prepare documentation for AI GA

.spelling

@@ -315,4 +315,5 @@ GPT-3
 freeform
 pre-defined
 stringified
-params
+params
+GPT-4o-mini

content/guides/api-calls/api-versioning-strategy.md

@@ -214,6 +214,14 @@ Breaking changes in the Box API occur within versioned releases, typically accom
 We use [oasdiff](https://github.com/Tufin/oasdiff/blob/main/BREAKING-CHANGES-EXAMPLES.md) tool to detect most of the possible breaking changes.
 </Message>
 
+## AI agent configuration versioning
+
+The aim of [AI agent](g://box-ai/ai-agents) versioning is to provide developers with more control of model version management and to ensure the consistency of the responses. 
+The following points apply regarding the agent versioning:
+
+- Each model snapshot is supported for 12 months, unless there are factors outside of Box's control. For example, a Large Language Model may get deprecated.
+- A model snapshot is available unless a new, stable model version is released A 6-month window is provided to test and transition to the new snapshot.
+
 ## Support policy and deprecation information
 
 When new versions of the Box APIs and Box SDKs are released, earlier versions will be retired. Box marks a version as `deprecated` at least 24 months before retiring it. In other words, a deprecated version cannot become end-of-life

content/guides/box-ai/ai-agents/get-agent-default-config.md

@@ -13,8 +13,7 @@ related_guides:
 # Get default AI agent configuration
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
-
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
 </Message>
 
 The `GET /2.0/ai_agent_default` endpoint allows you to fetch the default configuration for AI services. 

content/guides/box-ai/ai-agents/index.md

@@ -13,6 +13,10 @@ related_guides:
 
 # AI model overrides
 
+<Message type="notice">
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
+</Message>
+
 Box updates the default models across the endpoints on a regular basis to stay up to date with the most advanced options. 
 
 If your implementation is based on Box AI, a new default model might alter the results in a way that could break or change a downstream process. Switching to a specific version may prevent encountering any issues.

content/guides/box-ai/ai-agents/overrides-tutorial.md

@@ -13,8 +13,7 @@ related_guides:
 # Override AI model configuration
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
-
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
 </Message>
 
 The `agent_ai` configuration allows you to override the default AI model configuration. It is available for the following endpoints:
@@ -127,11 +126,11 @@ The set of parameters available for `ask`, `text_gen`, `extract`, `extract_struc
 
 ### LLM endpoint params
 
-The `llm_endpoint_params` configuration options differ depending on the overall AI model being [Google][google-params] or [OpenAI][openai-params] based.
+The `llm_endpoint_params` configuration options differ depending on the overall AI model being [Google][google-params], [OpenAI][openai-params], or [AWS][aws-params] based.
 
 For example, both `llm_endpoint_params` objects accept a `temperature` parameter, but the outcome differs depending on the model.
 
-For Google models, the [`temperature`][google-temp] is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
+For Google and AWS models, the [`temperature`][google-temp] is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
 
 For OpenAI models, [`temperature`][openai-temp] is the sampling temperature with values between 0 and 2. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic. When introducing your own configuration, use `temperature` or or `top_p` but not both.
 
@@ -354,4 +353,5 @@ Using this model results in a response listing more metadata entries:
 [openai-tokens]: https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them
 [agent]: e://get_ai_agent_default
 [google-temp]: https://ai.google.dev/gemini-api/docs/models/generative-models#model-parameters
-[openai-temp]: https://community.openai.com/t/temperature-top-p-and-top-k-for-chatbot-responses/295542
+[openai-temp]: https://community.openai.com/t/temperature-top-p-and-top-k-for-chatbot-responses/295542
+[aws-params]: r://ai-llm-endpoint-params-aws

content/guides/box-ai/ask-questions.md

@@ -11,11 +11,6 @@ related_guides:
 
 # Ask questions to Box AI
 
-<Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
-
-</Message>
-
 Box AI API allows you to
 ask a question about a supplied file or
 a set of files, and get a response based on

content/guides/box-ai/extract-metadata-structured.md

@@ -12,7 +12,7 @@ related_guides:
 # Extract metadata from file (structured)
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
 
 </Message>
 

content/guides/box-ai/extract-metadata.md

@@ -10,7 +10,7 @@ related_guides:
 # Extract metadata from file (freeform)
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
 
 </Message>
 

content/guides/box-ai/generate-text.md

@@ -10,7 +10,7 @@ related_guides:
 # Generate text with Box AI
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
+Box AI API is available to all Enterprise Plus customers.
 
 </Message>
 

content/guides/box-ai/index.md

@@ -14,7 +14,7 @@ related_guides:
 # Box AI
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
 </Message>
 
 Box AI API allows you to use Box AI
@@ -115,19 +115,6 @@ better results for this language.
 
