# Google Gemini

🚀 Launch your own AI chatbot effortlessly with Google Gemini! 

{% embed url="<https://www.youtube.com/watch?v=aIWxpy_JTAI>" %}

You have to follow the instructions to connect Google Gemini

1. Go to 👇

{% embed url="<https://ai.google.dev/>" %}

2. Click on “Get Gemini API key in Google Studio”
3. Go to AI STUDIO Create API key  👇

{% embed url="<https://aistudio.google.com/app/apikey>" %}

<figure><img src="/files/SDQi38UHQpEYax6NVonC" alt=""><figcaption></figcaption></figure>

4. Select project

<figure><img src="/files/gklLP4zfy5qmZf4ZGzhz" alt=""><figcaption></figcaption></figure>

5. API key generated. Copy the API key

<figure><img src="/files/YtuCeXq8Ju6JVHQk4QSi" alt=""><figcaption></figcaption></figure>

6. Paste the API in Integration -> Google Gemini

<figure><img src="/files/HeR8CweEMKQqtAKJjevj" alt=""><figcaption></figcaption></figure>

**Available Actions:**

* Chat completions
* Clear chat history&#x20;
* List available models.
* Vision: Image-to-text conversion.

<figure><img src="/files/dndZ7djbgUy2oNSWspw3" alt=""><figcaption></figcaption></figure>

**Creating Chat Completions:**

* Users can input messages from users, enable history, select preferred models, set parameters (max tokens, temperature), and receive responses.
* Notable difference: Google Gemini doesn't support system messages, limiting its use for business-related inquiries compared to OpenAI.

<figure><img src="/files/O6y2zAaNEd21wfZI0nsB" alt=""><figcaption></figcaption></figure>

**Response Payload:**

* Responses are fast and returned with a different payload structure compared to OpenAI.
* Responses are located within the content section of the payload.
* Safety ratings provided, including categories like sexually explicit, hate speech, harassment, and dangerous content.

<figure><img src="/files/gF388QRnHosKRe3ACmzm" alt=""><figcaption></figcaption></figure>

Safety ratings:

<figure><img src="/files/lQ35b6xI1GVQEi2AH0IJ" alt=""><figcaption></figcaption></figure>

**Models:**

Users can retrieve available models through a GET request.

<figure><img src="/files/SYSfzL6ypXzire3uONur" alt=""><figcaption></figcaption></figure>

**Vision Functionality:**

Vision functionality allows users to input image URLs and receive descriptions, with safety ratings provided for images as well.

<figure><img src="/files/N7JNqkMoe8kK0rsfN2h4" alt=""><figcaption></figcaption></figure>

How to use in flow follow the video:

🚀 Launch your own AI chatbot effortlessly with Google Gemini!&#x20;

{% embed url="<https://www.youtube.com/watch?v=aIWxpy_JTAI>" %}


---

# Agent Instructions: 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:

```
GET https://docs.rapidbott.com/help-center/artificial-intelligencs/google-gemini.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.