> For the complete documentation index, see [llms.txt](https://docs.3dolphins.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.3dolphins.ai/5.3.0-id/bot-settings-1/think-paragraph/think-paragraph-configuration.md).

# Think Paragraph Configuration

Anda dapat mengatur konfigurasi think paragraph dengan mengklik tombol **'Configuration'** (<img src="/files/baU9xJp5f0X7j5ylelTN" alt="" data-size="line">) di kanan atas halaman. Kemudian, Anda dapat melihat pop up konfigurasi dan Anda dapat memutuskan bagaimana tepatnya bot Anda menafsirkan apa yang dikatakan pelanggan Anda dengan menggunakan tingkat kepercayaan. Setiap kali pelanggan Anda mengetik pesan, bot menganalisis akurasinya. Dalam pop-up ini, Anda juga dapat mengatur Client Id dan Client Secret.

![Think Paragraph Configuration](/files/rPuZSNWgGoObyKrUaYUA)

**Penjelasan Komponen:**

| Nama                               | Deskripsi                                                                                                                                                                                                   |
| ---------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Retrieval Score (Confidence Level) | Anda dapat memutuskan seberapa tepat bot Anda menafsirkan apa yang dikatakan pelanggan Anda dengan menggunakan tingkat kepercayaan. Setiap kali pelanggan Anda mengetik pesan, bot menganalisis akurasinya. |
| Client Id & Client Secret          | Client id dan client secret digunakan untuk integrasi dengan 3Dolphins Think.                                                                                                                               |
| Iteration                          | Untuk menentukan jumlah proses epoch yang akan dijalankan oleh sistem.                                                                                                                                      |
| Learning Rate                      | Merupakan jumlah bobot yang diperbarui selama training.                                                                                                                                                     |
| Min Learning Rate                  | Mengatur jumlah minimum bobot yang diperbarui selama training.                                                                                                                                              |
| Layer Size                         | Parameter untuk mengonfigurasi ukuran hidden layer.                                                                                                                                                         |
| Batch Size                         | Menentukan jumlah sampel untuk diproses sebelum memperbarui parameter model internal (jumlah kata yang diproses sekaligus).                                                                                 |
| Min Word Frequency                 | Jumlah minimal kata yang harus muncul di corpus.                                                                                                                                                            |
| Window Size                        | Parameter untuk mengatur panjang cutout dari urutan waktu data.                                                                                                                                             |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.3dolphins.ai/5.3.0-id/bot-settings-1/think-paragraph/think-paragraph-configuration.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.