Google Gemini refers to a family of large language models (LLMs) developed by Google DeepMind. It was announced on December 6, 2023, and is seen as the successor to LaMDA and PaLM 2.
The Gemini family consists of three models:
- Gemini Ultra
-
The largest and most capable model. It excels at multimodal tasks, which involve understanding and generating text, code, and other forms of data.
- Gemini Pro
-
A smaller model, designed for a balance of performance and efficiency. It is well-suited for tasks such as question answering, summarization, and translation.
- Gemini Nano
-
The smallest model, optimized for mobile and edge devices. It can still perform basic language tasks such as text generation and translation.
Gemini is still under development, but it has already achieved impressive results on a range of benchmarks. For example, Gemini Ultra achieved a state-of-the-art score of 59.4% on the new MMMU benchmark, which consists of multimodal tasks spanning different domains requiring deliberate reasoning.
Google is making Gemini models available through Google AI Studio and Google Cloud Vertex AI, so developers can integrate them into their own applications. The company is also releasing a limited number of Gemini 1.5 Pro models for early testing.
Gemini Pro
The first version of Gemini Pro is now accessible via the Gemini API and here’s more about it:
-
Gemini Pro outperforms other similarly-sized models on research benchmarks.
-
Today’s version comes with a 32K context window for text, and future versions will have a larger context window.
-
It’s free to use right now, within limits, and it will be competitively priced.
-
It comes with a range of features: function calling, embeddings, semantic retrieval and custom knowledge grounding, and chat functionality.
-
It supports 38 languages across 180+ countries and territories worldwide.
In today’s release, Gemini Pro accepts text as input and generates text as## output. It is also made a dedicated Gemini Pro Vision multimodal endpoint available today that accepts text and imagery as input, with text output.
SDKs are available for Gemini Pro to help you build apps that run anywhere. Python, Android (Kotlin), Node.js, Swift and JavaScript are all supported.
Google AI Studio
Google AI Studio is a free, web-based developer tool that enables you to quickly develop prompts and then get an API key to use in your app development.
You can sign into Google AI Studio with your Google account and take advantage of the free quota, which allows 60 requests per minute; 20x more than other free offerings. When you’re ready, you can simply click on “Get code” to transfer your work to your IDE of choice, or use one of the quickstart templates available in Android Studio, Colab or Project IDX.
To help us improve product quality, when you use the free quota, your API and Google AI Studio input and output may be accessible to trained reviewers. This data is de-identified from your Google account and API key.
Safety settings
This guide describes the adjustable safety settings available for the Gemini API. During the prototyping stage, you can adjust safety settings on 4 dimensions to quickly assess if your application requires more or less restrictive configuration.
By default, safety settings block content (including prompts) with medium or higher probability of being unsafe across any dimension. This baseline safety is designed to work for most use cases, so you should only adjust your safety settings if it’s consistently required for your application.
| Adjusting to lower safety settings will trigger a more indepth review process of your application. |
Safety filters
In addition to the adjustable safety filters, the Gemini API has built-in protections against core harms, such as content that endangers child safety. These types of harm are always blocked and cannot be adjusted.
The adjustable safety filters cover the following categories:
-
Harassment
-
Hate speech
-
Sexually explicit
-
Dangerous
These settings allow the developer to determine what is appropriate for your use case. For example, if you’re building a video game dialogue, you may deem it acceptable to allow more content rated as dangerous due to the nature of the game. Here are a few other example use cases that may need some flexibility in these safety settings:
| Use Case | Category |
|---|---|
Anti-Harassment Training App | Hate speech, Sexually explicit |
Screenplay Writer | Sexually explicit, Dangerous |
Toxicity classifier | Harassment, Dangerous |
Probability versus severity
The Gemini API blocks content based on the probability of content being unsafe and not the severity. This is important to consider because some content can have low probability of being unsafe even though the severity of harm could still be high. For example, comparing the sentences:
-
The robot punched me.
-
The robot slashed me up.
Sentence 1 might result in a higher probability of being unsafe but you might consider sentence 2 to be a higher severity in terms of violence.
Given this, it is important for each developer to carefully test and consider what the appropriate level of blocking is needed to support their key use cases while minimizing harm to end users.
Safety Settings
Safety settings are part of the request you send to the text service. It can be adjusted for each request you make to the API. The following table lists the categories that you can set and describes the type of harm that each category encompasses.
| Categories | Descriptions |
|---|---|
Harassment | Negative or harmful comments targeting identity and/or protected attributes. |
Hate speech | Content that is rude, disrespectful, or profane. |
Sexually explicit | Contains references to sexual acts or other lewd content. |
Dangerous | Promotes, facilitates, or encourages harmful acts. |
These definitions are in the API reference as well. The Gemini models only support HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_SEXUALLY_EXPLICIT, and HARM_CATEGORY_DANGEROUS_CONTENT.
