检索增强生成（Retrieval-Augmented Generation, RAG）作为应用大模型落地的方案之一，通过让 LLM 获取上下文最新数据来解决 LLM 的局限性。典型的应用案例是基于公司特定的文档和知识库开发的聊天机器人，为公司内部人员快速检索内部文档提供便利。另外，也适用于特定领域的 GenAI 应用，如医疗保健、金融和法律服务。尽管 Naive RAG 在处理简单问题时表现良好，但在面对复杂任务时却显得力不从心。本文将探讨 Naive RAG 的局限性，并介绍如何通过引入代理（Agentic）方法来提升 RAG 系统的智能性和实用性。
Naive RAG 的局限性
Naive RAG 方法在处理简单问题时表现良好，例如：
然而，当面对更复杂的问题时，Naive RAG 的局限性就显现出来了。
总结性问题：例如，“给我一个公司 10K 年度报告的总结”，Naive RAG 难以在不丢失重要信息的情况下生成全面的总结。
比较性问题：例如，“Milvus 2.4 与 Milvus 2.3 区别有哪些”，Naive RAG 难以有效地进行多文档比较。
结构化分析和语义搜索：例如，“告诉我美国表现最好的网约车公司的风险因素”，Naive RAG 难以在复杂的语义搜索和结构化分析中表现出色。
一般性多部分问题：例如，“告诉我文章 A 中的支持 X 的论点，再告诉我文章 B 中支持 Y 的论点，按照我们的内部风格指南制作一个表格，然后基于这些事实生成你自己的结论”，Naive RAG 难以处理多步骤、多部分的复杂任务。
Naive RAG 上述痛点的原因
单次处理：Naive RAG 通常是一次性处理查询，缺乏多步骤的推理能力。
缺乏查询理解和规划：Naive RAG 无法深入理解查询的复杂性，也无法进行任务规划。
缺乏工具使用能力：Naive RAG 无法调用外部工具或 API 来辅助完成任务。
缺乏反思和错误纠正：Naive RAG 无法根据反馈进行自我改进。
无记忆（无状态）：Naive RAG 无法记住对话历史，无法在多轮对话中保持上下文一致性。
从 RAG 到 Agentic RAG
为了克服 Naive RAG 的局限性，我们可以引入代理方法（Agentic），使 RAG 系统更加智能和灵活。
路由
路由是最简单的代理推理形式。给定用户查询和一组选择，系统可以输出一个子集，将查询路由到合适的处理模块。
工具
调用外部工具或 API 来辅助完成任务。比如，使用查询天气接口来获取最新的天气信息。
查询/任务规划
将查询分解为可并行处理的子查询。每个子查询可以针对任何一组 RAG 管道执行，从而提高处理效率和准确性。
反思
使用反馈来改进代理的执行并减少错误，反馈可以来自 LLM 自身。
记忆
除了当前查询外，还可以将对话历史作为输入，纳入 RAG 管道中，从而在多轮对话中保持上下文一致性。
实践
我们基于 Milvus，llamaIndex 构建一个 Agentic RAG 案例。
首先，我们把 Milvus 2.3 和 2.4 release note 文档，通过 llamaIndex SentenceWindowNodeParser分段之后，导入到 Milvus。
node_parser = SentenceWindowNodeParser.from_defaults( window_size=3, window_metadata_key="window", original_text_metadata_key="original_text",)
# Extract nodes from documentsnodes = node_parser.get_nodes_from_documents(documents)
vector_store = MilvusVectorStore(dim=1536, uri="http://localhost:19530", collection_name='agentic_rag', overwrite=True, enable_sparse=False, hybrid_ranker="RRFRanker", hybrid_ranker_params={"k": 60})
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex( nodes, storage_context=storage_context)
复制代码
然后，我们定义两个 agent tool，他们分别是 vector query tool 和 summary tool。vector query tool 利用了 Milvus Hybrid search 能力。summary tool 采用了 llamaIndex 的 SummaryIndex 对于文档块提取 summary。
def vector_query( query: str, page_numbers: Optional[List[int]] = None) -> str: # The target key defaults to `window` to match the node_parser's default postproc = MetadataReplacementPostProcessor( target_metadata_key="window" ) # BAAI/bge-reranker-base is a cross-encoder model # link: https://huggingface.co/BAAI/bge-reranker-base rerank = BGERerankFunction( top_n = 3, model_name = "BAAI/bge-reranker-base", device="cpu" )
# The QueryEngine class is equipped with the generator and facilitates the retrieval and generation steps query_engine = vector_index.as_query_engine( similarity_top_k = 3, vector_store_query_mode="hybrid", # Milvus starts supporting from version 2.4, use 'Default' for versions before 2.4 node_postprocessors = [postproc, rerank], )
response = query_engine.query(query) return response
vector_query_tool = FunctionTool.from_defaults( name=f"vector_tool_{name}", fn=vector_query)
复制代码
summary_index = SummaryIndex(nodes)summary_query_engine = summary_index.as_query_engine( response_mode="tree_summarize", use_async=True,)summary_tool = QueryEngineTool.from_defaults( name=f"summary_tool_{name}", query_engine=summary_query_engine, description=( f"Useful for summarization questions related to {name}" ),)
复制代码
最后，通过 llamaIndex 的ReActAgentWorker整合 vector query tool 和 summary tool，以及 React 的特性，反思，路由以及使用工具能力，实现 Agentic RAG。
response = agent.query( "Tell me about the difference between milvus 2.3 and milvus 2.4?")
