Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone

This content originally appeared on DEV Community and was authored by Tej Hagargi

Recently, I was working on a Retrieval-Augmented Generation (RAG) chatbot where users can upload PDFs or where I can scrape structured website data. The goal was to convert this data into embeddings, store it in a vector database, and then use it to answer user queries.

Step 1: Extract Raw Text

From pdf

import { PdfReader } from 'pdfreader';

let text = '';
const pdfReader = new PdfReader();

await new Promise<void>((resolve, reject) => {
  pdfReader.parseBuffer(buffer, (err: any, item: any) => {
    if (err) reject(err);
    else if (!item) resolve();
    else if (item.text) text += item.text + ' ';
  });
});

From scraped website data:

function extractTextFromScrapedData(data: ScrapedData): string {
  const sections: string[] = [];

  if (data.about) sections.push(`About: ${data.about}`);
  if (data.services) sections.push(`Services: ${data.services.join('\n• ')}`);
  if (data.contact?.phone) sections.push(`Phone: ${data.contact.phone}`);

  return sections.join('\n\n');
}

Step 2: Split Text into Chunks

Long documents need to be split so the LLM can handle them. I used LangChain’s RecursiveCharacterTextSplitter:

import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
import { Document } from "@langchain/core/documents";

const doc = new Document({ pageContent: text });
const splitter = new RecursiveCharacterTextSplitter({
  chunkSize: 1000,
  chunkOverlap: 200
});

const allSplits = await splitter.splitDocuments([doc]);
console.log("Chunks created:", allSplits.length);

Step 3: Generate Embeddings + Store

This is the most important part:
When you call vectorStore.addDocuments(), LangChain automatically calls your embedding model (e.g. OpenAI, Cohere) and saves those vectors into your configured database (Pinecone in my case).

import { vectorStore } from "@/app/lib/langchain";

// Store with namespace (client-specific)
await vectorStore.addDocuments(allSplits, { namespace: clientId });
console.log("✅ Documents added to vectorStore");

Step 4: Retrieve Context During Chat

When a user asks a question, we retrieve the top-k similar chunks:

const retrieved = await vectorStore.similaritySearchWithScore(
  userMessage,
  3,
  { namespace: clientId }
);

const relevantMatches = retrieved.filter(([doc, score]) => score > 0.6);
console.log("Relevant matches:", relevantMatches.length);

The other chunking methods are :

Agentic Chunking → LLM-guided, semantic-aware chunking based on meaning and context.
CharacterTextSplitter → Splits by character count (simple, fast).
RecursiveCharacterTextSplitter → Splits by hierarchy (paragraph → sentence → word → char). Most commonly used.
TokenTextSplitter → Splits by tokens, aligns with model tokenization.
MarkdownTextSplitter → Splits Markdown docs by headers/sections.
HTMLTextSplitter → Splits HTML while respecting tags.
CodeTextSplitter → Splits source code by functions, classes, logical blocks.

Refer to this doc for more clarifying
DOC

Happy Coding, Keep Striving.

This content originally appeared on DEV Community and was authored by Tej Hagargi

Print Share Comment Cite Upload Translate Updates

APA

Tej Hagargi | Sciencx (2025-09-25T10:50:48+00:00) Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone. Retrieved from https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/

MLA

" » Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone." Tej Hagargi | Sciencx - Thursday September 25, 2025, https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/

HARVARD

Tej Hagargi | Sciencx Thursday September 25, 2025 » Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone., viewed ,<https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/>

VANCOUVER

Tej Hagargi | Sciencx - » Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/

CHICAGO

" » Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone." Tej Hagargi | Sciencx - Accessed . https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/

IEEE

" » Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone." Tej Hagargi | Sciencx [Online]. Available: https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/. [Accessed: ]

rf:citation

» Implementing a Retrieval-Augmented Generation (RAG) Chatbot with LangChain, Firebase, and Pinecone | Tej Hagargi | Sciencx | https://www.scien.cx/2025/09/25/implementing-a-retrieval-augmented-generation-rag-chatbot-with-langchain-firebase-and-pinecone-2/ |

Please log in to upload a file.

There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.

The other chunking methods are :

Related Posts