Rag pinecone vector store Recursive Character Text Splitter not returning output

I ma using 14 day trail n8n and try to build rag using google drive trigger and p
Pinecone Vector Store , it is connected with OenAI Embedding Node with Model text Embedding 3 small  and default Data loader then in turn with REcursive Character Text Splitter all , when executing workflow workflow executed smoothly but Recursive text splitter not returning out put, and embedding also. jsone is uploaded , pleas guide 

## What is the error message (if any)? No error code run smoothly

## Please share your workflow  shared beloe

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.){
{

“name”: “RAGtry”,

“nodes”: [

{

  "parameters": {

    "pollTimes": {

      "item": \[

        {

          "mode": "everyMinute"

        }

      \]

    },

    "triggerOn": "specificFolder",

    "folderToWatch": {

      "\__rl": true,

      "value": "1M0BWgtxVbbLNdWea6bh-Mb2cL9TAexl\_",

      "mode": "list",

      "cachedResultName": "gdrivragn8n",

      "cachedResultUrl": "https://drive.google.com/drive/folders/1M0BWgtxVbbLNdWea6bh-Mb2cL9TAexl\_"

    },

    "event": "fileCreated",

    "options": {}

  },

  "type": "n8n-nodes-base.googleDriveTrigger",

  "typeVersion": 1,

  "position": \[

    -624,

    -128

  \],

  "id": "27a29031-4dac-4208-955f-5a6763d63d56",

  "name": "file created",

  "credentials": {

    "googleDriveOAuth2Api": {

      "id": "nblAFBF7cgVS8xBY",

      "name": "Google Drive account"

    }

  }

},

{

  "parameters": {

    "pollTimes": {

      "item": \[

        {

          "mode": "everyMinute"

        }

      \]

    },

    "triggerOn": "specificFolder",

    "folderToWatch": {

      "\__rl": true,

      "value": "1M0BWgtxVbbLNdWea6bh-Mb2cL9TAexl\_",

      "mode": "list",

      "cachedResultName": "gdrivragn8n",

      "cachedResultUrl": "https://drive.google.com/drive/folders/1M0BWgtxVbbLNdWea6bh-Mb2cL9TAexl\_"

    },

    "event": "fileUpdated",

    "options": {}

  },

  "type": "n8n-nodes-base.googleDriveTrigger",

  "typeVersion": 1,

  "position": \[

    -608,

    16

  \],

  "id": "9f8d1730-3e5b-417a-85ee-a4a20a985077",

  "name": "file updated",

  "credentials": {

    "googleDriveOAuth2Api": {

      "id": "nblAFBF7cgVS8xBY",

      "name": "Google Drive account"

    }

  }

},

{

  "parameters": {

    "operation": "download",

    "fileId": {

      "\__rl": true,

      "value": "1ZmJKD9qmd0HFtZWM6yeOs4jD1VUtTYh2",

      "mode": "list",

      "cachedResultName": "INS-CIR-202-2023 Roshan Ghar.pdf",

      "cachedResultUrl": "https://drive.google.com/file/d/1ZmJKD9qmd0HFtZWM6yeOs4jD1VUtTYh2/view?usp=drivesdk"

    },

    "options": {}

  },

  "type": "n8n-nodes-base.googleDrive",

  "typeVersion": 3,

  "position": \[

    -368,

    -64

  \],

  "id": "2d353411-4d5d-4adb-9031-5d5d57cfd182",

  "name": "Download file",

  "credentials": {

    "googleDriveOAuth2Api": {

      "id": "nblAFBF7cgVS8xBY",

      "name": "Google Drive account"

    }

  }

},

{

  "parameters": {

    "mode": "insert",

    "pineconeIndex": {

      "\__rl": true,

      "value": "pineragn8n",

      "mode": "list",

      "cachedResultName": "pineragn8n"

    },

    "embeddingBatchSize": 50,

    "options": {}

  },

  "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",

  "typeVersion": 1.3,

  "position": \[

    -112,

    -128

  \],

  "id": "2df7dcf2-3199-4dfe-aaa7-0382c51fb972",

  "name": "Pinecone Vector Store",

  "credentials": {

    "pineconeApi": {

      "id": "16i7Qpz2A4mFKHyJ",

      "name": "Pinecone account"