复制代码
这是对于上述问题的思考过程，包括 React 的观察，思考，行动具体步骤
Thought: The user is asking about the differences between Milvus 2.3 and Milvus 2.4. I need to gather information about both versions to provide a comprehensive comparison.Action: vector_tool_milvus_2_3Action Input: {'query': "What's new in Milvus 2.3?"}Thought: It appears there is a persistent issue with the tool input. I will try using a different tool to gather the necessary information.Action: summary_tool_milvus_2_3Action Input: {'input': "What's new in Milvus 2.3?"}Observation: Milvus 2.3 introduces several new features and enhancements, including GPU support, Arm64 support, a refactored QueryNode, and a merged IndexCoord and DataCoord for simplified deployment. It also includes a new NATS-based message queue, upsert API, range search, count statement, cosine metrics, raw vectors in search returns, ScaNN index support, iterator functionality, JSON_CONTAINS expressions, and CDC support. Additionally, there are performance improvements such as MMap for capacity increase, optimized data filtering, growing index, and increased resource usage in multi-core environments. The release also features a new load balancer, dynamic configuration support, tracing support, reorganized error codes, and upgraded tools like Birdwatcher and Attu.Thought: I have gathered information about the new features and enhancements in Milvus 2.3. Now, I need to gather similar information for Milvus 2.4 to compare the two versions.Action: summary_tool_milvus_2_4Action Input: {'input': "What's new in Milvus 2.4?"}Observation: Milvus 2.4 introduces several new features and improvements. Key highlights include:...These updates aim to enhance system performance, improve observability, and streamline the codebase for increased simplicity.Thought: I now have detailed information about the new features and enhancements in both Milvus 2.3 and Milvus 2.4. I can compare the two versions based on these details.
复制代码
输出的答案，从答案来看，不仅详细列举了 Milvus 2.3 和 Milvus 2.4 各种功能特性，还有功能总结与对比。
Answer: Milvus 2.3 and Milvus 2.4 both introduce significant new features and improvements, but they focus on different aspects of the system. Here are the key differences:
### Milvus 2.3:1. **GPU and Arm64 Support**: Introduces GPU support and Arm64 support.2. **Refactored QueryNode**: Simplifies deployment by merging IndexCoord and DataCoord.3. **New Message Queue**: Implements a NATS-based message queue.4. **New APIs and Features**: Includes upsert API, range search, count statement, cosine metrics, raw vectors in search returns, ScaNN index support, iterator functionality, JSON_CONTAINS expressions, and CDC support.5. **Performance Improvements**: Features MMap for capacity increase, optimized data filtering, growing index, and increased resource usage in multi-core environments.6. **Load Balancer and Dynamic Configuration**: Introduces a new load balancer and dynamic configuration support.7. **Tool Upgrades**: Upgrades tools like Birdwatcher and Attu.
### Milvus 2.4:1. **New GPU Index - CAGRA**: Introduces a state-of-the-art GPU-based graph index for significant performance boosts.2. **Multi-vector and Hybrid Search**: Supports storing vector embeddings from multiple models and conducting hybrid searches.3. **Sparse Vectors**: Supports efficient approximate semantic nearest neighbor search for keyword interpretation and analysis.4. **Grouping Search**: Allows aggregation of search results by specific scalar fields.5. **Inverted Index and Fuzzy Match**: Improves scalar query performance and supports fuzzy matches.6. **New Data Types**: Supports Float16 and BFloat16 vector data types.7. **L0 Segment**: Enhances performance of delete and upsert operations by recording deleted data.8. **Refactored BulkInsert**: Improves logic for importing multiple files in a single request.9. **Memory-mapped Storage**: Optimizes memory usage by mapping file content into memory.10. **Milvus-CDC**: Improves stability for capturing and synchronizing incremental data.
### Summary:- **Milvus 2.3** focuses on broadening hardware support, enhancing deployment simplicity, and introducing various new APIs and performance improvements.- **Milvus 2.4** emphasizes advanced search capabilities, new data types, improved memory management, and further performance optimizations.
Both versions aim to enhance system performance and usability, but Milvus 2.4 introduces more advanced search features and optimizations compared to Milvus 2.3.
复制代码
结论
从 Naive RAG 到 Agentic RAG 的转变，标志着检索增强生成技术的一个重要进步。通过引入代理（Agentic）方法，我们可以显著提升 RAG 系统在处理复杂任务时的能力。这不仅使得 RAG 系统更加智能和灵活，也为其在实际应用中提供了更广阔的前景。未来，我们可以期待更多基于 Agentic RAG 的创新应用，推动大模型技术的发展。
Ref: https://docs.google.com/presentation/d/1IWjo8bhoatWccCfGLYw_QhUI4zfF-MujN3ORIDCBIbc/edit#slide=id.g2c00d03c26e_0_64
作者介绍
Milvus 北辰使者：臧伟
评论