{"workflow":{"id":11870,"name":"Chat with Google Drive documents using OpenAI and Pinecone RAG search","views":224,"recentViews":0,"totalViews":224,"createdAt":"2025-12-16T17:43:56.592Z","description":"## Try it out\n\nThis n8n workflow template lets you chat with your Google Drive documents (.docx, .json, .md, .txt, .pdf) using OpenAI and Pinecone vector database. It retrieves relevant context from your files in real time so you can get accurate, context-aware answers about your proprietary data—without the need to train your own LLM.\n#### Not interested in chunking and embedding your own data or figuring out which search method to use?\n\nTry our n8n quickstart for Pinecone Assistant [here](https://docs.pinecone.io/guides/assistant/quickstart/n8n-quickstart) or check out the full workflow to chat with your Google Drive documents [here](https://n8n.io/workflows/9942-rag-powered-document-chat-with-google-drive-openai-and-pinecone-assistant/).\n\n### Prerequisites\n\n* A [Pinecone account](https://app.pinecone.io/)\n* A GCP project with [Google Drive API enabled and configured](https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/)\n* An [Open AI account](https://auth.openai.com/create-account) and [API key](https://platform.openai.com/settings/organization/api-keys)\n* A [Cohere account](https://dashboard.cohere.com/welcome/register) and [API key](https://dashboard.cohere.com/api-keys)\n\n### Setup\n\n1. Create a Pinecone index in the Pinecone Console [here](https://app.pinecone.io/organizations/-/projects/-/indexes) \n\t1. Name your index `n8n-dense-index`\n\t2. Select OpenAI's `text-embedding-3-small`\n\t3. Set the Dimension to `1536`\n\t4. Leave everything else as default\n\t5. If you use a different index name, update the related nodes to reflect this change\n2. Use the Connect to Pinecone button to authenticate to Pinecone or if you self-host n8n, create a Pinecone credential and add your [Pinecone API key](https://app.pinecone.io/organizations/-/projects/-/keys) directly\n3. Setup your Google Drive OAuth2 API, Open AI, and Cohere credentials in n8n\n4. Download these files and add them to a Drive folder named `n8n-pinecone-demo` in the root of your My Drive\n\t1. [https://docs.pinecone.io/release-notes/2022.md](https://docs.pinecone.io/release-notes/2022.md)\n\t2. [https://docs.pinecone.io/release-notes/2023.md](https://docs.pinecone.io/release-notes/2023.md)\n\t3. [https://docs.pinecone.io/release-notes/2024.md](https://docs.pinecone.io/release-notes/2024.md)\n\t4. [https://docs.pinecone.io/release-notes/2025.md](https://docs.pinecone.io/release-notes/2025.md)\n\t5. [https://docs.pinecone.io/release-notes/2026.md](https://docs.pinecone.io/release-notes/2026.md)\n5. Activate the workflow or test it with a manual execution to ingest the documents\n6. Enter the chat prompts to chat with the Pinecone release notes\n\t1. `What support does Pinecone have for MCP?`\n\t2. `When was fetch by metadata released?`\n\n### Ideas for customizing this workflow\n\n- Use your own data and adjust the chunking strategy\n- Update the AI Agent System Message to reflect how the Pinecone Vector Store Tool will be used. Be sure to include info on what data can be retrieved using that tool.\n- Update the Pinecone Vector Store Tool Description to reflect what data you are storing in the Pinecone index\n### Need help?