Skip to content

Restructure documentation navigation #1526

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

Restructure documentation navigation #1526

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4ad9c28
Restructure documentation navigation
tzolov Oct 11, 2024
f3157a6
Rename AI Model API into AI Models
tzolov Oct 11, 2024
ee9de90
Get rid of the API suffix
tzolov Oct 11, 2024
c2aa35d
Improve Multimodality doc
tzolov Oct 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
68 changes: 34 additions & 34 deletions spring-ai-docs/src/main/antora/modules/ROOT/nav.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
* xref:index.adoc[Overview]
* xref:concepts.adoc[AI Concepts]
** xref:concepts.adoc[AI Concepts]
* xref:getting-started.adoc[Getting Started]
* xref:api/index.adoc[]
** xref:api/chatclient.adoc[]
*** xref:api/advisors.adoc[Advisors]
** xref:api/chatmodel.adoc[]
* xref:api/chatclient.adoc[]
** xref:api/advisors.adoc[Advisors]
* xref:api/index.adoc[AI Models]
** xref:api/chatmodel.adoc[Chat Models]
*** xref:api/prompt.adoc[]
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think the prompt stuff should move elsewhere. All the "API" subsections are specific to a model vendor whereas this is a higher level spring ai api topic.

*** xref:api/bedrock-chat.adoc[Amazon Bedrock]
**** xref:api/chat/bedrock/bedrock-anthropic3.adoc[Anthropic3]
**** xref:api/chat/bedrock/bedrock-anthropic.adoc[Anthropic2]
Expand Down Expand Up @@ -37,7 +38,7 @@
*** xref:api/chat/zhipuai-chat.adoc[ZhiPu AI]
// **** xref:api/chat/functions/zhipuai-chat-functions.adoc[Function Calling]
*** xref:api/chat/watsonx-ai-chat.adoc[watsonx.AI]
** xref:api/embeddings.adoc[]
** xref:api/embeddings.adoc[Embedding Models]
*** xref:api/bedrock.adoc[Amazon Bedrock]
**** xref:api/embeddings/bedrock-cohere-embedding.adoc[Cohere]
**** xref:api/embeddings/bedrock-titan-embedding.adoc[Titan]
Expand All @@ -56,49 +57,48 @@
**** xref:api/embeddings/vertexai-embeddings-palm2.adoc[PaLM2 Embedding]
*** xref:api/embeddings/watsonx-ai-embeddings.adoc[watsonx.AI]
*** xref:api/embeddings/zhipuai-embeddings.adoc[ZhiPu AI]
** xref:api/imageclient.adoc[]
** xref:api/imageclient.adoc[Image Models]
*** xref:api/image/azure-openai-image.adoc[Azure OpenAI]
*** xref:api/image/openai-image.adoc[OpenAI]
*** xref:api/image/stabilityai-image.adoc[Stability]
*** xref:api/image/zhipuai-image.adoc[ZhiPuAI]
*** xref:api/image/qianfan-image.adoc[QianFan]
** xref:api/audio[Audio Model API]
** xref:api/audio[Audio Models]
*** xref:api/audio/transcriptions.adoc[]
**** xref:api/audio/transcriptions/azure-openai-transcriptions.adoc[Azure OpenAI]
**** xref:api/audio/transcriptions/openai-transcriptions.adoc[OpenAI]
*** xref:api/audio/speech.adoc[]
**** xref:api/audio/speech/openai-speech.adoc[OpenAI]
** xref:api/moderation[Moderation Model API]
** xref:api/moderation[Moderation Models]
*** xref:api/moderation/openai-moderation.adoc[OpenAI]
// ** xref:api/generic-model.adoc[]

** xref:api/vectordbs.adoc[]
*** xref:api/vectordbs/azure.adoc[]
*** xref:api/vectordbs/apache-cassandra.adoc[]
*** xref:api/vectordbs/chroma.adoc[]
*** xref:api/vectordbs/elasticsearch.adoc[]
*** xref:api/vectordbs/gemfire.adoc[GemFire]
*** xref:api/vectordbs/milvus.adoc[]
*** xref:api/vectordbs/mongodb.adoc[]
*** xref:api/vectordbs/neo4j.adoc[]
*** xref:api/vectordbs/opensearch.adoc[]
*** xref:api/vectordbs/oracle.adoc[Oracle]
*** xref:api/vectordbs/pgvector.adoc[]
*** xref:api/vectordbs/pinecone.adoc[]
*** xref:api/vectordbs/qdrant.adoc[]
*** xref:api/vectordbs/redis.adoc[]
*** xref:api/vectordbs/hana.adoc[SAP Hana]
*** xref:api/vectordbs/typesense.adoc[]
*** xref:api/vectordbs/weaviate.adoc[]

** xref:api/functions.adoc[Function Calling]
** xref:api/multimodality.adoc[Multimodality]
** xref:api/prompt.adoc[]
** xref:api/structured-output-converter.adoc[Structured Output]
* xref:api/vectordbs.adoc[]
** xref:api/etl-pipeline.adoc[]
** xref:api/testing.adoc[]
** xref:api/generic-model.adoc[]
** xref:api/vectordbs/azure.adoc[]
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Similar to the other comment, the ETL pipeline, while certainly being vector store focused, is it's own top level concern or concept and like the other AI Model sections, this is where I go to find specific info on a vendor's vector store as compared to the higher level topic of ETL.

