--- title: "Chat with your company documents from Google Drive" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/189841ef-d27e-420f-a0ac-6e52d4d344cf" updated: "2026-11-12" --- # Chat with your company documents from Google Drive > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that answers questions from your company documents. It watches a Google Drive folder, stores new files in Pinecone with Gemini, and an agent in n8n’s chat answers from the closest pieces. Chat with your company documents from Google Drive is an n8n workflow in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow lets you chat with the documents in a Google Drive folder. One flow watches the folder. When a file is added or changed, it cuts the file into pieces, turns each piece into a vector with Gemini and stores it in a Pinecone index. A second flow takes a question from n8n’s chat. An agent searches the index for the closest pieces, and Gemini writes the answer from them. When the pieces hold no answer, the agent says so. Fifteen nodes run it, and three sticky notes explain the setup. ### Who it suits Teams that keep policies and handbooks in Google Drive and answer the same questions again and again, such as HR or an office manager. Skip it if the documents are too private to send to Google and Pinecone, or if every answer must name its source file. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | HR | HR teams | Answer staff questions from the handbook | An employee asks how many days of leave a new hire gets and reads the answer from the policy file. | | Operations | Office managers | Point newcomers to the house rules | A new hire asks about the expense rules and gets them from the finance policy. | | Support | Support leads | Give agents a quick lookup over the help files | An agent asks for the refund steps and gets them from the process document. | | Education | School administrators | Answer parents’ questions from the school handbook | An administrator asks about uniforms and reads the rule from the handbook file. | You need a little n8n: import a file, add three credentials, make an index in Pinecone and pick a Drive folder. ### Where to use it Any n8n that can reach Google Drive, Google’s Gemini API and Pinecone will run it. The folder watch runs only while the workflow is published, and the chat opens from the Chat button in n8n. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Another model: swap either Gemini chat node for any chat model node ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. You need a Google account with Drive, a Google AI key and a Pinecone account. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | Google Drive | A sign-in and a folder for your documents | | Google AI | An API key from Google AI Studio | | Pinecone | An account, an API key and an index named \`company-files\` with 3072 dimensions and the cosine metric | 1. In Pinecone, create an index named `company-files` with 3072 dimensions and the cosine metric, and copy an API key. 2. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 3. Add a Google Drive, a Google Gemini (PaLM) and a Pinecone credential, and select them in the nodes that ask for them. 4. In both Drive triggers, pick the folder that holds your documents. 5. In both Pinecone nodes, pick the `company-files` index. 6. Publish the workflow, add a document to the folder and give it a minute. 7. Open the chat in n8n and ask a question. ### How to use it Add documents to the folder and ask questions in the chat. The agent remembers the last few turns. A file you change is added again, so its old pieces stay in the index beside the new ones. What to change for a different result | To change | Where | | --- | --- | | The assistant’s role and rules | The system message in \`AI Agent\` | | How the document tool is described | \`Vector Store Tool\` | | The size of a piece | \`Recursive Character Text Splitter\`, 1,000 characters with an overlap of 100 | | The folder | Both Drive triggers | | The models | The two Gemini chat nodes and the two embeddings nodes | ### Example An HR manager adds “Leave policy.pdf” to the folder. At the next check the file goes into the index. An employee types “How many days of paid leave do new hires get?”. The agent calls the document tool, which finds the pieces about leave, and Gemini answers from them in a few sentences. Asked about something the files do not cover, the agent says it found no answer in the documents. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. A vector store keeps text as lists of numbers, called vectors, so a question can find pieces with a similar meaning. An agent is a node that decides when to call a tool. **For experts.** `Pinecone Vector Store` runs in insert mode, and `Default Data Loader` reads the binary field `data`. `Pinecone Vector Store (Retrieval)` feeds `Vector Store Tool`, which has its own chat model, `Google Gemini Chat Model (retrieval)`. `Window Buffer Memory` keeps the last five interactions inside the n8n process. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`Google Drive File Created\` and \`Google Drive File Updated\` | Watch one folder | Check every minute | | \`Download File From Google Drive\` | Downloads the file | A Google Doc arrives as a Word file | | \`Pinecone Vector Store\` | Stores the pieces | Adds them again on each update | | \`Vector Store Tool\` | Searches the index for the agent | Returns the 4 closest pieces | | \`AI Agent\` | Writes the reply | Follows its system message | ### Good to know Two model names needed a swap, and the Pinecone index must match the new vector size. - Vectors: Google’s page, read on 12 November 2026, shut \`text-embedding-004\` down on 14 January 2026 and names \`gemini-embedding-2\`. That model returns one combined vector when a request holds several inputs, which Mindket did not want to rely on without a run. The copy uses \`gemini-embedding-001\`, a text-only model that is also the node’s default - Index size: \`gemini-embedding-001\` returns 3072 values by default, so make the index with 3072 dimensions. An index made for another size will not take the vectors - Chat model: \`gemini-2.0-flash-exp\` is not on Google’s page any more, and the \`gemini-2.0-flash\` family shut down on 1 June 2026. Mindket’s copy uses \`gemini-3.8-flash\`, which Google’s models page lists as stable - Changed files: the old pieces of a changed file stay in the index, because the Pinecone node’s Clear Namespace option is off - File types: the loader reads PDF, Word, text, CSV, JSON and