Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Minor doc improvements

Browse Source
This commit is contained in:
Christian Tzolov
2024-06-03 22:10:34 +02:00
parent 19f3930737
commit 7c86fc7c89
6 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
spring-ai-docs/src/main/antora/modules/ROOT/images/function-calling-basic-flow.jpg → spring-ai-docs/src/main/antora/modules/ROOT/images/function-calling-basic-flow2.jpg
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 237 KiB

After

Width:  |  Height:  |  Size: 237 KiB

BIN
spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-rag.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 363 KiB

BIN
spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-rag2.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 383 KiB

2
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/functions.adoc
View File

@@ -3,7 +3,7 @@
The integration of function support in AI models, permits the model to request the execution of client-side functions, thereby accessing necessary information or performing tasks dynamically as required.
image::function-calling-basic-flow.jpg[Function calling, width=500, align="center"]
image::function-calling-basic-flow2.jpg[Function calling, width=500, align="center"]
Spring AI currently supports Function invocation for the following AI Models

2
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/index.adoc
View File

@@ -26,7 +26,7 @@ Portable `Vector Store API` across multiple providers, including a novel `SQL-li
`Function calling`. Spring AI makes it easy to have the AI model invoke your POJO `java.util.Function` object.
image::function-calling-basic-flow.jpg[Function calling, width=500, align="center"]
image::function-calling-basic-flow2.jpg[Function calling, width=500, align="center"]
Check the Spring AI xref::api/functions.adoc[Function Calling] documentation.

4
spring-ai-docs/src/main/antora/modules/ROOT/pages/concepts.adoc
View File

@@ -189,7 +189,7 @@ The next phase in RAG is processing user input.
When a user's question is to be answered by an AI model, the question and all the "`similar`" document pieces are placed into the prompt that is sent to the AI model.
This is the reason to use a vector database. It is very good at finding similar content.
image::spring-ai-rag.jpg[Spring AI RAG, width=1000, align="center"]
image::spring-ai-rag2.jpg[Spring AI RAG, width=1000, align="center"]
There are several concepts that are used in implementing RAG.
The concepts map onto classes in Spring AI:
@@ -205,7 +205,7 @@ The concepts map onto classes in Spring AI:
Large Language Models (LLMs) are frozen after training, leading to stale knowledge and they are unable to access or modify external data.
image::function-calling-basic-flow.jpg[Function calling, width=800, align="center"]
image::function-calling-basic-flow2.jpg[Function calling, width=800, align="center"]
The `Function Calling` mechanism addresses these shortcomings.
It allows you to register your own functions to connect the large language models to the APIs of external systems.