Skip to content

Commit

Permalink
Merge branch 'main' of github.com:box/developer.box.com
Browse files Browse the repository at this point in the history
  • Loading branch information
SowaProgramuje committed Oct 31, 2024
2 parents fd339be + dbdb7c4 commit 8a456a8
Show file tree
Hide file tree
Showing 25 changed files with 765 additions and 90 deletions.
19 changes: 18 additions & 1 deletion .spelling
Original file line number Diff line number Diff line change
Expand Up @@ -315,5 +315,22 @@ GPT-3
freeform
pre-defined
stringified
textembedding
Gecko
16k
4k
200k
128k
8k
1k
multimodal
1m
32k
2k
summarization
GPT-4o
Anthropic
GPT-4o-2024-05-13
text-embedding-ada-002
params
GPT-4o-mini
GPT-4o-mini
4 changes: 2 additions & 2 deletions content/guides/box-ai/ai-agents/get-agent-default-config.md
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,6 @@ When you set the `mode` parameter to `extract_structured` the response will be a
</Tabs>

[prereq]: g://box-ai/prerequisites
[models]: g://box-ai/supported-models
[models]: g://box-ai/ai-models
[ai-agent-config]: g://box-ai/ai-agents/overrides-tutorial
[override-tutorials]: g://box-ai/ai-agents/overrides-tutorial
[override-tutorials]: g://box-ai/ai-agents/overrides-tutorial
2 changes: 1 addition & 1 deletion content/guides/box-ai/ai-agents/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -31,4 +31,4 @@ To see specific use cases, check the [overrides tutorial][overrides].
[text-gen]: e://post_ai_text_gen#param_ai_agent
[agent-default]: g://box-ai/ai-agents/get-agent-default-config
[overrides]: g://box-ai/ai-agents/overrides-tutorial
[models]: g://box-ai/supported-models
[models]: g://box-ai/ai-models
7 changes: 4 additions & 3 deletions content/guides/box-ai/ai-agents/overrides-tutorial.md
Original file line number Diff line number Diff line change
Expand Up @@ -126,11 +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.

Expand Down Expand Up @@ -353,4 +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
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
---
rank: 14
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# AWS Claude 3.5 Sonnet

## Overview

**AWS Claude 3.5 Sonnet** model is designed to enhance language understanding and generation tasks.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**AWS Claude 3.5 Sonnet**| The name of the model. |
|API model name|`aws__claude_3_5_sonnet`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Amazon Web Services (AWS)** | The trusted organization that securely hosts LLM. |
|Model provider|**AWS Bedrock**| The organization that provides this model. |
|Release date| **June 20th, 2024** | The release date for the model.|
|Knowledge cutoff date| **April 2024**| The date after which the model does not get any information updates. |
|Input context window |**200k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens | **4k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **Not specified**| The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use. |

## Additional documentation

For additional information, see [official AWS Claude 3.5 Sonnet documentation][aws-claude].

[aws-claude]: https://aws.amazon.com/bedrock/claude/
[overrides]: g://box-ai/ai-agents/overrides-tutorial
36 changes: 36 additions & 0 deletions content/guides/box-ai/ai-models/aws-claude-3-haiku-model-card.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
---
rank: 15
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# AWS Claude 3 Haiku

## Overview

**AWS Claude 3 Haiku** model is tailored for various language tasks, including creative writing and conversational AI.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**AWS Claude 3 Haiku**| The name of the model. |
|API model name|`aws__claude_3_haiku`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Amazon Web Services (AWS)** | The trusted organization that securely hosts LLM. |
|Model provider|**Anthropic**| The organization that provides this model. |
|Release date| **March 13th, 2024** | The release date for the model.|
|Knowledge cutoff date| **August 2023**| The date after which the model does not get any information updates. |
|Input context window |**200k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens | **4k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **117** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use. |

## Additional documentation

For additional information, see [official AWS Claude 3 Haiku documentation][aws-claude].

[aws-claude]: https://aws.amazon.com/bedrock/claude/
[overrides]: g://box-ai/ai-agents/overrides-tutorial
34 changes: 34 additions & 0 deletions content/guides/box-ai/ai-models/aws-claude-3-sonnet-model-card.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
---
rank: 16
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# AWS Claude 3 Sonnet

**AWS Claude 3 Sonnet** model is designed for advanced language tasks, focusing on comprehension and context handling.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**AWS Claude 3 Sonnet**| The name of the model. |
|API model name|`aws__claude_3_sonnet`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Amazon Web Services (AWS)** | The trusted organization that securely hosts LLM. |
|Model provider|**Anthropic**| The organization that provides this model. |
|Release date| **March 4th 2024** | The release date for the model.|
|Knowledge cutoff date| **August 2023**| The date after which the model does not get any information updates. |
|Input context window |**200k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens | **4k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **49.8** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use.|

## Additional documentation

For additional information, see [official AWS Claude 3 Sonnet documentation][aws-claude].