\n\nYou can find help by asking in the [Pinecone Discord community](https://discord.gg/tJ8V62S3sH) or [filing an issue](https://github.com/pinecone-io/n8n-templates/issues/new/choose) on this repo.","workflow":{"meta":{"instanceId":"6ae6d27e57788e6797af2bf16734f2cac83ad4b8f8ebbf57445f55ef5d3a52da","templateCredsSetupCompleted":true},"nodes":[{"id":"e73ef010-c51c-4bb1-87cb-92cd65a6a73a","name":"Pinecone Vector Store","type":"@n8n/n8n-nodes-langchain.vectorStorePinecone","position":[-16,16],"parameters":{"mode":"insert","options":{"pineconeNamespace":"release-notes-namespace"},"pineconeIndex":{"__rl":true,"mode":"list","value":"n8n-dense-index","cachedResultName":"n8n-dense-index"}},"credentials":{"pineconeApi":{"id":"pBm0ARHJdLXfTUXe","name":"Pinecone"}},"typeVersion":1.3},{"id":"98c2d7b7-88ff-49d6-9095-a386846f690b","name":"Embeddings OpenAI","type":"@n8n/n8n-nodes-langchain.embeddingsOpenAi","position":[-80,592],"parameters":{"options":{"dimensions":1536}},"credentials":{"openAiApi":{"id":"wRaEYGibKa7GoCaK","name":"OpenAi account"}},"typeVersion":1.2},{"id":"5c37d980-4726-4f35-8845-71e8d4750121","name":"When chat message received","type":"@n8n/n8n-nodes-langchain.chatTrigger","position":[-464,864],"webhookId":"016c2966-4f58-4598-9bce-d48c8f6b4bc8","parameters":{"options":{}},"typeVersion":1.3},{"id":"b51a237f-2467-4f72-8d14-04b2443c5270","name":"AI Agent","type":"@n8n/n8n-nodes-langchain.agent","position":[-176,864],"parameters":{"options":{"systemMessage":"You are a helpful assistant. Only use the Pinecone Vector Store Tool to retrieve data about Pinecone releases. Include the file name and file url in citations wherever referenced in output."}},"typeVersion":2.2},{"id":"f1299e20-a590-46f3-a742-24bd93fbd78e","name":"OpenAI Chat Model","type":"@n8n/n8n-nodes-langchain.lmChatOpenAi","position":[-272,1136],"parameters":{"model":{"__rl":true,"mode":"list","value":"gpt-4.1-mini"},"options":{}},"credentials":{"openAiApi":{"id":"wRaEYGibKa7GoCaK","name":"OpenAi account"}},"typeVersion":1.2},{"id":"c06a2096-c5cc-4a0d-a9f8-fcef5c237c81","name":"Pinecone Vector Store Tool","type":"@n8n/n8n-nodes-langchain.vectorStorePinecone","position":[112,1008],"parameters":{"mode":"retrieve-as-tool","topK":20,"options":{"pineconeNamespace":"release-notes-namespace"},"useReranker":true,"pineconeIndex":{"__rl":true,"mode":"list","value":"n8n-dense-index","cachedResultName":"n8n-dense-index"},"toolDescription":"Contains data about Pinecone releases."},"credentials":{"pineconeApi":{"id":"pBm0ARHJdLXfTUXe","name":"Pinecone"}},"typeVersion":1.3},{"id":"a62e23b3-eae6-48e6-9b9e-4b5853234a62","name":"Sticky Note7","type":"n8n-nodes-base.stickyNote","position":[-1248,-80],"parameters":{"width":604,"height":1488,"content":"![Pinecone logo](https://www.pinecone.io/images/pinecone-logo-for-n8n-templates.png)\n\n\n## Try it out\n\nThis n8n workflow template lets you chat with your Google Drive documents (.docx, .json, .md, .txt, .pdf) using OpenAI and Pinecone vector database. It retrieves relevant context from your files in real time so you can get accurate, context-aware answers about your proprietary data—without the need to train your own LLM.\n#### Not interested in chunking and embedding your own data or figuring out which search method to use?\n\nTry our n8n quickstart for Pinecone Assistant [here](https://docs.pinecone.io/guides/assistant/quickstart/n8n-quickstart) or check out the full workflow to chat with your Google Drive documents [here](https://n8n.io/workflows/9942-rag-powered-document-chat-with-google-drive-openai-and-pinecone-assistant/).\n\n### Prerequisites\n\n* A [Pinecone account](https://app.pinecone.io/)\n* A GCP project with [Google Drive API enabled and configured](https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/)\n* An [Open AI account](https://auth.openai.com/create-account) and [API key](https://platform.openai.com/settings/organization/api-keys)\n* A [Cohere account](https://dashboard.cohere.com/welcome/register) and [API key](https://dashboard.cohere.com/api-keys)\n\n### Setup\n\n1. Create a Pinecone index in the Pinecone Console [here](https://app.pinecone.io/organizations/-/projects/-/indexes) \n\t1. Name your index `n8n-dense-index`\n\t2. Select OpenAI's `text-embedding-3-small`\n\t3. Set the Dimension to `1536`\n\t4. Leave everything