LlamaIndex goes beyond RAG so agents can make complex decisions

Popular AI orchestration framework LlamaIndex It introduced Agent Document Workflow (ADW), a new architecture that the company says goes beyond augmented retrieval generation (RAG) processes and increases agent productivity.

As coordination frameworks continue to improve, this method could provide organizations with an option to enhance agents’ decision-making capabilities.

LlamaIndex says ADW can help agents manage “complex workflows beyond simple extraction or matching.”

Some agent frameworks are based on RAG systems, which provide agents with the information they need to complete tasks. However, this method does not allow agents to make decisions based on this information.

LlamaIndex provided some real-life examples of how ADW works well. For example, in contract reviews, human analysts must extract key information, reference regulatory requirements, identify potential risks and issue recommendations. When deployed in this workflow, AI agents would ideally follow the same pattern and make decisions based on the documents they read to review contracts and knowledge from other documents.

“ADW addresses these challenges by treating documents as part of broader business processes,” LlamaIndex said in a report Blog post. “An ADW system can maintain state across steps, apply business rules, coordinate different components, and take actions based on the content of the document – ​​not just parsing it.”

LlamaIndex has previously said that RAG, although an important technology, It remains primitiveespecially for organizations seeking more powerful decision-making capabilities using artificial intelligence.

Understand the context of decision making

LlamaIndex has developed reference architectures that combine the analysis capabilities of LlamaCloud and agents. It “builds systems that can understand context, maintain state, and drive multi-step processes.”

To do this, each workflow has a document that acts as a formatter. It can direct agents to click on LlamaParse to extract information from data, maintain and process document context state, and then retrieve reference material from another knowledge base. From here, agents can start creating contract review use case recommendations or other actionable decisions for different use cases.

“By maintaining status throughout the process, agents can handle complex, multi-step workflows that go beyond simple extraction or matching,” the company said. “This approach allows them to build deep context around the documents they are processing while coordinating between different system components.”

Different proxy frameworks

Proxy format It’s an emerging space, and many organizations are still exploring how agents – or multiple agents – can work for them. AI agents and applications may become coordinated A bigger conversation This is the year where agents move from single systems to multi-agent ecosystems.

AI agents are an extension of what RAG offers, which is the ability to find information based on institutional knowledge.

But as more organizations start deploying AI agents, they also want them to do many of the tasks done by human employees. For these more complex use cases, “vanilla” RAG is not enough. One advanced approach that companies have taken into consideration is RAG Agentwhich expands the agents’ knowledge base. Models can decide whether they need to find more information, which tool to use to get that information and whether the context they just fetched is relevant, before arriving at a conclusion.

Daily insights into business use cases with VB Daily

If you want to impress your boss, VB Daily has you covered. We give you the inside scoop on what companies are doing with generative AI, from organizational transformations to hands-on deployments, so you can share insights to maximize ROI.

Read our privacy policy

Thanks for subscribing. Check more VB newsletters here.

An error occurred.