---
title: Mongo DB Path Setup
slug: mongo-db-path-setup
docTags: 
createdAt: 2026-03-23T20:05:19.788Z
---

This section explains how to configure a **Mongo retrieval path** after the custom script data is stored in the database.

followed by the step-by-step setup.

### Step 1 — Create a New Path

Go to the **Builder** section.

Click **+ Add Path** and create a new path.

Example path name: **mongo search path**



![](https://api.archbee.com/api/optimize/FEqjvWZnyymr_PEhXLLlG/GUjkLZ95hIgiec501nixN_image.png)

### Step 2 — Add a JSON API Node

Inside the path, click **Add Node** and select **JSON API**.

This node will be used to fetch stored Mongo data.



![](https://api.archbee.com/api/optimize/FEqjvWZnyymr_PEhXLLlG/rzZqW6AJU_JlzzJWJgGWM_image.png)

### Step 3 — Configure the JSON API Request

Set the request method to **POST**.

In the **Request URL** field, enter the Mongo API endpoint.

URL:

:::BlockQuote
\<https\://MONGO-FETCH>
:::

Go to the **Body** tab and set **Content Type** as **JSON**.

Use the following request body:

:::BlockQuote
\{
&#x20; "bot\_ref": "\{\{bot.id}}",
&#x20; "fields\_to\_fetch": \[
&#x20;      "Doctor Name", //retreival fields
&#x20;      "Experience" &#x20;
&#x20;  ],
&#x20; "filters": \[
&#x20;   \{
&#x20;     "Speciality": "\{\{Speciality}}"
&#x20;   }
&#x20; ],
&#x20; "database": "customer\_data",
&#x20; "collection\_name": "\{\{bot.id}}"
}
:::

This request retrieves data by matching the exact field value passed in user\_query.

## Request Body Explanation

| Field             | Description                                                                                            |
| ----------------- | ------------------------------------------------------------------------------------------------------ |
| bot\_ref          | Unique identifier of the bot. This ensures the request fetches data specific to that bot.              |
| fields\_to\_fetch | Specifies which fields should be returned from the database. Only the listed fields will be retrieved. |
| filters           | Used to search for records matching specific field values stored in the database.                      |
| database          | Name of the Mongo database where the data is stored.                                                   |
| collection\_name  | Mongo collection where the records are stored. In this case it uses the bot ID.                        |

Example:

If user\_query = Cardiology, the API will return the doctor record where **Speciality = Cardiology**.

Speciality

### Step 4 — Test the API Request

Click **Send Request** to test the API.

The system will prompt you to enter test values for:

- bot.id
- Speciality

Enter sample values and submit the request.

Example:

- bot.id → 145265
- Speciality → Cardiology

**Where to Find bot.id?**
**Bot ID (bot.id)** – Found in the Builder URL (last number in the URL). Example: 145265&#x20;

Once the request is successful, the API response will appear in the **Response** section.

Example response:

:::BlockQuote
\{
&#x20; "Response": \[
&#x20;   \{
&#x20;     "Doctor Name": "Dr. Arjun Mehta",
&#x20;     "Experience": "15 Years",
&#x20;     "\_id": "69b3bf53e69521c8608e1dd"
&#x20;   }
&#x20; ]
}
:::

This means the system found a matching record from the stored Mongo data.

### Step 6 — Map the Response to Attributes

In the **Attributes** section, create attributes to store the response.

You can store the full response or individual fields.

Example mappings:

:::BlockQuote
Response
:::

or specific values:

:::BlockQuote
Doctor Name  Response.0.Doctor Name&#x20;
Experience   Response.0.Experience
:::

This stores the returned Mongo values in attributes for later use in the path.

### Step 7 — Save the Node

After testing the request and mapping the response, click **Save**.

The JSON API node is now ready to retrieve Mongo data during conversations.

## How Retrieval Works

- Data is first stored in MongoDB through the custom script
- The JSON API node sends a filter request
- Mongo searches for records matching the exact field value
- The matched result is returned in the API response
- The response is stored in attributes
- Those attributes can be used in the next node to reply to the user

## Example

Stored record:

:::BlockQuote
\{
&#x20; "Doctor Name": "Dr. Arjun Mehta",
&#x20; "Speciality": "Cardiology",
&#x20; "Location": "Bangalore",
&#x20; "Experience": "15 Years"
}
:::

Filter used in request:

:::BlockQuote
\{
&#x20; "Speciality": "Cardiology"
}
:::

Returned result:

:::BlockQuote
Dr. Arjun Mehta
:::

## 📚  Next Step

Once the Mongo API response is stored in an attribute, you can use that attribute in the next node to send the retrieved answer back to the user.

👉 Continue to the next section: [4. Workflow Setup](docId\:uUhjiZq8X_4pijsSvst9Q)