    }

  }

},

{

  "parameters": {

    "options": {

      "dimensions": 1536,

      "batchSize": 50

    }

  },

  "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",

  "typeVersion": 1.2,

  "position": \[

    -288,

    112

  \],

  "id": "c72d7486-9eae-4098-ac8a-912a67718770",

  "name": "Embeddings OpenAI",

  "credentials": {

    "openAiApi": {

      "id": "TYquTcltzWfp5Ok3",

      "name": "paidopenapikey"

    }

  }

},

{

  "parameters": {

    "dataType": "binary",

    "textSplittingMode": "custom",

    "options": {

      "metadata": {

        "metadataValues": \[

          {

            "name": "filename",

            "value": "={{ $('Download file').item.json.name }}"

          }

        \]

      }

    }

  },

  "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",

  "typeVersion": 1.1,

  "position": \[

    64,

    0

  \],

  "id": "22159453-fbec-4177-8f4b-4695f0d4e5a3",

  "name": "Default Data Loader",

  "alwaysOutputData": true

},

{

  "parameters": {

    "chunkSize": 500,

    "chunkOverlap": 50,

    "options": {}

  },

  "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",

  "typeVersion": 1,

  "position": \[

    -64,

    112

  \],

  "id": "4be330dd-db9f-45e2-bbf5-9a2eae900e1c",

  "name": "Recursive Character Text Splitter"

}

],

“pinData”: {},

“connections”: {

"file created": {

  "main": \[

    \[

      {

        "node": "Download file",

        "type": "main",

        "index": 0

      }

    \]

  \]

},

"file updated": {

  "main": \[

    \[

      {

        "node": "Download file",

        "type": "main",

        "index": 0

      }

    \]

  \]

},

"Download file": {

  "main": \[

    \[

      {

        "node": "Pinecone Vector Store",

        "type": "main",

        "index": 0

      }

    \]

  \]

},

"Embeddings OpenAI": {

  "ai_embedding": \[

    \[

      {

        "node": "Pinecone Vector Store",

        "type": "ai_embedding",

        "index": 0

      }

    \]

  \]

},

"Default Data Loader": {

  "ai_document": \[

    \[

      {

        "node": "Pinecone Vector Store",

        "type": "ai_document",

        "index": 0

      }

    \]

  \]

},

"Recursive Character Text Splitter": {

  "ai_textSplitter": \[

    \[

      {

        "node": "Default Data Loader",

        "type": "ai_textSplitter",

        "index": 0

      }

    \]

  \]

}

},

“active”: false,

“settings”: {

"executionOrder": "v1",

"binaryMode": "separate"

},

“versionId”: “36c72e83-e44b-4da3-a783-2241c34395a4”,

“meta”: {

"templateCredsSetupCompleted": true,

"instanceId": "568d41a4614a8599d7d1a2f4e3b0342bbe612b20a7e08ef74b5213c08d404de4"

},

“id”: “UCej8PnySomyBnAG”,

“tags”: [

{

  "updatedAt": "2026-04-17T17:07:25.816Z",

  "createdAt": "2026-04-17T17:07:25.816Z",

  "id": "IlsRlIPkBq3Jg5l2",

  "name": "RAG"

}

]

}


## Share the output returned by the last node

<!-- If you need help with data transformations, please also share your expected output. -->

## Information on your n8n setup

* **n8n version:**
* **Database (default: SQLite):**
* **n8n EXECUTIONS_PROCESS setting (default: own, main):**
* **Running n8n via (Docker, npm, n8n cloud, desktop app):**
* **Operating system:**
1 Like

Hi @Moqeem_Ahmad1
The recommended approach for the insertion of documents in pinecone is below:

And so you instead of using text splitting CUSTOM use it simple, and there if you want you can also choose “Load Specific Data” instead of all incoming data for more accurate and meaningful retrieval, give this a shot and let me know how this goes.

1 Like

quick follow-up on anshul’s suggestion — when using custom text splitting with the recursive splitter, make sure it’s connected to the Default Data Loader with the ai_textSplitter edge (not the main output). if the output is blank in the logs but workflow executes fine, the issue is usually that the data flow between nodes isn’t set up correctly. try anshul’s simpler setup first and let us know if it works, then we can debug the custom config.