j1-template 2024.1.5 → 2024.2.1

data/lib/starter_web/pages/public/manuals/integrations/gemini/gemini.adoc

@@ -1,525 +0,0 @@
----
-title:                                  Google Gemini
-title_extention:                        Gemini API Integration for J1 Template
-tagline:                                User Guide for J1 Template
-
-date:                                   2022-08-14
-
-description: >
-                                        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".
-keywords: >
-                                        Jekyll, Theme, JekyllOne, Info, Google,
-                                        Gemini, Manual
-
-categories:                             [ Manual, Module ]
-tags:                                   [ Google, Gemini ]
-
-image:
-  path:                                 /assets/images/modules/attics/1920x1280/build-with-gemini.jpg
-  width:                                1920
-  height:                               1280
-
-tts:                                    true
-comments:                               false
-exclude_from_search:                    false
-regenerate:                             false
-permalink:                              /pages/public/manuals/integrations/google/gemini/
-
-resources:                              [
-                                          animate,
-                                          clipboard, rouge
-                                        ]
-resource_options:
-  - attic:
-      slides:
-        - url:                          /assets/images/modules/attics/1920x1280/build-with-gemini.jpg
-          alt:                          Build with Gemini
-#          badge:
-#            type:                       unsplash
-#            author:                     Eleni Afiontzi
-#            href:                       //unsplash.com/de/@eleniafiontzi
----
-
-// Page Initializer
-// =============================================================================
-// Enable the Liquid Preprocessor
-:page-liquid:
-
-// Set (local) page attributes here
-// -----------------------------------------------------------------------------
-// :page--attr:                         <attr-value>
-:images-dir:                            {imagesdir}/pages/roundtrip/100_present_images
-
-//  Load Liquid procedures
-// -----------------------------------------------------------------------------
-{% capture load_attributes %}themes/{{site.template.name}}/procedures/global/attributes_loader.proc{%endcapture%}
-
-// Load page attributes
-// -----------------------------------------------------------------------------
-{% include {{load_attributes}} scope="all" %}
-
-
-// Page content
-// ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-// Include sub-documents (if any)
-// -----------------------------------------------------------------------------
-[role="dropcap"]
-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.
-
-[role="mt-5"]
-== 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.
-
-
-[role="mt-5"]
-== Google AI Studio
-// https://ai.google.dev/docs
-
-link://ai.google.dev/[Google AI Studio, {browser-window--new}] 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.
-
-
-[role="mt-5"]
-== 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.
-
-[NOTE]
-====
-Adjusting to lower safety settings will trigger a more indepth
-review process of your application.
-====
-
-[role="mt-4"]
-=== 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:
-
-[cols="4a, 8a", options="header", width="100%", role="rtable mt-3 mb-5"]
-|===
-|Use Case |Category
-
-|Anti-Harassment Training App
-|Hate speech, Sexually explicit
-
-|Screenplay Writer
-|Sexually explicit, Dangerous
-
-|Toxicity classifier
-|Harassment, Dangerous
-
-|===
-
-[role="mt-4"]
-==== 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.
-
-[role="mt-4"]
-==== 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.
-
-[cols="4a, 8a", options="header", width="100%", role="rtable mt-3 mb-5"]
-|===
-|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
-link://ai.google.dev/api/rest/v1/HarmCategory[API reference, {browser-window--new}]
-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.
-
-[cols="4a, 8a", options="header", width="100%", role="rtable mt-3 mb-5"]
-|===
-|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
-link://ai.google.dev/api/rest/v1/SafetySetting#harmblockthreshold[HarmBlockThreshold, {browser-window--new}]
-API reference for details.
-
-[role="mt-4"]
-==== Safety feedback
-
-link://ai.google.dev/api/rest/v1/models/generateContent[generateContent, {browser-window--new}]
-returns a
-link //ai.google.dev/api/rest/v1/GenerateContentResponse[GenerateContentResponse, {browser-window--new}]
-which includes safety feedback.
-
-Prompt feedback is included in
-link://ai.google.dev/api/rest/v1/GenerateContentResponse#PromptFeedback[promptFeedback, {browser-window--new}].
-If
-link://ai.google.dev/api/rest/v1/GenerateContentResponse#blockreason[promptFeedback.blockReason, {browser-window--new}]
-is set, then the content of the prompt was blocked.
-
-Response candidate feedback is included in
-link://ai.google.dev/api/rest/v1/GenerateContentResponse#FinishReason[finishReason, {browser-window--new}]
-and
-link://ai.google.dev/api/rest/v1/GenerateContentResponse#safetyrating[safetyRatings, {browser-window--new}].
-
-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:
-
-[cols="4a, 8a", options="header", width="100%", role="rtable mt-3 mb-5"]
-|===
-|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`.
