{"product_id":"hr-policy-q-a-bot-telegram-groq-gemini-drive-rag","title":"HR Policy Q\u0026A Bot: Telegram + Groq + Gemini + Drive (RAG)","description":"\u003ch3\u003eAsk your HR questions—automatically—directly in Telegram (with RAG over your HR policy)\u003c\/h3\u003e\n\u003cp\u003eThis \u003cstrong\u003en8n automation workflow\u003c\/strong\u003e indexes your \u003cstrong\u003eHR policy PDF from Google Drive\u003c\/strong\u003e and answers employee questions in \u003cstrong\u003eTelegram\u003c\/strong\u003e using a \u003cstrong\u003eGroq\u003c\/strong\u003e chat model with \u003cstrong\u003eretrieval-augmented generation (RAG)\u003c\/strong\u003e. No manual searching—just grounded answers pulled from your policy text.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eLoads your HR policy PDF\u003c\/strong\u003e: Manually downloads the HR policy document from \u003cstrong\u003eGoogle Drive\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eBuilds a searchable knowledge base\u003c\/strong\u003e: Splits the PDF content, generates \u003cstrong\u003eGoogle Gemini embeddings\u003c\/strong\u003e, and inserts chunks into an \u003cstrong\u003ein-memory vector store\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eListens in Telegram\u003c\/strong\u003e: Triggers whenever a new message is received by your \u003cstrong\u003eTelegram bot\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRetrieves relevant policy passages\u003c\/strong\u003e: Uses the vector store to find relevant excerpts for the user’s question.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGenerates a grounded response\u003c\/strong\u003e: Calls a \u003cstrong\u003eGroq chat model\u003c\/strong\u003e with per-chat conversation memory, then sends the answer back to the originating Telegram chat.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eEmployees ask HR questions like leave policy, reimbursements, or code-of-conduct rules, and receive answers sourced from the policy.\u003c\/li\u003e\n  \u003cli\u003eSaaS operators reduce HR workload by handling repetitive “policy lookup” questions via Telegram.\u003c\/li\u003e\n  \u003cli\u003eAutomation engineers create a maintainable HR Q\u0026amp;A assistant that re-indexes when the PDF changes.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eTelegram\u003c\/strong\u003e: Telegram bot token (via @BotFather) + Telegram trigger for incoming messages.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGoogle Drive\u003c\/strong\u003e: OAuth credentials to download the HR policy PDF.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGoogle Gemini\u003c\/strong\u003e: API key used for embeddings during indexing.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGroq\u003c\/strong\u003e: API key powering the chat model for RAG responses.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003en8n \/ LangChain Agent\u003c\/strong\u003e: Uses an “\u003cstrong\u003eHR Policy Agent\u003c\/strong\u003e” node to retrieve passages and generate answers; you can edit its system message to adjust tone, language, or word limit.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eImportant note\u003c\/strong\u003e: Run the manual “\u003cstrong\u003eLoad knowledge base\u003c\/strong\u003e” trigger once to index, and re-run it when the document changes or after n8n restarts (the in-memory store resets).\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":46228904378547,"sku":"N8N-20873","price":44.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/jMAdpq6af0GouZ4Z2X-yc_1nUGxSYb.png?v=1792056362","url":"https:\/\/buyflowscripts.com\/products\/hr-policy-q-a-bot-telegram-groq-gemini-drive-rag","provider":"N8N Commerce","version":"1.0","type":"link"}