 </Message>
 
-## Box AI API in User Activity Report (UAR)
-
-[User Activity Reports][uar] provide an overview of the
-actions the users are taking in Box. Box Admins
-use this report to view the actions taken by their
-users within a given time period, and this
-includes interactions with Box AI. The report
-contains the following action types that Box admins can
-select to get details for Box AI:
-
-* `AI query`: The user queried Box AI and received a response.
-* `Failed AI query`: The user queried Box AI but did not receive a response.
-
 [boxainotes]: https://support.box.com/hc/en-us/articles/22198577315347-Box-AI-for-Notes
 [boxaidocs]: https://support.box.com/hc/en-us/articles/22158484213267-Box-AI-for-Documents
 [boxaielement]: g://embed/ui-elements/preview#box-ai-ui-element

content/guides/box-ai/prerequisites.md

@@ -10,7 +10,7 @@ related_guides:
 # Get started with Box AI
 
 <Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
+Endpoints related to metadata extraction are currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
 </Message>
 
 To implement Box AI API in your solutions, you need

content/guides/box-ai/supported-models.md

@@ -8,14 +8,10 @@ related_guides:
 
 # Supported AI models
 
-<Message type="notice">
-Box AI API is currently a beta feature offered subject to Box’s Main Beta Agreement, and the available capabilities may change. Box AI API is available to all Enterprise Plus customers.
-</Message>
-
 The table lists the supported AI models you can use to:
 
 - get the [default AI agent configuration][agent],
-- override the AI agent configuration used in [`POST 2.0/ai/ask`][ask] and [`POST 2.0/ai/text_gen`][text-gen] endpoints.
+- override the AI agent configuration used in the Box AI API endpoints.
 
 When using `model` parameter your API calls, use the **API Name** listed in the table.
 For example, to get the AI agent configuration for a specific model, use the [model][ai-model] parameter and provide the `openai__gpt_3_5_turbo_16k` API name.
@@ -30,7 +26,7 @@ may be limited.
 | Provider | Family |Availability| API Name | External documentation | Capability | 
 | --------------- | ------ |-----| --------------------------------------- | ----------------------------------------------------------------------- | ---------- |
 | Microsoft Azure | GPT |available| `azure__openai__gpt_3_5_turbo_16k` | [Azure OpenAI GPT-3.5 model documentation][azure-ai-model-gpt35] | Chat | 
-| Microsoft Azure | GPT |available| `azure__openai__gpt_4o_mini` | [Azure OpenAI GPT-3.5 model documentation][azure-ai-model-gpt40] | Chat | 
+| Microsoft Azure | GPT |available| `azure__openai__gpt_4o_mini` | [Azure OpenAI GPT-4o-mini model documentation][azure-ai-model-gpt40] | Chat | 
 | Microsoft Azure | GPT |available| `azure__openai__text_embedding_ada_002` | [Azure OpenAI embeddings models documentation][azure-ai-embeddings] | Embeddings | 
 | GCP Vertex | Gecko | available |`google__textembedding_gecko` | [Google Vertex AI embeddings models documentation][vertex-ai-model] | Embeddings | 
 | GCP Vertex | Gecko | available |`google__textembedding_gecko_002` | [Google Vertex AI embeddings model documentation][vertex-ai-model] | Embeddings |
@@ -45,6 +41,10 @@ may be limited.
 | OpenAI | GPT | available in Beta only|`openai__gpt_4_turbo_preview` | [OpenAI GPT-4 models documentation][openai-gpt-4-models] | Chat | 
 | OpenAI | GPT | available in Beta only |`openai__gpt_4o_2024_05_13` | [OpenAI GPT-4 models documentation][openai-gpt-4-models] | Chat | 
 | OpenAI | GPT |available in Beta only| `openai__text_embedding_ada_002` | [Azure OpenAI embeddings models documentation][openai-embeddings] | Embeddings | 
+| AWS | Claude |available | `aws__claude_3_haiku` | [Amazon Claude model documentation][aws-claude] | Chat | 
+| AWS | Claude |available | `aws__claude_3_sonnet` | [Amazon Claude model documentation][aws-claude] | Chat |
+| AWS | Claude |available | `aws__claude_3_5_sonnet` | [Amazon Claude model documentation][aws-claude] | Chat | 
+| AWS | Titan |available | `aws__titan_text_lite` | [Amazon Titan model documentation][aws-titan] | Chat | 
 
 [ask]: e://post_ai_ask
 [text-gen]: e://post_ai_text_gen
@@ -59,3 +59,5 @@ may be limited.
 [azure-ai-embeddings]: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#embeddings
 [openai-embeddings]: https://platform.openai.com/docs/models/embeddings
 [ai-model]: e://get-ai-agent-default#param-model
+[aws-claude]: https://aws.amazon.com/bedrock/claude/
+[aws-titan]: https://aws.amazon.com/bedrock/titan/