** xref:api/vectordbs/apache-cassandra.adoc[]
** xref:api/vectordbs/chroma.adoc[]
** xref:api/vectordbs/elasticsearch.adoc[]
** xref:api/vectordbs/gemfire.adoc[GemFire]
** xref:api/vectordbs/milvus.adoc[]
** xref:api/vectordbs/mongodb.adoc[]
** xref:api/vectordbs/neo4j.adoc[]
** xref:api/vectordbs/opensearch.adoc[]
** xref:api/vectordbs/oracle.adoc[Oracle]
** xref:api/vectordbs/pgvector.adoc[]
** xref:api/vectordbs/pinecone.adoc[]
** xref:api/vectordbs/qdrant.adoc[]
** xref:api/vectordbs/redis.adoc[]
** xref:api/vectordbs/hana.adoc[SAP Hana]
** xref:api/vectordbs/typesense.adoc[]
** xref:api/vectordbs/weaviate.adoc[]


* xref:observabilty/index.adoc[]
* xref:api/functions.adoc[Function Calling]
* xref:api/multimodality.adoc[Multimodality]
* xref:api/testing.adoc[LLM Evaluation]
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We rarely use LLM, i'll change to AI Model Evaluation

* xref:api/structured-output-converter.adoc[Structured Output]

* Service Connections
** xref:api/docker-compose.adoc[Docker Compose]
Expand Down
18 changes: 8 additions & 10 deletions spring-ai-docs/src/main/antora/modules/ROOT/pages/api/multimodality.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,23 +1,21 @@
[[Multimodality]]
= Multimodality API

// image::orbis-sensualium-pictus2.jpg[Orbis Sensualium Pictus, align="center"]

> "All things that are naturally connected ought to be taught in combination" - John Amos Comenius, "Orbis Sensualium Pictus", 1658

Humans process knowledge, simultaneously across multiple modes of data inputs.
The way we learn, our experiences are all multimodal.
We don't have just vision, just audio and just text.

These foundational principles of learning were articulated by the father of modern education link:https://en.wikipedia.org/wiki/John_Amos_Comenius[John Amos Comenius], in his work, "Orbis Sensualium Pictus", dating back to 1658.

image::orbis-sensualium-pictus2.jpg[Orbis Sensualium Pictus, align="center"]

> "All things that are naturally connected ought to be taught in combination"

Contrary to those principles, in the past, our approach to Machine Learning was often focused on specialized models tailored to process a single modality.
Contrary to those principles, the Machine Learning was often focused on specialized models tailored to process a single modality.
For instance, we developed audio models for tasks like text-to-speech or speech-to-text, and computer vision models for tasks such as object detection and classification.

However, a new wave of multimodal large language models starts to emerge.
Examples include OpenAI's GPT-4 Vision, Google's Vertex AI Gemini Pro Vision, Anthropic's Claude3, and open source offerings LLaVA and balklava are able to accept multiple inputs, including text images, audio and video and generate text responses by integrating these inputs.
Examples include OpenAI's GPT-4o , Google's Vertex AI Gemini 1.5, Anthropic's Claude3, and open source offerings Llama3.2, LLaVA and Balklava are able to accept multiple inputs, including text images, audio and video and generate text responses by integrating these inputs.

The multimodal large language model (LLM) features enable the models to process and generate text in conjunction with other modalities such as images, audio, or video.
NOTE: The multimodal large language model (LLM) features enable the models to process and generate text in conjunction with other modalities such as images, audio, or video.

== Spring AI Multimodality

Expand Down Expand Up @@ -68,7 +66,7 @@ and produce a response like:
Spring AI provides multimodal support for the following chat models:

* xref:api/chat/openai-chat.adoc#_multimodal[OpenAI (e.g. GPT-4 and GPT-4o models)]
* xref:api/chat/ollama-chat.adoc#_multimodal[Ollama (e.g. LlaVa and Baklava models)]
* xref:api/chat/ollama-chat.adoc#_multimodal[Ollama (e.g. LlaVa, Baklava, Llama3.2 models)]
* xref:api/chat/vertexai-gemini-chat.adoc#_multimodal[Vertex AI Gemini (e.g. gemini-1.5-pro-001, gemini-1.5-flash-001 models)]
* xref:api/chat/anthropic-chat.adoc#_multimodal[Anthropic Claude 3]
* xref:api/chat/bedrock/bedrock-anthropic3.adoc#_multimodal[AWS Bedrock Anthropic Claude 3]
Expand Down