-
-[role="mt-4"]
-=== 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 [.material-icons]#warning# *No Content* message appears if the content
-is blocked. To see more details, hold the pointer over *No Content* and
-click [.material-icons]#warning# *Safety*.
-
-[role="mt-4"]
-=== Code examples
-
-This section shows how to use the safety settings in code using the
-python client library.
-
-[role="mt-4"]
-==== 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.
-
-[source, js]
-----
-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
-});
-
-----
-
-[role="mt-4"]
-==== Response example
-
-The following shows a code snippet for parsing the safety feedback from
-the response.
-
-[source, python]
-----
-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)
-----
-
-[role="mt-4"]
-=== Next steps
-
-* See the link://ai.google.dev/api/[API reference, {browser-window--new}]
-  to learn more about the full API.
-* Review the link://ai.google.dev/docs/safety_setting_gemini[safety guidance, {browser-window--new}]
-  for a general look at safety considerations when developing with LLMs.
-* Learn more about assessing probability versus severity from the
-  link://developers.perspectiveapi.com/s/about-the-api-score[Jigsaw team, {browser-window--new}]
-* Learn more about the products that contribute to safety solutions
-  like the
-  link://medium.com/jigsaw/reducing-toxicity-in-large-language-models-with-perspective-api-c31c39b7a4d7[Perspective API, {browser-window--new}].
-* You can use these safety settings to create a toxicity classifier.
-  See the
-  link://ai.google.dev/examples/train_text_classifier_embeddings[classification example, {browser-window--new}]
-  to get started.
-
-[role="mt-5"]
-== Train a Google Gemini bot using the API interface
-
-. Set Up a Google Cloud Project
-
-* Create a Google Cloud project if you don't already have one.
-* Enable the Dialogflow API and the Gemini API.
-* Create a service account with the "Dialogflow API Admin" and "Gemini API Admin" roles.
-* Generate a private key for the service account.
-
-[start=2]
-. Create a Gemini Agent
-
-* Go to the Gemini console and click "Create Agent".
-* Enter a name and description for your agent.
-* Select the language for your agent.
-* Click "Create".
-* Link Your Dialogflow Agent to Your Gemini Agent
-
-[start=3]
-. Go to the Dialogflow console and open your agent.
-
-* Click the "Integrations" tab.
-* Click "Add Integration".
-* Select "Gemini" from the list of integrations.
-* Enter the Gemini API endpoint and your service account's private key.
-* Click "Link".
-
-[start=4]
-. Train Your Gemini Bot
-
-* Open the Gemini console and go to the "Training" tab.
-* Click "Create Training Run".
-* Select your agent from the dropdown list.
-* Enter a name for the training run.
-* Select the training data to use.
-* Click "Start Training".
-
-[start=5]
-. Test the Agent
-
-* Click "Test" in the top right corner of the Dialogflow Console.
-* Type in a message and press "Enter."
-* The agent will generate a response based on the training data.
-
-[start=6]
-. Deploy the Agent to Gemini
-
-* Click the "Deploy" button in the top right corner of the Dialogflow Console.
-* Select "Gemini" as the deployment target.
-* Click "Deploy."
-
-[role="mt-4"]
-=== Monitor the Training Process
-
-The training process will take some time. You can monitor the progress in the Gemini console.
-Once the training is complete, you will receive an email notification.
-Deploy Your Gemini Bot
-
-Once the training is complete, you can deploy your bot to your website or mobile app.
-To do this, you will need to generate a deployment token from the Gemini console.
-Follow the instructions in the Gemini documentation to deploy your bot.
-Test Your Bot
-
-[role="mt-4"]
-=== Test the bot
-
-Once your bot is deployed, you can test it by sending it messages.
-You can use the Gemini console or the Gemini API to send messages to your bot.
-Evaluate the bot's responses to ensure that it is functioning as expected.
-Maintain and Update Your Bot
-
-Over time, you may need to maintain and update your bot.
-This may involve retraining the bot with new data or fixing bugs.
-You can use the Gemini console or the Gemini API to manage your bot.
-By following these steps, you can train, deploy, and maintain a Google Gemini bot using the API interface.
-
-[role="mt-5"]
-== What's next
-
-Prompt design is the process of creating prompts that elicit the desired
-response from language models. Writing well structured prompts is an essential
-part of ensuring accurate, high quality responses from a language model.
-Learn about link://ai.google.dev/docs/prompt_best_practices[best practices for prompt writing, {browser-window--new}].
-
-Gemini offers several model variations to meet the needs of different use
-cases, such as input types and complexity, implementations for chat or other
-dialog language tasks, and size constraints. Learn about the
-link://ai.google.dev/models/gemini[available Gemini models, {browser-window--new}].
-
-Gemini offers options for
-link://ai.google.dev/docs/increase_quota[requesting rate limit increases, {browser-window--new}].
-The rate limit for Gemini Pro models is 60 requests per minute (RPM).