `PINECONE_ENVIRONMENT` environment variable.")
+
+PINECONE_INDEX_NAME = os.environ.get("PINECONE_INDEX", "langchain-test")
+
 ### Ingest code - you may need to run this the first time
 # Load
 # from langchain.document_loaders import WebBaseLoader
@@ -20,14 +29,14 @@
 # from langchain.text_splitter import RecursiveCharacterTextSplitter
 # text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
 # all_splits = text_splitter.split_documents(data)
-#
+
 # # Add to vectorDB
 # vectorstore = Pinecone.from_documents(
-#     documents=all_splits, embedding=OpenAIEmbeddings(), index_name='langchain-test'
+#     documents=all_splits, embedding=OpenAIEmbeddings(), index_name=PINECONE_INDEX_NAME
 # )
 # retriever = vectorstore.as_retriever()
 
-vectorstore = Pinecone.from_existing_index("langchain-test", OpenAIEmbeddings())
+vectorstore = Pinecone.from_existing_index(PINECONE_INDEX_NAME, OpenAIEmbeddings())
 retriever = vectorstore.as_retriever()
 
 # Condense a chat history and follow-up question into a standalone question
@@ -62,9 +71,9 @@ def _format_chat_history(chat_history: List[Tuple[str, str]]) -> List:
         buffer.append(AIMessage(content=ai))
     return buffer
 
-# User input 
+# User input
 class ChatHistory(BaseModel):
-    chat_history: List[Tuple[str, str]] 
+    chat_history: List[Tuple[str, str]]
     question: str