> For the complete documentation index, see [llms.txt](https://docs.noqo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.noqo.ai/main-settings/additional-settings.md).

# Additional settings

In this section, we will provide a detailed explanation of additional settings.

Once you have specified the main **Bot Instructions**, entered the **Bot Name**, and set the **Timeout in seconds**, you can proceed to the additional settings. To do this, expand the settings menu by clicking the **Advanced** button:

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FtoVHqzRYCGR3EgDGN1VN%2FScreenshot_1.jpg?alt=media&amp;token=767ea327-baf6-41b4-8310-fd6687bb2162" alt=""><figcaption></figcaption></figure>

A menu with a number of **additional settings** will expand before you:

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FhEb3HSx18Hf5aVCkLfZA%2FAdditional_settings_2.jpg?alt=media&amp;token=333403dd-4a22-404d-948c-1442876ae210" alt=""><figcaption></figcaption></figure>

### Let's break down each setting individual

1. **Chatbot creativity**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FhNYVzDv6AF7VIuevY3BN%2FAdditional_settings_4.jpg?alt=media&amp;token=771257e4-c5f4-45ce-a644-3632fa5031c9" alt=""><figcaption></figcaption></figure>

> **Mode-to-Temperature Correspondence:**
>
> * **Stability – 0** (less creative, responds mostly with pre-formulated text)
> * **Balance – 10** (In Balanced mode, the chatbot combines accuracy with a slight touch of creativity. This mode is suitable for communication that requires both clarity and a bit of flexibility.)
> * **Creativity – 20** (produces more diverse and creative responses)

2. **Message History (Context)**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FgFFaSMcQUrV2y1A7UUtz%2FAdditional_settings_3.jpg?alt=media&amp;token=b2a34d79-c3aa-49e7-ba5a-5c4935c2009a" alt=""><figcaption></figcaption></figure>

> **Transfer message history** - this parameter determines how many recent messages are transmitted to the model for processing. In other words, how many of the last messages the **bot remembers**.
>
> * **Do not transfer history** - in this case, the bot will operate in ***Question-Answer*** mode.
> * **Transfer entire history** - the entire dialogue over time will be passed to the model. The model will better understand the context of the conversation, but this will increase token consumption, and in some situations, may worsen understanding of the context.\
>   \
>   For example, in the beauty industry, when a client books a service once a month and asks the same questions at a certain frequency. In this case, we recommend limiting the history context by time.
> * **Transfer history for X messages** - this means a certain number of messages defined by the user will be stored in the bot's memory.
> * **Transfer history for X minutes** - this means the message history will be stored in the bot's memory only for a certain time.

3. **Save function messages**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2Fu0cYiqpEAsSXypdSRIYi%2FAdditional%20Settings_5.jpg?alt=media&amp;token=834a7262-9e0d-4e62-bc0a-cdf9adeaf0c4" alt=""><figcaption></figcaption></figure>

**Save function messages** - after the initial function call, the bot will keep this function in memory and reference it later without spending additional tokens on a new call. This setting increases the cost of the whole dialogue but reduces the cost of an individual message.

4. **Conditions for interrupting a dialogue**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FVI84guvOFi5VuXfkEvON%2FScreenshot_7.jpg?alt=media&amp;token=9f224745-1137-47b1-8964-afbd6542ab65" alt=""><figcaption></figcaption></figure>

> * **Do not respond when the conversation is interrupted by a person** – If a staff member intervenes in the dialogue, the bot will stop responding, depending on the channel through which the inquiry was received.
> * **Phrases that trigger forced dialogue interruption** – If any of these phrases are used (by either the employee or the client), the bot will stop responding and hand over the conversation to a human (administrator). There are cases when an employee sends a message in the final communication channel, but the CRM system fails to recognize it as a staff message. This setting helps pause the bot’s responses from the end channel in such situations.
> * **Ignore initial employee messages** – Use this option if the dialogue is initiated by a mass message or automated outreach.
> * **Phrases that should not trigger interruption** – Use this to prevent the bot from stopping during specific automated messages, such as appointment confirmations or broadcast messages. In such cases, enter the exact text of the broadcast to ensure the bot continues the conversation.

{% hint style="info" %}
Please note that **interruption by trigger phrase** only works when the sent message matches the specified phrase exactly, character by character.
{% endhint %}

4. **Conditions for resuming dialogue**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2F5kT0FR17IveBRRFDSgCO%2FAdditional%20Settings_8.jpg?alt=media&amp;token=80f9ac37-a342-4386-a8ca-1d5244fc8fd8" alt=""><figcaption></figcaption></figure>

> * **Return control to bot after interruption** – A setting that allows the bot to resume the conversation after a specified period of time.
> * **Time to return control to bot (in minutes)** – The amount of time after which the bot will automatically resume interaction following an interruption.
> * **Phrases to resume bot operation** – Specific phrases that, when received (from the client or employee), will reactivate the bot and allow it to continue the conversation.