[aws-claude]: https://aws.amazon.com/bedrock/claude/
[overrides]: g://box-ai/ai-agents/overrides-tutorial
35 changes: 35 additions & 0 deletions content/guides/box-ai/ai-models/aws-titan-text-lite-model-card.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
---
rank: 17
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# AWS Titan Text Lite

**AWS Titan Text Lite** model is designed for advanced language processing, capable of handling extensive contexts, making it suitable for complex tasks,
although the model itself is lightweight.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**AWS Titan Text Lite**| The name of the model. |
|API model name|`aws__titan_text_lite`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Amazon Web Services (AWS)** | The trusted organization that securely hosts LLM. |
|Model provider|**Anthropic**| The organization that provides this model. |
|Release date| **September 2024** | The release date for the model.|
|Knowledge cutoff date| **Not provided**| The date after which the model does not get any information updates. |
|Input context window |**128k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens | **4k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **Not specified** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use.|

## Additional documentation

For additional information, see [official AWS Titan documentation][aws-titan].

[aws-titan]: https://aws.amazon.com/bedrock/titan/
[overrides]: g://box-ai/ai-agents/overrides-tutorial
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
---
rank: 3
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# Azure OpenAI GPT-4o-2024-05-13

**Azure OpenAI GPT-4o-2024-05-13** is a multimodal model designed to handle lightweight tasks.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**GPT-4o 2024-05-13**| The name of the model. |
|API model name|`azure__openai__gpt_4o_2024-05-13`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Microsoft Azure** | The trusted organization that securely hosts LLM. |
|Model provider|**OpenAI**| The organization that provides this model. |
|Release date|**May 13th, 2024** | The release date for the model.|
|Knowledge cutoff date| **September 2023**| The date after which the model does not get any information updates. |
|Input context window |**128k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens |**2k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **87.5** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use.|

## Additional documentation

For additional information, see [official Azure OpenAI GPT-4o-2024-05-13 documentation][azure-ai-mini-4o-model].

[azure-ai-mini-4o-model]: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=python-secure#gpt-4o-and-gpt-4-turbo
[overrides]: g://box-ai/ai-agents/overrides-tutorial
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
---
rank: 4
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# Azure OpenAI GPT-4o Mini

**Azure OpenAI GPT-4o Mini** is a multimodal model designed to handle lightweight tasks.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**GPT-4o Mini**| The name of the model. |
|API model name|`azure__openai__gpt_4o_mini`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Microsoft Azure** | The trusted organization that securely hosts LLM. |
|Model provider|**OpenAI**| The organization that provides this model. |
|Release date|**July 18th, 2024** | The release date for the model.|
|Knowledge cutoff date| **October 2023**| The date after which the model does not get any information updates. |
|Input context window |**128k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens |**16k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **85.4** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use.|

## Usage

Box Webapp uses this model to cover the following use cases:

* Creating content
* Editing content
* Creating summaries
* Single doc Q&A on text

Box AI API uses this model to cover the following use cases:

* Creating content
* Editing content
* Creating summaries
* Single doc Q&A on text
* Extracting metadata

## Additional documentation

For additional information, see [official Azure OpenAI GPT-4o Mini documentation][azure-ai-mini-4o-model].

[azure-ai-mini-4o-model]: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=python-secure#gpt-4o-and-gpt-4-turbo
[overrides]: g://box-ai/ai-agents/overrides-tutorial
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
---
rank: 5
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---
# Azure text-embedding-ada-002

**Azure text-embedding-ada-002** is a multimodal model designed to handle lightweight tasks.

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**text-embedding-ada-002**| The name of the model. |
|API model name|`azure__openai__text_embedding_ada_002`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Microsoft Azure** | The trusted organization that securely hosts LLM. |
|Model provider|**OpenAI**| The organization that provides this model. |
|Release date|**December 2022** | The release date for the model.|
|Knowledge cutoff date| **September 2021**| The date after which the model does not get any information updates. |
|Input context window |**8k tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens |**Not applicable** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **1000** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use.|

## Additional documentation

For additional information, see [official Azure Embeddings models documentation][azure-ai-embeddings].

[azure-ai-embeddings]: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#embeddings
[overrides]: g://box-ai/ai-agents/overrides-tutorial
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
---
rank: 6
related_guides:
- box-ai/ask-questions
- box-ai/generate-text
- box-ai/extract-metadata
- box-ai/extract-metadata-structured
- box-ai/ai-agents/get-agent-default-config
---

# Google Gemini 1.5 Flash

**Google Gemini 1.5 Flash** is a multimodal model designed to handle lightweight tasks. It is designed for high-volume, low-latency tasks, making it highly efficient for large-scale use cases like summarization, multimodal processing, and categorization

## Model details

| Item | Value | Description |
|-----------|----------|----------|
|Model name|**Google Gemini 1.5 Flash**| The name of the model. |
|API model name|`google__gemini_1_5_flash_001`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
|Hosting layer| **Google** | The trusted organization that securely hosts LLM. |
|Model provider|**Google**| The organization that provides this model. |
|Release date|**May 14th 2024** | The release date for the model.|
|Knowledge cutoff date| **November 2023**| The date after which the model does not get any information updates. |
|Input context window |**1m tokens**| The number of tokens supported by the input context window.|
|Maximum output tokens |**8k tokens** |The number of tokens that can be generated by the model in a single request.|
|Empirical throughput| **176** | The number of tokens the model can generate per second.|
|Open source | **No** | Specifies if the model's code is available for public use. |

## Additional documentation

For additional information, see [official Google Gemini 1.5 Flash documentation][vertex-ai-gemini-models].

[vertex-ai-gemini-models]: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-models
[overrides]: g://box-ai/ai-agents/overrides-tutorial
Loading

0 comments on commit 8a456a8

Please sign in to comment.