知识图谱检索增强的GraphRAG(基于Neo4j代码实现）

class GraphRag(object):def __init__(self):        """Any embedding function implementing `langchain.embeddings.base.Embeddings` interface."""self._database = 'neo4j'self.label = 'Med'self._driver = neo4j.GraphDatabase.driver(uri=os.environ["NEO4J_URI"],auth=(os.environ["NEO4J_USERNAME"],os.environ["NEO4J_PASSWORD"]))        self.embeddings_zh = HuggingFaceEmbeddings(model_name=os.environ["EMBEDDING_MODEL"])self.vectstore = Neo4jVector(embedding=self.embeddings_zh, username=os.environ["NEO4J_USERNAME"], password=os.environ["NEO4J_PASSWORD"], url=os.environ["NEO4J_URI"], node_label=self.label, index_name="vector" )

def query(self, query: str, params: dict = {}) -> List[Dict[str, Any]]:"""Query Neo4j database."""from neo4j.exceptions import CypherSyntaxError
with self._driver.session(database=self._database) as session:try:data = session.run(query, params)return [r.data() for r in data]except CypherSyntaxError as e:raise ValueError(f"Generated Cypher Statement is not valid\n{e}")
def add_embeddings(self):"""Add embeddings to Neo4j database."""# 查询图中所有节点，并且根据节点的描述和名字生成embedding，添加到该节点上query = """MATCH (n) WHERE not (n:{}) RETURN ID(n) AS id, labels(n) as labels, n""".format(self.label)print("qurey node...")data = self.query(query)ids, texts, embeddings, metas = [], [], [], []for row in tqdm(data,desc="parsing node"):ids.append(row['id'])text = row['n'].get('name','') + row['n'].get('desc','')texts.append(text)metas.append({"label": row['labels'], "context": text})self.embeddings_zh.multi_process = False
print("node embeddings...")embeddings = self.embeddings_zh.embed_documents(texts)print("adding node embeddings...")ids_ret = self.vectstore.add_embeddings(ids=ids,texts=texts,embeddings=embeddings,metadatas=metas)        return ids_ret
# Fulltext index query    def structured_retriever(self, query, limit=3, simlarity=0.9) -> str:"""        Collects the neighborhood of entities mentioned in the question"""        # step1 从图谱中检索与查询相关的实体。docs_with_score = self.vectstore.similarity_search_with_score(query, k=topk)entities = [item[0].page_content for item in data if item[1] > simlarity] # scoreself.vectstore.query("CREATE FULLTEXT INDEX entity IF NOT EXISTS FOR (e:Med) ON EACH [e.context]")result = ""for entity in entities:qry = entity            # step2 从全局索引中查出entity label，query1 =f"""CALL db.index.fulltext.queryNodes('entity', '{qry}') YIELD node, score return node.label as label,node.context as context, node.id as id, score LIMIT {limit}"""data1 = self.vectstore.query(query1)            # step3 根据label在相应的节点中查询邻居节点路径for item in data1:node_type = item['label']node_type = item['label'] if type(node_type) == str else node_type[0]node_id = item['id']query2 = f"""match (node:{node_type})-[r]-(neighbor) where ID(node) = {node_id} RETURN type(r) as rel, node.name+' - '+type(r)+' - '+neighbor.name as output limit 50"""data2 = self.vectstore.query(query2)                # step4 为了保持多样性，对关系进行筛选rel_dict = defaultdict(list)if len(data2) > 3*limit:for item1 in data2:rel_dict[item1['rel']].append(item1['output'])if rel_dict:rel_dict = {k:random.sample(v, 3) if len(v)>3 else v for k,v in rel_dict.items()}result += "\n".join(['\n'.join(el) for el in rel_dict.values()]) +'\n'else:result += "\n".join([el['output'] for el in data2]) +'\n'return result