杭州信贷网站制作,陕西天和建设有限公司网站,中铁集团招聘2022招聘信息,网站定制案例微安电力检索增强生成#xff08;Retrieval-Augmented Generation, RAG#xff09;作为应用大模型落地的方案之一#xff0c;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#xff0c;为公司内部人员快速检索内部… 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。 01. Naive RAG的局限性 Naive RAG方法在处理简单问题时表现良好例如 “特斯拉的主要风险因素是什么”基于特斯拉2021年10K报告“Milvus 2.4有哪些功能”基于Milvus 2.4 release note 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。 02. 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。 03. 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。 04. 实践 我们基于MilvusLlamaIndex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_size3,window_metadata_keywindow,original_text_metadata_keyoriginal_text,
)# Extract nodes from documents
nodes node_parser.get_nodes_from_documents(documents)vector_store MilvusVectorStore(dim1536, urihttp://localhost:19530,collection_nameagentic_rag,overwriteTrue,enable_sparseFalse,hybrid_rankerRRFRanker,hybrid_ranker_params{k: 60})storage_context StorageContext.from_defaults(vector_storevector_store)index VectorStoreIndex(nodes, storage_contextstorage_context
) 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_parsers defaultpostproc MetadataReplacementPostProcessor(target_metadata_keywindow)# BAAI/bge-reranker-base is a cross-encoder model# link: https://huggingface.co/BAAI/bge-reranker-basererank BGERerankFunction(top_n 3, model_name BAAI/bge-reranker-base,devicecpu)# The QueryEngine class is equipped with the generator and facilitates the retrieval and generation stepsquery_engine vector_index.as_query_engine(similarity_top_k 3, vector_store_query_modehybrid, # Milvus starts supporting from version 2.4, use Default for versions before 2.4node_postprocessors [postproc, rerank],)response query_engine.query(query)return responsevector_query_tool FunctionTool.from_defaults(namefvector_tool_{name},fnvector_query
) summary_index SummaryIndex(nodes)
summary_query_engine summary_index.as_query_engine(response_modetree_summarize,use_asyncTrue,
)
summary_tool QueryEngineTool.from_defaults(namefsummary_tool_{name},query_enginesummary_query_engine,description(fUseful for summarization questions related to {name}),
) 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?
) 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_3
Action Input: {query: Whats 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_3
Action Input: {input: Whats 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_4
Action Input: {input: Whats 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. 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. 05. 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#slideid.g2c00d03c26e_0_64 作者介绍 Milvus 北辰使者臧伟 推荐阅读
