What it does
Two n8n workflows. The first imports product documentation from Google Docs, splits it into chunks, creates embeddings with OpenAI and stores them in a MongoDB Atlas vector store. The second answers WhatsApp messages (text, voice, images or documents) by retrieving relevant chunks.
Use cases
- 01Answer a product question sent as a text message
- 02Transcribe a voice note and reply from the docs
- 03Read a screenshot or PDF and give context
Connects
HTTP Request · Google Docs · WhatsApp Business Cloud · Code · AI Agent · Embeddings OpenAI · OpenAI Chat Model · Simple Memory · Recursive Character Text Splitter · Default Data Loader · OpenAI · MongoDB Atlas Vector Store