> ## Documentation Index
> Fetch the complete documentation index at: https://developers.remeinium.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# /nearest_neighbors

> Find semantically similar words for a given Sinhala word.

<Tabs>
  <Tab title="Python">
    **Python example:**

    ```python theme={null}
    from gradio_client import Client

    client = Client("Remeinium/Embedding_Siyabasa")
    result = client.predict(
        word="පෞරාණික",
        top_k=5,
        api_name="/nearest_neighbors"
    )
    print(json.dumps(result, indent=4))
    ```

    **Response format:**

    ```json theme={null}
    {
        "query": "පෞරාණික",
        "neighbors": [
            {"word": "ඉපැරණි", "similarity": 0.755...},
            {"word": "පුරාවිද්යාත්මක", "similarity": 0.749...},
            ...
        ],
        "model": "UgannA_SiyabasaV2"
    }
    ```
  </Tab>

  <Tab title="Javascript">
    ```javascript theme={null}
    import { Client } from "@gradio/client";
    	
    	const client = await Client.connect("Remeinium/Embedding_Siyabasa");
    	const result = await client.predict("/nearest_neighbors", { 		
    			word: "පෞරාණික", 		
    			top_k: 5, 
    	});

    	console.log(result.data);
    	
    ```
  </Tab>

  <Tab title="cURL">
    ```bash theme={null}
    curl -X POST https://remeinium-embedding-siyabasa.hf.space/gradio_api/call/nearest_neighbors -s -H "Content-Type: application/json" -d '{
    	"data": ["පෞරාණික",5]}' \
    	| awk -F'"' '{ print $4}'  \
    	| read EVENT_ID; curl -N https://remeinium-embedding-siyabasa.hf.space/gradio_api/call/nearest_neighbors/$EVENT_ID
    ```
  </Tab>
</Tabs>

#### **Accepts 2 parameters:**

1. `word` : `str` \**<u>Required</u>*

   > The input value that is provided in the "Query Word" Textbox component.
2. `top_k` : `float` *Default: 10*

   > The input value that is provided in the "Number of Results" Slider component.

#### **Returns 1 element**

`str | float | bool | list | dict`

> The output value that appears in the "Similar Words" Json component.