The following table describes the block settings you can adjust for each category. For example, if you set the block setting to Block few for the Hate speech category, everything that has a high probability of being hate speech content is blocked. But anything with a lower probability is allowed.
If not set, the default block setting is Block some for all categories.
| Threshold (API) | Description |
|---|---|
BLOCK_NONE | Always show regardless of probability of unsafe content |
BLOCK_ONLY_HIGH | Block when high probability of unsafe content |
BLOCK_MEDIUM_AND_ABOVE | Block when medium or high probability of unsafe content |
BLOCK_LOW_AND_ABOVE | Block when low, medium or high probability of unsafe content |
HARM_BLOCK_THRESHOLD_UNSPECIFIED | Threshold is unspecified, block using default threshold |
You can set these settings for each request you make to the text service. See the HarmBlockThreshold API reference for details.
Safety feedback
generateContent returns a link //ai.google.dev/api/rest/v1/GenerateContentResponse[GenerateContentResponse, window="_blank"] which includes safety feedback.
Prompt feedback is included in promptFeedback. If promptFeedback.blockReason is set, then the content of the prompt was blocked.
Response candidate feedback is included in finishReason and safetyRatings.
If response content was blocked and the finishReason was SAFETY, you can inspect safetyRatings for more details. The safety rating includes the category and the probability of the harm classification. The content that was blocked is not returned.
The probability returned correspond to the block confidence levels as shown in the following table:
| Probability | Description |
|---|---|
NEGLIGIBLE | Content has a negligible probability of being unsafe |
LOW | Content has a low probability of being unsafe |
MEDIUM | Content has a medium probability of being unsafe |
HIGH | Content has a high probability of being unsafe |
For example, if the content was blocked due to the harassment category having a high probability, the safety rating returned would have category equal to HARASSMENT and harm probability set to HIGH.
Safety settings in Google AI Studio
You can also adjust safety settings in Google AI Studio, but you cannot turn them off. To do so, in the Run settings, click Edit safety settings:
And use the knobs to adjust each setting:
A No Content message appears if the content is blocked. To see more details, hold the pointer over No Content and click Safety.
Code examples
This section shows how to use the safety settings in code using the python client library.
Request example
The following is a python code snippet showing how to set safety settings in your GenerateContent call. This sets the harm categories Harassment and Hate speech to BLOCK_LOW_AND_ABOVE which blocks any content that has a low or higher probability of being harassment or hate speech.
import { GoogleGenerativeAI } from "//esm.run/@google/generative-ai";
import { HarmCategory, HarmBlockThreshold } from "//esm.run/@google/generative-ai";
const safetySettings = [
{
category: HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE
},
{
category: HarmCategory.HARM_CATEGORY_HARASSMENT,
threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH
},
{
category: HarmCategory.HARM_CATEGORY_HATE_SPEECH,
threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH
},
{
category: HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT,
threshold: HarmBlockThreshold.BLOCK_NONE
}
];
const model = genAI.getGenerativeModel({
model: "gemini-pro",
safetySettings
});Response example
The following shows a code snippet for parsing the safety feedback from the response.
try:
print(response.text)
except ValueError:
# If the response doesn't contain text, check if the prompt was blocked.
print(response.prompt_feedback)
# Also check the finish reason to see if the response was blocked.
print(response.candidates[0].finish_reason)
# If the finish reason was SAFETY, the safety ratings have more details.
print(response.candidates[0].safety_ratings)Next steps
-
See the API reference to learn more about the full API.
-
Review the safety guidance for a general look at safety considerations when developing with LLMs.
-
Learn more about assessing probability versus severity from the Jigsaw team
-
Learn more about the products that contribute to safety solutions like the Perspective API.
-
You can use these safety settings to create a toxicity classifier. See the classification example to get started.
Test the J1 Gemini implementation
For testing the current implementation of J1 Gemini, a previewer page is available at Chatbot. You’ll find a rich set of examples sorted by typical requests to demonstrate use cases the bot can process.
What next
Prompt design is creating prompts that elicit the desired response from language models. Writing well-structured prompts is essential to ensuring accurate, high-quality responses from a language model. Learn about best practices for prompt writing.
Gemini offers several model variations to meet the needs of different use cases, such as input types and complexity, chat or other dialog language task implementations, and size constraints. Learn about the available Gemini models.
Gemini offers options for requesting rate limit increases. The rate limit for Gemini Pro models is 60 requests per minute (RPM).