Picture by Editor | ChatGPT
# Introduction
Prepared for a sensible walkthrough with little to no code concerned, relying on the strategy you select? This tutorial reveals the right way to tie collectively two formidable instruments — OpenAI‘s GPT fashions and the Airtable cloud-based database — to prototype a easy, toy-sized retrieval-augmented technology (RAG) system. The system accepts question-based prompts and makes use of textual content information saved in Airtable because the information base to provide grounded solutions. Should you’re unfamiliar with RAG techniques, or desire a refresher, don’t miss this article collection on understanding RAG.
# The Substances
To apply this tutorial your self, you may want:
- An Airtable account with a base created in your workspace.
- An OpenAI API key (ideally a paid plan for flexibility in mannequin alternative).
- A Pipedream account — an orchestration and automation app that allows experimentation beneath a free tier (with limits on every day runs).
# The Retrieval-Augmented Technology Recipe
The method to construct our RAG system isn’t purely linear, and a few steps might be taken in numerous methods. Relying in your degree of programming information, you might go for a code-free or almost code-free strategy, or create the workflow programmatically.
In essence, we’ll create an orchestration workflow consisting of three elements, utilizing Pipedream:
- Set off: just like an internet service request, this ingredient initiates an motion move that passes by the following components within the workflow. As soon as deployed, that is the place you specify the request, i.e., the consumer immediate for our prototype RAG system.
- Airtable block: establishes a connection to our Airtable base and particular desk to make use of its information because the RAG system’s information base. We’ll add some textual content information to it shortly inside Airtable.
- OpenAI block: connects to OpenAI’s GPT-based language fashions utilizing an API key and passes the consumer immediate alongside the context (retrieved Airtable information) to the mannequin to acquire a response.
However first, we have to create a brand new desk in our Airtable base containing textual content information. For this instance, I created an empty desk with three fields (ID: one-line textual content, Supply: one-line textual content, Content material: lengthy textual content), after which imported information from this publicly obtainable small dataset containing textual content with primary information about Asian nations. Use the CSV and hyperlink choices to import the info into the desk. Extra details about creating tables and importing information is in this text.
After getting your information base prepared in Airtable, let’s swap to Pipedream for the remainder of the method! Register should you haven’t performed so but, and log in. There are a number of methods to provoke a workflow. One among them is by describing what you wish to create to Pipedream’s AI agent, which is intuitive however could lead to errors needing fixes, as we’ll illustrate shortly. Pipedream has two parallel UIs: one for manually constructing and modifying workflows, and one for conversations with its AI agent, referred to as String.
Pipedream’s AI conversational interface (String)
Should you go for letting String construct an approximate model of your required workflow, describe clearly what to construct, with a immediate that will look one thing like:
I might prefer to orchestrate a easy toy RAG utility that makes use of an Airtable desk containing textual content, and OpenAI’s GPT fashions (I’ve a paid API key).
Pipedream’s language mannequin could return a solution so that you can approve (at your individual threat), like this:
I will create a easy RAG (Retrieval-Augmented Technology) agent that connects your Airtable desk with OpenAI’s GPT fashions. This is what I will construct:
Arrange a set off to just accept queries (through webhook or guide execution)
Search and retrieve related textual content out of your Airtable desk primarily based on the question
Use the retrieved textual content as context for OpenAI GPT to generate an knowledgeable response
Return the AI-generated reply that is grounded in your Airtable information
This provides you with a primary RAG system the place you possibly can ask questions and get solutions primarily based on the content material saved in your Airtable, enhanced by GPT’s reasoning capabilities.
For the sake of experimentation and “seeing what occurs,” approve the recommended plan of action to acquire a three-block workflow just like the one within the picture proven above.
Since this isn’t the core Pipedream editor UI, swap to it by clicking “Open Pipedream” within the higher proper nook. A brand new tab will open with the precise Pipedream workflow editor.
For the set off block, a URL is routinely generated with a syntax just like this one I obtained for mine: https://eoupscprutt37xx.m.pipedream.web. Click on it and, within the settings pane that opens on the right-hand aspect, guarantee the primary couple of choices are set to “Full HTTP request” and “Return a static response.”
For the second block (Airtable motion) there could also be a little bit work to do. First, hook up with your Airtable base. Should you’re working in the identical browser, this is likely to be simple: register to Airtable from the pop-up window that seems after clicking “Join new account,” then observe the on-screen steps to specify the bottom and desk to entry:
Pipedream workflow editor: connecting to Airtable
Right here comes the difficult half (and a motive I deliberately left an imperfect immediate earlier when asking the AI agent to construct the skeleton workflow): there are a number of sorts of Airtable actions to select from, and the particular one we’d like for a RAG-style retrieval mechanism is “Checklist information.” Chances are high, this isn’t the motion you see within the second block of your workflow. If that’s the case, take away it, add a brand new block within the center, choose “Airtable,” and select “Checklist information.” Then reconnect to your desk and check the connection to make sure it really works.
