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 methods to tie collectively two formidable instruments — OpenAI‘s GPT fashions and the Airtable cloud-based database — to prototype a easy, toy-sized retrieval-augmented era (RAG) system. The system accepts question-based prompts and makes use of textual content knowledge saved in Airtable because the information base to supply grounded solutions. In case you’re unfamiliar with RAG techniques, or desire a refresher, don’t miss this article collection on understanding RAG.
# The Components
To observe this tutorial your self, you will want:
- An Airtable account with a base created in your workspace.
- An OpenAI API key (ideally a paid plan for flexibility in mannequin selection).
- A Pipedream account — an orchestration and automation app that permits experimentation below a free tier (with limits on every day runs).
# The Retrieval-Augmented Era 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 could 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 components, utilizing Pipedream:
- Set off: much like an online service request, this factor initiates an motion stream that passes by means of the following components within the workflow. As soon as deployed, that is the place you specify the request, i.e., the person immediate for our prototype RAG system.
- Airtable block: establishes a connection to our Airtable base and particular desk to make use of its knowledge because the RAG system’s information base. We’ll add some textual content knowledge to it shortly inside Airtable.
- OpenAI block: connects to OpenAI’s GPT-based language fashions utilizing an API key and passes the person immediate alongside the context (retrieved Airtable knowledge) to the mannequin to acquire a response.
However first, we have to create a brand new desk in our Airtable base containing textual content knowledge. 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 knowledge from this publicly obtainable small dataset containing textual content with primary information about Asian international locations. Use the CSV and hyperlink choices to import the info into the desk. Extra details about creating tables and importing knowledge is in this text.
After getting your information base prepared in Airtable, let’s change to Pipedream for the remainder of the method! Register should you haven’t executed so but, and log in. There are a number of methods to provoke a workflow. One in all them is by describing what you wish to create to Pipedream’s AI agent, which is intuitive however could end in errors needing fixes, as we’ll illustrate shortly. Pipedream has two parallel UIs: one for manually constructing and enhancing workflows, and one for conversations with its AI agent, known as String.
Pipedream’s AI conversational interface (String)
In case 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 software 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 danger), like this:
I will create a easy RAG (Retrieval-Augmented Era) agent that connects your Airtable desk with OpenAI’s GPT fashions. Here is what I will construct:
Arrange a set off to simply accept queries (through webhook or handbook 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 knowledge
This provides you with a primary RAG system the place you’ll be able to 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 advised plan of action to acquire a three-block workflow much like the one within the picture proven above.
Since this isn’t the core Pipedream editor UI, change 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 mechanically generated with a syntax much like this one I acquired 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 bit work to do. First, hook up with your Airtable base. In case you’re working in the identical browser, this may be easy: sign up 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 tough half (and a cause I deliberately left an imperfect immediate earlier when asking the AI agent to construct the skeleton workflow): there are a number of kinds of Airtable actions to select from, and the precise one we want for a RAG-style retrieval mechanism is “Record data.” Likelihood is, 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 “Record data.” Then reconnect to your desk and check the connection to make sure it really works.
That is what a efficiently examined connection appears to be like like:
Pipedream workflow editor: testing connection to Airtable
Final, arrange and configure OpenAI entry to GPT. Preserve 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 person query subject must be set as {{ steps.set off.occasion.physique.check }}, and the information base data (your textual content “paperwork” for RAG from Airtable) should be set as {{ steps.list_records.$return_value }}.
You possibly can maintain the remaining as default and check, however you could encounter parsing errors widespread to those sorts of workflows, prompting you to leap again to String for assist and computerized fixes utilizing the AI agent. Alternatively, you’ll be able to straight copy and paste the next into the OpenAI element’s code subject on the backside for a sturdy answer:
import openai from "@pipedream/openai"
export default defineComponent({
identify: "Generate RAG Response",
description: "Generate a response utilizing OpenAI primarily based on person query and Airtable information base content material",
sort: "motion",
props: {
openai,
mannequin: {
propDefinition: [
openai,
"chatCompletionModelId",
],
},
query: {
sort: "string",
label: "Consumer Query",
description: "The query from the webhook set off",
default: "{{ steps.set off.occasion.physique.check }}",
},
knowledgeBaseRecords: {
sort: "any",
label: "Data Base Data",
description: "The Airtable data containing the information base content material",
default: "{{ steps.list_records.$return_value }}",
},
},
async run({ $ }) {
// Extract person query
const userQuestion = this.query;
if (!userQuestion) {
throw new Error("No query supplied from the set off");
}
// Course of Airtable data to extract content material
const data = this.knowledgeBaseRecords;
let knowledgeBaseContent = "";
if (data && Array.isArray(data)) {
knowledgeBaseContent = data
.map(document => {
// Extract content material from fields.Content material
const content material = document.fields?.Content material;
return content material ? content material.trim() : "";
})
.filter(content material => content material.size > 0) // Take away empty content material
.be part of("nn---nn"); // Separate completely different information base entries
}
if (!knowledgeBaseContent) {
throw new Error("No content material present in information base data");
}
// Create system immediate with information base context
const systemPrompt = `You're a useful assistant that solutions questions primarily based on the supplied information base. Use solely the knowledge from the information base beneath to reply questions. If the knowledge will not be obtainable within the information base, please say so.
Data Base:
${knowledgeBaseContent}
Directions:
- Reply primarily based solely on the supplied information base content material
- Be correct and concise
- If the reply will not be within the information base, clearly state that the knowledge will not be obtainable
- Cite related components of the information base when doable`;
// 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({
$,
knowledge: {
mannequin: this.mannequin,
messages: messages,
temperature: 0.7,
max_tokens: 1000,
},
});
const generatedResponse = response.generated_message?.content material;
if (!generatedResponse) {
throw new Error("Did not generate response from OpenAI");
}
// Export abstract for person 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: data ? data.size : 0,
full_openai_response: response,
};
},
})
If no errors or warnings seem, you need to be prepared to check and deploy. Deploy first, after which check by passing a person 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 every part runs appropriately, scroll all the way down to see the response returned by the GPT mannequin accessed within the final stage of the workflow:
GPT mannequin response
Properly executed! This response is grounded within the information base we inbuilt Airtable, so we now have a easy prototype RAG system that mixes Airtable and GPT fashions through Pipedream.
# Wrapping Up
This text confirmed methods 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 era. Pipedream permits defining orchestration workflows programmatically, manually, or aided by its conversational AI agent. Via the writer’s experiences, we succinctly showcased the professionals and cons of every strategy.
Iván Palomares Carrascosa is a pacesetter, author, speaker, and adviser in AI, machine studying, deep studying & LLMs. He trains and guides others in harnessing AI in the actual world.