LangChain Neo4j 集成

LangChain 是一个庞大的生成式 AI 编排库，支持众多 LLM、向量存储、文档加载器和代理。它管理模板，将组件组合成链，并支持监控和可观测性。

广泛而深入的 Neo4j 集成支持向量搜索、Cypher 生成、数据库查询和知识图谱构建。

以下是图集成的概述。

将 Neo4j 集成到 LangChain 生态系统

升级到 LangChain 0.1.0+ 时，请务必阅读本文：将 GraphAcademy Neo4j 和 LLM 课程更新到 Langchain v0.1。

安装

pip install langchain langchain-community langchain-neo4j
# pip install langchain-openai tiktoken
# pip install neo4j

功能包括

Neo4jVector

Neo4j 向量集成支持多种操作

从 LangChain 文档创建向量
查询向量
使用额外的图检索 Cypher 查询向量
从现有图数据构建向量实例
混合搜索
元数据过滤

from langchain.docstore.document import Document
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_neo4j import Neo4jVector
from langchain_openai import OpenAIEmbeddings

loader = TextLoader("../../modules/state_of_the_union.txt")

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# The Neo4jVector Module will connect to Neo4j and create a vector index if needed.

db = Neo4jVector.from_documents(
    docs, embeddings, url=url, username=username, password=password
)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, k=2)

混合搜索

混合搜索结合了向量搜索和全文搜索，并对结果进行重新排序和去重。

from langchain.docstore.document import Document
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_neo4j import Neo4jVector
from langchain_openai import OpenAIEmbeddings

loader = TextLoader("../../modules/state_of_the_union.txt")

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# The Neo4jVector Module will connect to Neo4j and create a vector index if needed.

db = Neo4jVector.from_documents(
    docs, embeddings, url=url, username=username, password=password,
    search_type="hybrid"
)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, k=2)

元数据过滤

元数据过滤通过允许根据特定节点属性细化搜索来增强向量搜索。这种集成方法通过利用向量相似性和节点的上下文属性来确保更精确和相关的搜索结果。

db = Neo4jVector.from_documents(
    docs,
    OpenAIEmbeddings(),
    url=url, username=username, password=password
)

query = "What did the president say about Ketanji Brown Jackson"
filter = {"name": {"$eq": "adam"}}

docs = db.similarity_search(query, filter=filter)

Neo4j 图

Neo4j 图集成是 Neo4j Python 驱动的包装器。它允许从 LangChain 以简化方式查询和更新 Neo4j 数据库。许多集成允许您将 Neo4j 图用作 LangChain 的数据源。

from langchain_neo4j import Neo4jGraph

graph = Neo4jGraph(url=NEO4J_URI, username=NEO4J_USERNAME, password=NEO4J_PASSWORD)

QUERY = """
MATCH (m:Movie)-[:IN_GENRE]->(:Genre {name: $genre})
RETURN m.title, m.plot
ORDER BY m.imdbRating DESC LIMIT 5
"""

graph.query(QUERY, params={"genre": "action"})

CypherQAChain

CypherQAChain 是 LangChain 的一个组件，它允许您以自然语言与 Neo4j 图数据库进行交互。它使用 LLM 和图模式将用户问题转换为 Cypher 查询，对图执行该查询，并使用返回的上下文信息和原始问题与第二个 LLM 一起生成自然语言响应。

# pip install --upgrade --quiet  langchain
# pip install --upgrade --quiet  langchain-openai

from langchain_neo4j import Neo4jGraph, GraphCypherQAChain
from langchain_openai import ChatOpenAI

graph = Neo4jGraph(url=NEO4J_URI, username=NEO4J_USERNAME, password=NEO4J_PASSWORD)

# Insert some movie data
graph.query(
"""
MERGE (m:Movie {title:'Top Gun'})
WITH m
UNWIND ['Tom Cruise', 'Val Kilmer', 'Anthony Edwards', 'Meg Ryan'] AS actor
MERGE (a:Actor {name:actor})
MERGE (a)-[:ACTED_IN]->(m)
"""
)

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True,
    allow_dangerous_requests=True
)

chain.run("Who acted in Top Gun?")

高级 RAG 策略

除了基本的 RAG 策略，LangChain 中的 Neo4j 集成还支持高级 RAG 策略，这些策略允许更复杂的检索策略。这些也以 LangChain 模板的形式提供。

常规 RAG - 直接向量搜索
父-子检索器 - 将代表特定概念的嵌入块链接到父文档
假设问题 - 从文档块生成问题并对其进行向量索引，以便为用户问题提供更好的匹配候选
摘要 - 索引文档的摘要而非整个文档
使用 Neo4j 实现高级检索 RAG 策略

pip install -U "langchain-cli[serve]"

langchain app new my-app --package neo4j-advanced-rag

# update server.py to add the neo4j-advanced-rag template as an endpoint
cat <<EOF > server.py
from fastapi import FastAPI
from langserve import add_routes

from neo4j_advanced_rag import chain as neo4j_advanced_chain

app = FastAPI()

# Add this
add_routes(app, neo4j_advanced_chain, path="/neo4j-advanced-rag")


if __name__ == "__main__":
    import uvicorn

    uvicorn.run(app, host="0.0.0.0", port=8000)
EOF

langchain serve