diff --git a/docs/modules/ROOT/assets/images/.keepme b/docs/modules/ROOT/assets/images/.keepme deleted file mode 100644 index e69de29bb..000000000 diff --git a/docs/modules/ROOT/assets/images/chatbot-architecture.png b/docs/modules/ROOT/assets/images/chatbot-architecture.png new file mode 100644 index 000000000..c5f104adb Binary files /dev/null and b/docs/modules/ROOT/assets/images/chatbot-architecture.png differ diff --git a/docs/modules/ROOT/assets/images/llms-big-picture.png b/docs/modules/ROOT/assets/images/llms-big-picture.png new file mode 100644 index 000000000..5af83eb3c Binary files /dev/null and b/docs/modules/ROOT/assets/images/llms-big-picture.png differ diff --git a/docs/modules/ROOT/pages/index.adoc b/docs/modules/ROOT/pages/index.adoc index e5ee71a4a..24dcf1af0 100644 --- a/docs/modules/ROOT/pages/index.adoc +++ b/docs/modules/ROOT/pages/index.adoc @@ -16,6 +16,8 @@ For instance, an application utilizing this extension can: This extension is built upon the https://github.com/langchain4j/langchain4j[LangChain4j library]. It offers a declarative approach to interact with diverse LLMs like OpenAI, Hugging Face, or Ollama. It facilitates LLM-invoked functions within Quarkus applications and allows document loading within the LLM "context". +image::llms-big-picture.png[width=600,align="center"] + == Quick Overview To incorporate this extension, add the `io.quarkiverse.langchain4j:quarkus-langchain4j` extension to your build file. diff --git a/docs/modules/ROOT/pages/retrievers.adoc b/docs/modules/ROOT/pages/retrievers.adoc index 5cd80ce02..74897fe60 100644 --- a/docs/modules/ROOT/pages/retrievers.adoc +++ b/docs/modules/ROOT/pages/retrievers.adoc @@ -4,6 +4,7 @@ include::./includes/attributes.adoc[] Many applications involving Large Language Models (LLMs) often require user-specific data beyond their training set, such as CSV files, data from various sources, or reports. To achieve this, the process of Retrieval Augmented Generation (RAG) is commonly employed. + == Understanding the Data Ingestion Journey Before delving into the RAG process, it's crucial to delineate two distinct phases: @@ -12,6 +13,8 @@ The Data Ingestion Process:: Involves data collection, cleaning, transformation, The RAG Process:: Before engaging with the LLM, it seeks relevant documents in the database and passes them for model augmentation. +image::chatbot-architecture.png[width=1000,align="center"] + == Unveiling Embeddings Embeddings denote data representations, typically in a lower-dimensional space (arrays of floats), preserving essential characteristics of the original data. In the realm of language or text, word embeddings represent words as numerical vectors in a continuous space.