else as default\n\t5. If you use a different index name, update the related nodes to reflect this change\n2. Use the Connect to Pinecone button to authenticate to Pinecone or if you self-host n8n, create a Pinecone credential and add your [Pinecone API key](https://app.pinecone.io/organizations/-/projects/-/keys) directly\n3. Setup your Google Drive OAuth2 API, Open AI, and Cohere credentials in n8n\n4. Download these files and add them to a Drive folder named `n8n-pinecone-demo` in the root of your My Drive\n\t1. https://docs.pinecone.io/release-notes/2022.md\n\t2. https://docs.pinecone.io/release-notes/2023.md\n\t3. https://docs.pinecone.io/release-notes/2024.md\n\t4. https://docs.pinecone.io/release-notes/2025.md\n\t5. https://docs.pinecone.io/release-notes/2026.md\n5. Activate the workflow or test it with a manual execution to ingest the documents\n6. Enter the chat prompts to chat with the Pinecone release notes\n\t1. `What support does Pinecone have for MCP?`\n\t2. `When was fetch by metadata released?`\n\n### Ideas for customizing this workflow\n\n- Use your own data and adjust the chunking strategy\n- Update the AI Agent System Message to reflect how the Pinecone Vector Store Tool will be used. Be sure to include info on what data can be retrieved using that tool.\n- Update the Pinecone Vector Store Tool Description to reflect what data you are storing in the Pinecone index\n### Need help?\n\nYou can find help by asking in the [Pinecone Discord community](https://discord.gg/tJ8V62S3sH) or [filing an issue](https://github.com/pinecone-io/n8n-templates/issues/new/choose) on this repo."},"typeVersion":1},{"id":"f738618b-ce9f-41ab-a6f5-2f7fed2a1d9f","name":"Default Data Loader","type":"@n8n/n8n-nodes-langchain.documentDefaultDataLoader","position":[128,192],"parameters":{"options":{"metadata":{"metadataValues":[{"name":"external_file_id","value":"={{ $json.id }}"}]}},"dataType":"binary","binaryMode":"specificField","textSplittingMode":"custom"},"typeVersion":1.1},{"id":"0af1ef79-079b-4c93-a7d6-ea65c153de52","name":"Cohere Reranker","type":"@n8n/n8n-nodes-langchain.rerankerCohere","position":[208,1248],"parameters":{"topN":5},"credentials":{"cohereApi":{"id":"93irEWSds2FNTyXk","name":"Cohere"}},"typeVersion":1},{"id":"3058cf8c-385d-4f9b-bdb4-12243bb1c52f","name":"Sticky Note","type":"n8n-nodes-base.stickyNote","position":[-608,-80],"parameters":{"color":7,"width":1184,"height":608,"content":"## 1. Download, chunk, embed, and upsert Pinecone release notes to Pinecone index"},"typeVersion":1},{"id":"c844c7ca-fc77-44d7-9fc7-3ae5dd5b11b1","name":"Sticky Note1","type":"n8n-nodes-base.stickyNote","position":[-608,736],"parameters":{"color":7,"width":1184,"height":672,"content":"## 2. Chat with the Pinecone release notes"},"typeVersion":1},{"id":"766a7768-8bf7-458b-b43c-29fe238fc8df","name":"Character Text Splitter - markdown","type":"@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter","position":[224,352],"parameters":{"chunkSize":2000,"separator":"\n ### Upgrade from Starter to Standard trial\n\n Organizations on the Starter plan can now upgrade to a Standard plan trial at any time. The Standard trial provides 21 days and \\$300 in credits to test Pinecone at scale, with access to Standard plan features such as higher limits. For more information, see [Standard plan trial](/guides/organizations/manage-billing/standard-trial).\n\n```\n\nEach release is contained in an `Update` tag and each feature indicated by `###`. We expect our queries to be as granular as features in a release, so we try to chunk by release without breaking up features. We want chunks to be big enough to contain meaningful information but not so big that the meaning is diluted or it can't fit within the context window of the embedding model. Here, we use the Character Text Splitter and split on `