EPub. Google Sheets and Slides arrive as Excel and PowerPoint files, which it cannot read - Memory: the last five turns live in n8n’s memory, and a restart clears them - Not run: Mindket read this copy against n8n’s source and Google’s pages and did not run it on a live n8n - Your data: the text of your files and your questions go to Google and Pinecone, and anyone who can open the chat can read answers drawn from every file in the folder - Credentials: the JSON holds none ## README ```markdown # Chat with your company documents from Google Drive An n8n workflow that answers questions from your company documents. One flow watches a Google Drive folder and stores each new or changed file in a Pinecone index, using Gemini to make the vectors. A second flow takes a question from n8n's chat, and an agent answers from the closest pieces. ## What is inside - `workflow.json`: the workflow as n8n exports it, 18 nodes. Fifteen run, and three are sticky notes. The fifteen are two Drive triggers and a download step, the Pinecone store with its loader, text splitter and embeddings, and the chat trigger. The rest are the agent with its memory and chat model, and the document tool with its own Pinecone search, embeddings and chat model. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - The two `Embeddings Google Gemini` nodes used `models/text-embedding-004`. Google's deprecation page, read on 12 November 2026, shut that model down on 14 January 2026 and names `gemini-embedding-2`. That model returns one combined vector when a request holds several inputs, and Mindket did not want to rely on that without a run. Both nodes now use `models/gemini-embedding-001`, a text-only model that is also this node's own default. It returns 3072 values by default. - The two `Google Gemini Chat Model` nodes used `models/gemini-2.0-flash-exp`. Google's page does not list that name any more, and the `gemini-2.0-flash` family shut down on 1 June 2026. Both nodes now use `models/gemini-3.8-flash`, which Google's models page lists as stable. - The credential links are gone. Both Drive triggers have an empty folder to pick, because the original pointed at the author's own folder. - The three sticky notes are written again, and the set-up note now gives the index size. - The file's name is ours. - Nothing else. The agent's rules, the document tool, the splitter and the loader are as the file had them. Mindket read this copy against n8n's source and Google's pages. It was not run on a live n8n. ## Before you start - An n8n instance, on n8n Cloud or your own server. - A Google account with Drive, and a folder for your documents. - A Google AI Studio API key for the Gemini credential. - A Pinecone account and an API key. ## Set it up 1. In Pinecone, create an index named `company-files` with 3072 dimensions and the cosine metric, and copy an API key. 2. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 3. Add a Google Drive credential, a Google Gemini (PaLM) credential with your AI Studio key and a Pinecone credential. Select them in the nodes that ask for them. 4. In `Google Drive File Created` and `Google Drive File Updated`, pick the folder that holds your documents. 5. In both Pinecone nodes, pick the `company-files` index. 6. Publish the workflow, add a document to the folder and give it a minute. 7. Open the chat in n8n and ask a question. ## What happens in a run Filling the index: 1. `Google Drive File Created` and `Google Drive File Updated` check the folder every minute. Both pass the file on to `Download File From Google Drive`, which downloads it under its own name. 2. `Pinecone Vector Store` stores the file in insert mode. `Default Data Loader` reads the downloaded file, `Recursive Character Text Splitter` cuts it into pieces of about 1,000 characters that overlap by 100, and `Embeddings Google Gemini` turns each piece into a vector. Answering a question: 3. `When chat message received` passes your question to `AI Agent`, which has `Window Buffer Memory` and `Google Gemini Chat Model`. 4. The agent's system message makes it a helpful HR assistant for questions about company policies. It must use the `company_documents_tool` for anything that comes from the documents. When the documents hold no answer, it must say so in a fixed line. 5. `Vector Store Tool` searches through `Pinecone Vector Store (Retrieval)` and `Embeddings Google Gemini (retrieval)`, returns the closest pieces and has `Google Gemini Chat Model (retrieval)` write the answer from them. ## What to change - The assistant's role and rules: the system message in `AI Agent`. - How the document tool is described to the agent: `Vector Store Tool`. - The size of a piece: `Recursive Character Text Splitter`. - The folder: both Drive triggers. - The models: the two Gemini chat nodes and the two embeddings nodes. If you change an embeddings model, make a new index of its size and fill it again. ## Good to know - An index made for another vector size than the one in step 1 will not take the vectors. - A changed file is added again. The Pinecone node's Clear Namespace option is off, so the old pieces of that file stay beside the new ones. - The loader reads PDF, Word, text, CSV, JSON and EPub. A Google Doc is downloaded as a Word file. Google Sheets and Slides arrive as Excel and PowerPoint files, which the loader cannot read. - The triggers react to files created or changed after you publish the workflow, so add your documents then. - The chat memory holds the last five interactions inside the n8n process, and a restart clears it. - Both embeddings nodes must use the same model, or the search finds nothing useful. They do in this copy. - Data: the text of your files and your questions go to Google and Pinecone. Anyone who can open the chat can read answers drawn from every file in the folder. - Cost: Google bills the Gemini calls and Pinecone bills the index, each under your plan. ``` ## What is in it 3 files, 17 KB, downloaded as a zip. ```text NOTICE.md 671 B README.md 5 KB workflow.json 11 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 6 steps, starting on a Google Drive event or on a chat message - AI: 2 steps call an AI model: Pinecone Vector Store and AI Agent - Sign-ins: Signs in to: Google Drive, Pinecone, Google Gemini and Google service account - API keys: No API key is left in the file - Step types: Mindket’s checker reads all 5 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/189841ef-d27e-420f-a0ac-6e52d4d344cf) - [Its page on Mindket](https://mindket.com/p/189841ef-d27e-420f-a0ac-6e52d4d344cf)