That is what a efficiently examined connection seems like:
Pipedream workflow editor: testing connection to Airtable
Final, arrange and configure OpenAI entry to GPT. Maintain your API key helpful. In case your third block’s secondary label isn’t “Generate RAG response,” take away the block and substitute it with a brand new OpenAI block with this subtype.
Begin by establishing an OpenAI connection utilizing your API key:
Establishing OpenAI connection
The consumer query subject needs to be set as {{ steps.set off.occasion.physique.check }}, and the information base information (your textual content “paperwork” for RAG from Airtable) should be set as {{ steps.list_records.$return_value }}.
You may maintain the remaining as default and check, however you might encounter parsing errors frequent to those sorts of workflows, prompting you to leap again to String for assist and automated fixes utilizing the AI agent. Alternatively, you possibly can instantly copy and paste the next into the OpenAI element’s code subject on the backside for a sturdy resolution:
import openai from "@pipedream/openai"
export default defineComponent({
title: "Generate RAG Response",
description: "Generate a response utilizing OpenAI primarily based on consumer query and Airtable information base content material",
sort: "motion",
props: {
openai,
mannequin: {
propDefinition: [
openai,
"chatCompletionModelId",
],
},
query: {
sort: "string",
label: "Consumer Query",
description: "The query from the webhook set off",
default: "{{ steps.set off.occasion.physique.check }}",
},
knowledgeBaseRecords: {
sort: "any",
label: "Data Base Information",
description: "The Airtable information containing the information base content material",
default: "{{ steps.list_records.$return_value }}",
},
},
async run({ $ }) {
// Extract consumer query
const userQuestion = this.query;
if (!userQuestion) {
throw new Error("No query offered from the set off");
}
// Course of Airtable information to extract content material
const information = this.knowledgeBaseRecords;
let knowledgeBaseContent = "";
if (information && Array.isArray(information)) {
knowledgeBaseContent = information
.map(report => {
// Extract content material from fields.Content material
const content material = report.fields?.Content material;
return content material ? content material.trim() : "";
})
.filter(content material => content material.size > 0) // Take away empty content material
.be a part of("nn---nn"); // Separate totally different information base entries
}
if (!knowledgeBaseContent) {
throw new Error("No content material present in information base information");
}
// Create system immediate with information base context
const systemPrompt = `You're a useful assistant that solutions questions primarily based on the offered information base. Use solely the knowledge from the information base under to reply questions. If the knowledge shouldn't be obtainable within the information base, please say so.
Data Base:
${knowledgeBaseContent}
Directions:
- Reply primarily based solely on the offered information base content material
- Be correct and concise
- If the reply shouldn't be within the information base, clearly state that the knowledge shouldn't be obtainable
- Cite related elements of the information base when potential`;
// Put together messages for OpenAI
const messages = [
{
role: "system",
content: systemPrompt,
},
{
role: "user",
content: userQuestion,
},
];
// Name OpenAI chat completion
const response = await this.openai.createChatCompletion({
$,
information: {
mannequin: this.mannequin,
messages: messages,
temperature: 0.7,
max_tokens: 1000,
},
});
const generatedResponse = response.generated_message?.content material;
if (!generatedResponse) {
throw new Error("Didn't generate response from OpenAI");
}
// Export abstract for consumer suggestions
$.export("$abstract", `Generated RAG response for query: "${userQuestion.substring(0, 50)}${userQuestion.size > 50 ? '...' : ''}"`);
// Return the generated response
return {
query: userQuestion,
response: generatedResponse,
model_used: this.mannequin,
knowledge_base_entries: information ? information.size : 0,
full_openai_response: response,
};
},
})
If no errors or warnings seem, try to be prepared to check and deploy. Deploy first, after which check by passing a consumer question like this within the newly opened deployment tab:
Testing deployed workflow with a immediate asking what’s the capital of Japan
If the request is dealt with and all the pieces runs accurately, scroll right down to see the response returned by the GPT mannequin accessed within the final stage of the workflow:
GPT mannequin response
Nicely performed! This response is grounded within the information base we in-built Airtable, so we now have a easy prototype RAG system that mixes Airtable and GPT fashions through Pipedream.
# Wrapping Up
This text confirmed the right way to construct, with little or no coding, an orchestration workflow to prototype a RAG system that makes use of Airtable textual content databases because the information base for retrieval and OpenAI’s GPT fashions for response technology. Pipedream permits defining orchestration workflows programmatically, manually, or aided by its conversational AI agent. By the writer’s experiences, we succinctly showcased the professionals and cons of every strategy.
Iván Palomares Carrascosa is a frontrunner, author, speaker, and adviser in AI, machine studying, deep studying & LLMs. He trains and guides others in harnessing AI in the true world.
