LlamaAgents Builder: From Immediate to Deployed AI Agent in Minutes

On this article, you’ll discover ways to construct, deploy, and check a no-code document-processing AI agent with LlamaAgents Builder in LlamaCloud.

Subjects we are going to cowl embrace:

• Easy methods to create a document-classification agent utilizing a pure language immediate.
• Easy methods to deploy the agent to a GitHub-backed utility with out writing code.
• Easy methods to check the deployed agent on invoices and contracts within the LlamaCloud interface.

Let’s not waste any extra time.

LlamaAgents Builder: From Immediate to Deployed AI Agent in Minutes (click on to enlarge)
Picture by Editor

Introduction

Creating an AI agent for duties like analyzing and processing paperwork autonomously used to require hours of near-endless configuration, code orchestration, and deployment battles. Till now.

This text unveils the method of constructing, deploying, and utilizing an clever agent from scratch with out writing a single line of code, utilizing LlamaAgents Builder. Higher nonetheless, we are going to host it as an app in a software program repository that will likely be 100% owned by us.

We’ll full the entire course of in a matter of minutes, so time is of the essence: let’s get began.

Constructing with LlamaAgents Builder

LlamaAgents Builder is likely one of the latest options within the LlamaCloud net platform, whose flagship product was initially launched as LlamaParse. A barely complicated mixture of names, I do know! For now, simply remember the fact that we are going to entry the brokers builder by this hyperlink.

The very first thing you must see is a house menu just like the one proven within the screenshot under. If this isn’t what you see, attempt clicking the “LlamaParse” icon within the top-left nook as a substitute, after which you must see this — a minimum of on the time of writing.

LlamaParse dwelling menu

Discover that, on this instance, we’re working underneath a newly created free-plan account, which permits as much as 10,000 pages of processing.

See the “Brokers” block on the bottom-right facet? That’s the place LlamaAgents Builder lives. Regardless that it’s in beta on the time of writing, we will already construct helpful agent-based workflows, as we are going to see.

As soon as we click on on it, a brand new display will open with a chat interface much like Gemini, ChatGPT, and others. You’ll get a number of advised workflows for what you’d like your agent to do, however we are going to specify our personal by typing the next immediate into the enter field on the backside. Simply pure language, no code in any respect:

Create an agent that classifies paperwork into “Contracts” and “Invoices”. For contracts, extract the signing events; for invoices, the full quantity and date.

Specifying what the agent ought to do with a pure language immediate

Merely ship the immediate, and the magic will begin. With a exceptional degree of transparency within the reasoning course of, you’ll see the steps accomplished and the progress made to date:

AgentBuilder creating our agent workflow

After a couple of minutes, the creation course of will likely be full. Not solely are you able to see the complete workflow diagram, which has steadily grown all through the method, however you additionally obtain a succinct and clear description of the way to use your newly created agent. Merely superb.

Agent workflow constructed

The following step is to deploy our agent in order that it may be used. Within the top-right nook, you might even see a “Push & Deploy” button. This initiates the method of publishing your agent workflow’s software program packages right into a GitHub repository, so ensure you have a registered account on GitHub first. You’ll be able to simply register with an present Google or Microsoft account, as an example. After you have the LlamaCloud platform related to your GitHub account, this can be very simple to push and deploy your agent: simply give it a reputation, specify whether or not you need it in a personal repository, and that’s it:

Pushing and deploying agent workflow into GitHub

The method will take a couple of minutes, and you will notice a stream of command-line-like messages showing on the fly. As soon as it’s finalized and your agent standing seems as “Working“, you will notice a couple of ultimate messages much like this:

The “Uvicorn” messages point out that our agent has been deployed and is operating as a microservice API inside the LlamaCloud infrastructure. In case you are acquainted with FastAPI endpoints, you might need to attempt it programmatically by the API, however on this tutorial, we are going to maintain issues less complicated (we promised zero coding, didn’t we?) and check out the whole lot ourselves in LlamaCloud’s personal person interface.

To do that, click on the “Go to” button that seems on the prime:

Deployed agent up and operating

Now comes probably the most thrilling half. It is best to have been taken to a playground web page referred to as “Evaluation,” the place you may attempt your agent out. Begin by importing a file, for instance, a PDF doc containing an bill or a contract. In case you don’t have one, simply create a fictitious instance doc of your individual utilizing Microsoft Phrase, Google Docs, or an identical device, reminiscent of this one:

LlamaCloud Agent Testing UI: processing an bill

As quickly because the doc is loaded, the agent begins working by itself, and in a matter of seconds, it should classify your doc and extract the required knowledge fields, relying on the doc sort. You’ll be able to see this outcome on the right-hand-side panel within the picture above: the full quantity and bill date have been accurately extracted by the agent.

How about importing an instance doc containing a contract now?

LlamaCloud Agent Testing UI: processing a contract

As anticipated, the doc is now categorized as a contract, and on this event, the extracted data consists of the names of the signing events.

Properly performed! As you retain operating examples, ensure you approve or reject them primarily based on whether or not they have been processed accurately: this helps the agent study from suggestions.

Agent testing circumstances and their standing

Wrapping Up

We’ve seen the way to construct and deploy, step-by-step and with no strains of code, an AI agent able to classifying paperwork and processing them in several methods relying on the doc sort — all in a matter of minutes and inside LlamaCloud’s newly added characteristic, LlamaAgents Builder.