Airtable + GPT: Prototyping a Light-weight RAG System with No-Code Instruments

# Introduction

 
Prepared for a sensible walkthrough with little to no code concerned, relying on the strategy you select? This tutorial reveals the 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 era (RAG) system. The system accepts question-based prompts and makes use of textual content information saved in Airtable because the information base to supply grounded solutions. In the event you’re unfamiliar with RAG techniques, or desire a refresher, don’t miss this text collection on understanding RAG.

# The Components

 
To apply 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 underneath a free tier (with limits on day by 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 several methods. Relying in your degree of programming information, it’s possible you’ll go for a code-free or practically code-free strategy, or create the workflow programmatically.

In essence, we’ll create an orchestration workflow consisting of three elements, utilizing Pipedream:

1. Set off: just like an internet service request, this factor initiates an motion stream that passes by the subsequent 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.
2. 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.
3. 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 accessible small dataset containing textual content with fundamental information about Asian nations. Use the CSV and hyperlink choices to import the information into the desk. Extra details about creating tables and importing information is on this article.

After you have your information base prepared in Airtable, let’s change to Pipedream for the remainder of the method! Register in the event you haven’t accomplished 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 modifying workflows, and one for conversations with its AI agent, known as String.

In the event you go for letting String construct an approximate model of your required workflow, describe clearly what to construct, with a immediate which will look one thing like:

I would wish 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 simply accept queries (by way of 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 offers you a fundamental 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 prompt 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, 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 just like this one I bought for mine: https://eoupscprutt37xx.m.pipedream.internet. 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, connect with your Airtable base. In the event you’re working in the identical browser, this is perhaps simple: check in to Airtable from the pop-up window that seems after clicking “Join new account,” then comply with the on-screen steps to specify the bottom and desk to entry:

Right here comes the difficult 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 sorts of Airtable actions to select from, and the precise one we’d like for a RAG-style retrieval mechanism is “Record 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 “Record information.” Then reconnect to your desk and take a look at the connection to make sure it really works.

That is what a efficiently examined connection appears like:

Final, arrange and configure OpenAI entry to GPT. Preserve your API key useful. In case your third block’s secondary label isn’t “Generate RAG response,” take away the block and exchange it with a brand new OpenAI block with this subtype.

Begin by establishing an OpenAI connection utilizing your API key:

The consumer query subject needs to be set as {{ steps.set off.occasion.physique.take a look at }}, and the information base information (your textual content “paperwork” for RAG from Airtable) should be set as {{ steps.list_records.$return_value }}.

You’ll be able to maintain the remainder as default and take a look at, however it’s possible you’ll encounter parsing errors frequent to those sorts of workflows, prompting you to leap again to String for help and computerized fixes utilizing the AI agent. Alternatively, you possibly can immediately 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({
  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: "Person Query",
      description: "The query from the webhook set off",
      default: "{{ steps.set off.occasion.physique.take a look at }}",
    },
    knowledgeBaseRecords: {
      sort: "any",
      label: "Information 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(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 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 beneath to reply questions. If the knowledge isn't accessible within the information base, please say so.

Information Base:
${knowledgeBaseContent}

Directions:
- Reply primarily based solely on the offered information base content material
- Be correct and concise
- If the reply isn't within the information base, clearly state that the knowledge isn't accessible
- Cite related elements 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({
      $,
      information: {
        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 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, you have to be prepared to check and deploy. Deploy first, after which take a look at by passing a consumer question like this within the newly opened deployment tab:

If the request is dealt with and all the pieces runs appropriately, scroll all the way down to see the response returned by the GPT mannequin accessed within the final stage of the workflow:

Properly accomplished! 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 by way of Pipedream.

# Wrapping Up

 
This text confirmed the 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 era. Pipedream permits defining orchestration workflows programmatically, manually, or aided by its conversational AI agent. By the creator’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 true world.