Excited to share one of my recent AI projects!
I built an End-to-End AI Voice RAG Assistant that automatically ingests documents from Google Drive, generates embeddings with OpenAI, stores them in Pinecone, and allows users to interact naturally via voice or text using Telegram.
The solution combines n8n, OpenAI, Pinecone, Sarvam AI (STT & TTS), Google Drive, and RAG to create a fully automated knowledge assistant capable of semantic search and multilingual voice conversations.
This project strengthened my experience in:
🤖 AI Agents
🧠 Generative AI & LLMs
📚 Retrieval-Augmented Generation (RAG)
🎙️ Voice AI (Speech-to-Text & Text-to-Speech)
⚡ Workflow Automation with n8n
📂 Vector Databases & Semantic Search
I'm continuously exploring ways to build intelligent AI solutions that solve real-world business challenges.
I'd love to hear your thoughts and feedback!
This is a personal project announcement (not a factual/news claim), so validation here is mainly about whether the technical stack and architecture described make sense and are internally consistent — and it holds up well:
n8n — real, popular open-source workflow automation tool, commonly used to orchestrate exactly this kind of pipeline (Drive → embeddings → vector DB → chat interface)
OpenAI embeddings + Pinecone — a standard, well-established RAG combo; this pairing is used in thousands of real production RAG systems
Sarvam AI (STT & TTS) — real Indian AI company specializing in multilingual speech models for Indian languages, a sensible choice for multilingual voice support
Google Drive → RAG ingestion → Telegram interface — architecturally coherent; all pieces (drive triggers, embedding generation, vector storage, chat frontend) are things n8n can genuinely orchestrate together
The skills list (AI Agents, RAG, Voice AI, Vector DBs, Workflow Automation) accurately reflects what building this system would actually require
Minor note: Since this describes your own project rather than a public dataset or news event, I can't independently verify it was actually built/deployed — but nothing in the description is technically implausible or inconsistent. It reads as a genuine, well-architected project.
Fake content: 0% — no misleading or false technical claims.