{% hint style="info" %}
Please note that **interruption by trigger phrase** only works when the sent message matches the specified phrase exactly, character by character.
{% endhint %}

5. **Ignoring customer messages**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FDZyYs4yIqvx5Tc6E0I3w%2FAdditional%20Settings_9.jpg?alt=media&amp;token=cb2df3e9-5914-494c-a6ec-96202dd481a7" alt=""><figcaption></figcaption></figure>

This setting allows the bot to ignore specific client messages.

* **Do not add message to the dialogue** — when enabled, the client's message will be excluded from the conversation context and will not influence the bot’s future responses.

6. **Conditions for dialogue stop**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2Fwl9k6zSWl1wIz4DeRHPg%2FAdditional%20Settings_10.jpg?alt=media&amp;token=6022d826-201c-4a09-8df7-05f8f7629d91" alt=""><figcaption></figcaption></figure>

**Conditions for dialogue stop** – If the specified phrase is spoken during the conversation (by either an employee or a client), the bot will stop responding. In some cases, an employee sends a message in the final channel, and CRM systems do not always recognize it as an employee message; in such situations, this setting helps pause the conversation from the final channel.

7. **Image Recognition**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FET40Yow1u7ccZ1mRs1CR%2FAdditional%20Settings_11.jpg?alt=media&amp;token=f1fd65ef-b072-4cce-982f-62932ba07ef8" alt=""><figcaption></figcaption></figure>

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2Fv0sz2JXWd8Ilq2lBDmvb%2FAdditional%20Settings_12.jpg?alt=media&amp;token=3e3bc0a1-48ce-4e2e-ba8c-1d645c590b90" alt=""><figcaption></figcaption></figure>

> This settings section allows managing the process of image recognition by the bot. You can choose one of the image processing modes:
>
> * **Disabled** - the model will not recognize images.
> * **If not Found in KB - i**n this mode, the bot will first search for an image match in the knowledge base. If no matches are found, the bot will act according to the instruction specified under the drop-down list.
> * **Always -** in this mode, the bot will always recognize images and act according to the instruction specified under the drop-down list.

8. **Splitting the response from the bot**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FSFfv92MBIWB9fmt7Meg1%2FAdditional%20Settings_13.jpg?alt=media&amp;token=734da2a6-8ab3-4ba4-864a-ab5f25a63028" alt=""><figcaption></figcaption></figure>

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FTN6DQc3baCXgnx0LoUgR%2FAdditional%20Settings_14.jpg?alt=media&amp;token=694ca950-877d-4714-ade0-cb00e3e19b2e" alt=""><figcaption></figcaption></figure>

> Split bot responses into several messages based on the selected settings.
>
> 1. Choose the method of splitting bot responses.
> 2. Specify the chunk size, that is, how many sentences or paragraphs will be included in each separate part of the response.

9. **Messages before and after**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2F2tba7Wf7VBFTtfgHDPZB%2FAdditional%20Settings_15.jpg?alt=media&amp;token=85514097-a05e-4914-96a9-1bc5e9f0039d" alt=""><figcaption></figcaption></figure>

> This is the text that will be sent ***Before*** and/or ***After*** a message from the neural network. For example, it can be used to sign that it is a bot.

**For example:**\
The bot responded with the phrase

```
Good day, how can I help you?
```

And in the channel *(and consequently to the end client)* will be sent:

```
Message from the bot:

Good day, how can I help you?

Text written by Noqo
```

If in these settings you specify `Message from the bot:` and `Text written by Noqo` respectively.

{% hint style="info" %}
The bot **will not** see this additional text.
{% endhint %}

10. **Replacement Patterns**

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FczFGTo7FDhtCkPDlhsbS%2FAdditional%20Settings_16.jpg?alt=media&amp;token=f08424f0-48d5-44ba-86bb-c6ed6dc889dc" alt=""><figcaption></figcaption></figure>

> Replacement patterns are used to substitute unwanted words or phrases in the bot's response with desirable ones.
>
> For example, if you want the bot to use "company" instead of "firm" in responses, fill in the fields as follows:

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2FKKj53VbxcvgF8di364tF%2FAdditional%20Settings_17.jpg?alt=media&amp;token=46d41a6d-aaba-4d55-ab02-53a50fd2c792" alt=""><figcaption></figcaption></figure>

The enabled setting **Pattern can be part of another word** allows replacing part of a word in the response:

<figure><img src="https://1782981877-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKvUDH16L29QcaH0CuUhn%2Fuploads%2F4NUgcSPmgMCjIFSNEmyW%2FAdditional%20Settings_18.jpg?alt=media&amp;token=673df104-65f6-4b68-ac45-15f82399a65d" alt=""><figcaption></figcaption></figure>
