j1-template 2024.3.17 → 2024.3.18

data/lib/starter_web/pages/public/manuals/integrations/google/gemini/security.asccidoc

@@ -1,274 +0,0 @@
-== 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.
-
-=== 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 you, 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 that's
-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=",",options="header",]
-|===
-|Use Case |Category
-|Anti-Harassment Training App |Hate speech, Sexually explicit
-|Screenplay Writer |Sexually explicit, Dangerous
-|Toxicity classifier |Harassment, Dangerous
-|===
-
-[[probability-vs]]
-==== 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
-
-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=",",options="header",]
-|===
-|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
-https://ai.google.dev/api/rest/v1/HarmCategory[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 other categories are used by PaLM
-2 (Legacy) models.
-
-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=",,",options="header",]
-|===
-|Threshold (Google AI Studio) |Threshold (API) |Description
-|Block none |BLOCK_NONE |Always show regardless of probability of unsafe
-content
-
-|Block few |BLOCK_ONLY_HIGH |Block when high probability of unsafe
-content
-
-|Block some |BLOCK_MEDIUM_AND_ABOVE |Block when medium or high
-probability of unsafe content
-
-|Block most |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
-https://ai.google.dev/api/rest/v1/SafetySetting#harmblockthreshold[`HarmBlockThreshold`]
-API reference for details.
-
-==== Safety feedback
-
-https://ai.google.dev/api/rest/v1/models/generateContent[`generateContent`]
-returns a
-https://ai.google.dev/api/rest/v1/GenerateContentResponse[`GenerateContentResponse`]
-which includes safety feedback.
-
-Prompt feedback is included in
-https://ai.google.dev/api/rest/v1/GenerateContentResponse#PromptFeedback[`promptFeedback`].
-If
-https://ai.google.dev/api/rest/v1/GenerateContentResponse#blockreason[`promptFeedback.blockReason`]
-is set, then the content of the prompt was blocked.
-
-Response candidate feedback is included in
-https://ai.google.dev/api/rest/v1/GenerateContentResponse#FinishReason[`finishReason`]
-and
-https://ai.google.dev/api/rest/v1/GenerateContentResponse#safetyrating[`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:
-
-[cols=",",options="header",]
-|===
-|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-ai-studio]]
-=== 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*:
-
-image:/static/docs/images/safety_settings_button.png[Safety settings
-button,scaledwidth=50.0%]
-
-And use the knobs to adjust each setting:
-
-image:/static/docs/images/safety_settings_ui.png[Safety settings
-button,scaledwidth=50.0%]
-
-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*.
-
-=== 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.
-
-[source, python]
-----
-from google.generativeai.types import HarmCategory, HarmBlockThreshold
-
-model = genai.GenerativeModel(model_name='gemini-pro-vision')
-response = model.generate_content(
-    ['Do these look store-bought or homemade?', img],
-    safety_settings={
-        HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
-        HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
-    }
-)
-----
-
-==== 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)
-----
-
-=== Next steps
-
-* See the https://ai.google.dev/api/[API reference] to learn more about
-the full API.
-* Review the link:/docs/safety_guidance[safety guidance] for a general
-look at safety considerations when developing with LLMs.
-* Learn more about assessing probability versus severity from the
-https://developers.perspectiveapi.com/s/about-the-api-score[Jigsaw team]
-* Learn more about the products that contribute to safety solutions like
-the
-https://medium.com/jigsaw/reducing-toxicity-in-large-language-models-with-perspective-api-c31c39b7a4d7[Perspective
-API].
-* You can use these safety settings to create a toxicity classifier. See
-the
-https://ai.google.dev/examples/train_text_classifier_embeddings[classification
-example] to get started.
-
-[[devsite-thumb-label-footer]]
-Was this helpful?
-
-image:data:image/svg+xml;base64,PHN2ZyBjbGFzcz0iZGV2c2l0ZS10aHVtYi1pY29uIiB2aWV3Ym94PSIwIDAgMjQgMjQiIGFyaWEtaGlkZGVuPSJ0cnVlIj4KICAgICAgICAgICAgICAgIDxwYXRoIGQ9Ik0yMSw3aC02LjMxbDAuOTUtNC41N2wwLjAzLTAuMzJjMC0wLjQxLTAuMTctMC43OS0wLjQ0LTEuMDZMMTQuMTcsMGMwLDAtNy4wOSw2Ljg1LTcuMTcsN0gydjEzaDE2IGMwLjgzLDAsMS41NC0wLjUsMS44NC0xLjIybDMuMDItNy4wNUMyMi45NSwxMS41LDIzLDExLjI2LDIzLDExVjlDMjMsNy45LDIyLjEsNywyMSw3eiBNNywxOEg0VjloM1YxOHogTTIxLDExbC0zLDdIOVY4bDQuMzQtNC4zNCBMMTIsOWg5VjExeiI+PC9wYXRoPgogICAgICAgICAgICAgIDwvc3ZnPg==[image]
-
-image:data:image/svg+xml;base64,PHN2ZyBjbGFzcz0iZGV2c2l0ZS10aHVtYi1pY29uIiB2aWV3Ym94PSIwIDAgMjQgMjQiIGFyaWEtaGlkZGVuPSJ0cnVlIj4KICAgICAgICAgICAgICAgIDxwYXRoIGQ9Ik0zLDE3aDYuMzFsLTAuOTUsNC41N2wtMC4wMywwLjMyYzAsMC40MSwwLjE3LDAuNzksMC40NCwxLjA2TDkuODMsMjRjMCwwLDcuMDktNi44NSw3LjE3LTdoNVY0SDYgQzUuMTcsNCw0LjQ2LDQuNSw0LjE2LDUuMjJsLTMuMDIsNy4wNUMxLjA1LDEyLjUsMSwxMi43NCwxLDEzdjJDMSwxNi4xLDEuOSwxNywzLDE3eiBNMTcsNmgzdjloLTNWNnogTTMsMTNsMy03aDl2MTBsLTQuMzQsNC4zNCBMMTIsMTVIM1YxM3oiPjwvcGF0aD4KICAgICAgICAgICAgICA8L3N2Zz4=[image]
-
-Send feedback
-
-Except as otherwise noted, the content of this page is licensed under
-the https://creativecommons.org/licenses/by/4.0/[Creative Commons
-Attribution 4.0 License], and code samples are licensed under the
-https://www.apache.org/licenses/LICENSE-2.0[Apache 2.0 License]. For
-details, see the https://developers.google.com/site-policies[Google
-Developers Site Policies]. Java is a registered trademark of Oracle
-and/or its affiliates.
-
-Last updated 2024-02-08 UTC.
-
-[\{ "type": "thumb-down", "id": "missingTheInformationINeed",
-"label":"Missing the information I need" },\{ "type": "thumb-down",
-"id": "tooComplicatedTooManySteps", "label":"Too complicated / too many
-steps" },\{ "type": "thumb-down", "id": "outOfDate", "label":"Out of
-date" },\{ "type": "thumb-down", "id": "samplesCodeIssue",
-"label":"Samples / code issue" },\{ "type": "thumb-down", "id":
-"otherDown", "label":"Other" }] [\{ "type": "thumb-up", "id":
-"easyToUnderstand", "label":"Easy to understand" },\{ "type":
-"thumb-up", "id": "solvedMyProblem", "label":"Solved my problem" },\{
-"type": "thumb-up", "id": "otherUp", "label":"Other" }]
-
-Need to tell us more?