Neo4j Advanced RAG template (#12794)

Todo:

- [x] Docs

templates/neo4j-advanced-rag/neo4j_advanced_rag/__init__.py

@@ -0,0 +1,3 @@
+from neo4j_advanced_rag.chain import chain
+
+__all__ = ["chain"]

templates/neo4j-advanced-rag/neo4j_advanced_rag/chain.py

@@ -0,0 +1,51 @@
+from operator import itemgetter
+
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate
+from langchain.pydantic_v1 import BaseModel
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import ConfigurableField, RunnableParallel
+
+from neo4j_advanced_rag.retrievers import (
+    hypothetic_question_vectorstore,
+    parent_vectorstore,
+    summary_vectorstore,
+    typical_rag,
+)
+
+template = """Answer the question based only on the following context:
+{context}
+
+Question: {question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+
+model = ChatOpenAI()
+
+retriever = typical_rag.as_retriever().configurable_alternatives(
+    ConfigurableField(id="strategy"),
+    default_key="typical_rag",
+    parent_strategy=parent_vectorstore.as_retriever(),
+    hypothetical_questions=hypothetic_question_vectorstore.as_retriever(),
+    summary_strategy=summary_vectorstore.as_retriever(),
+)
+
+chain = (
+    RunnableParallel(
+        {
+            "context": itemgetter("question") | retriever,
+            "question": itemgetter("question"),
+        }
+    )
+    | prompt
+    | model
+    | StrOutputParser()
+)
+
+
+# Add typing for input
+class Question(BaseModel):
+    question: str
+
+
+chain = chain.with_types(input_type=Question)

templates/neo4j-advanced-rag/neo4j_advanced_rag/retrievers.py

@@ -0,0 +1,49 @@
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Neo4jVector
+
+# Typical RAG retriever
+
+typical_rag = Neo4jVector.from_existing_index(
+    OpenAIEmbeddings(), index_name="typical_rag"
+)
+
+# Parent retriever
+
+parent_query = """
+MATCH (node)<-[:HAS_CHILD]-(parent)
+WITH parent, max(score) AS score // deduplicate parents
+RETURN parent.text AS text, score, {} AS metadata LIMIT 1
+"""
+
+parent_vectorstore = Neo4jVector.from_existing_index(
+    OpenAIEmbeddings(),
+    index_name="parent_document",
+    retrieval_query=parent_query,
+)
+
+# Hypothetic questions retriever
+
+hypothetic_question_query = """
+MATCH (node)<-[:HAS_QUESTION]-(parent)
+WITH parent, max(score) AS score // deduplicate parents
+RETURN parent.text AS text, score, {} AS metadata
+"""
+
+hypothetic_question_vectorstore = Neo4jVector.from_existing_index(
+    OpenAIEmbeddings(),
+    index_name="hypothetical_questions",
+    retrieval_query=hypothetic_question_query,
+)
+# Summary retriever
+
+summary_query = """
+MATCH (node)<-[:HAS_SUMMARY]-(parent)
+WITH parent, max(score) AS score // deduplicate parents
+RETURN parent.text AS text, score, {} AS metadata
+"""
+
+summary_vectorstore = Neo4jVector.from_existing_index(
+    OpenAIEmbeddings(),
+    index_name="summary",
+    retrieval_query=summary_query,
+)