Machine Learning: Rework intro page

docs/domain/ml/index.md

@@ -3,52 +3,104 @@
 
 # Machine Learning
 
-Guidelines about integrating CrateDB with machine learning frameworks and tools.
+Integrate CrateDB with machine learning frameworks and
+tools, for [MLOps] and [Vector database] operations.
 
-(langchain)=
-## LangChain
 
-Tutorials and Notebooks about using [LangChain] together with CrateDB.
+:::::{grid}
+:padding: 0
 
-- [LangChain and CrateDB: Code Examples]
+::::{grid-item}
+:class: rubric-slimmer
+:columns: 6
 
-- CrateDB's `FLOAT_VECTOR` type and its `KNN_MATCH` function can be used for storing and
-  retrieving embeddings, and for conducting similarity searches.
+:::{rubric} Machine Learning Operations
+:::
+Training a machine learning model, running it in production, and maintaining
+it, requires a significant amount of data processing and bookkeeping
+operations.
 
-  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/vector_search.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/vector_search.ipynb) [![Launch Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/crate/cratedb-examples/main?labpath=topic%2Fmachine-learning%2Fllm-langchain%2Fvector_search.ipynb)
+CrateDB, as a universal SQL database, supports this process through
+adapters to best-of-breed software components for MLOps procedures.
 
-- Database tables in CrateDB can be used as a source provider for LangChain documents.
+MLOps is a paradigm that aims to deploy and maintain machine learning models
+in production reliably and efficiently, including experiment tracking, and in
+the spirit of continuous development and DevOps.
+::::
 
-  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/document_loader.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/document_loader.ipynb) [![Launch Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/crate/cratedb-examples/main?labpath=topic%2Fmachine-learning%2Fllm-langchain%2Fdocument_loader.ipynb)
+::::{grid-item}
+:class: rubric-slimmer
+:columns: 6
 
-- CrateDB supports managing LangChain's conversation history.
+:::{rubric} Vector Store
+:::
+CrateDB's FLOAT_VECTOR data type implements a vector store and the k-nearest
+neighbour (kNN) search algorithm to find vectors that are similar to a query
+vector.
 
-  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/conversational_memory.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/conversational_memory.ipynb) [![Launch Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/crate/cratedb-examples/main?labpath=topic%2Fmachine-learning%2Fllm-langchain%2Fconversational_memory.ipynb)
+These feature vectors may be computed from raw data using machine learning
+methods such as feature extraction algorithms, word embeddings, or deep
+learning networks. 
 
-- What can you build with LangChain?
+Vector databases can be used for similarity search, multi-modal search,
+recommendation engines, large language models (LLMs), retrieval-augmented
+generation (RAG), and other applications.
+::::
+
+:::::
 
-  - [LangChain: Retrieval augmented generation]
-  - [LangChain: Analyzing structured data]
-  - [LangChain: Chatbots]
+
+## Anomaly Detection and Forecasting
 
 
 (mlflow)=
-## MLflow
+### MLflow
 
 Tutorials and Notebooks about using [MLflow] together with CrateDB.
 
-- Blog series on "Running Time Series Models in Production using CrateDB"
-  - Part 1: [Introduction to Time Series Modeling using Machine Learning]
+::::{info-card}
+:::{grid-item} **Blog: Running Time Series Models in Production using CrateDB**
+:columns: 9
+
+Part 1: Introduction to [Time Series Modeling using Machine Learning]
+
+The article will introduce you to the concept of time series modeling, and
+discuss the main obstacles faced during its implementation in production.
+
+It will introduce you to CrateDB, highlighting its key features and
+benefits, why it stands out in managing time series data, and why it is
+an especially good fit for supporting machine learning models in production.
+:::
+:::{grid-item}
+:columns: 3
+{tags-primary}`Fundamentals` \
+{tags-secondary}`Time Series Modeling`
+:::
+::::
 
-- [MLflow and CrateDB]: Guidelines and runnable code to get started with MLflow and
-  CrateDB, exercising time series anomaly detection and timeseries forecasting /
-  prediction using NumPy, Merlion, and Matplotlib.
 
-  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/mlops-mlflow/tracking_merlion.ipynb) [![Open in Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/mlops-mlflow/tracking_merlion.ipynb)
+::::{info-card}
+:::{grid-item} **Notebook: Create a Time Series Anomaly Detection Model**
+:columns: 9
+
+Guidelines and runnable code to get started with MLflow and
+CrateDB, exercising time series anomaly detection and timeseries forecasting /
+prediction using NumPy, Salesforce Merlion, and Matplotlib.
+
+[![README](https://img.shields.io/badge/Open-README-darkblue?logo=GitHub)][MLflow and CrateDB]
+[![Notebook on GitHub](https://img.shields.io/badge/Open-Notebook%20on%20GitHub-darkgreen?logo=GitHub)][tracking-merlion-github]
+[![Notebook on Colab](https://img.shields.io/badge/Open-Notebook%20on%20Colab-blue?logo=Google%20Colab)][tracking-merlion-colab]
+:::
+:::{grid-item}
+:columns: 3
+{tags-primary}`Fundamentals` \
+{tags-secondary}`Anomaly Detection`
+:::
+::::
 
 
 (pycaret)=
-## PyCaret
+### PyCaret
 
 Tutorials and Notebooks about using [PyCaret] together with CrateDB.
 
@@ -65,21 +117,78 @@ Tutorials and Notebooks about using [PyCaret] together with CrateDB.
 
 
 (scikit-learn)=
-## scikit-learn
+### scikit-learn
 
-Using [pandas] and [scikit-learn] to run a regression analysis within a [Jupyter Notebook].
+Using [pandas] and [scikit-learn] to run a regression analysis within a
+[Jupyter Notebook].
 
 - [Machine Learning and CrateDB: An introduction]
 - [Machine Learning and CrateDB: Getting Started With Jupyter]
 - [Machine Learning and CrateDB: Experiment Design & Linear Regression]
 
 
 (tensorflow)=
-## TensorFlow
+### TensorFlow
 
 - {doc}`./tensorflow`
 
 
+## LLMs / RAG
+
+One of the most powerful applications enabled by LLMs is sophisticated
+question-answering (Q&A) chatbots.
+These are applications that can answer questions about specific sources
+of information, using a technique known as Retrieval Augmented Generation,
+or RAG. RAG is a technique for augmenting LLM knowledge with additional data.
+
+
+(langchain)=
+### LangChain
+
+Tutorials and Notebooks about using [LangChain] together with CrateDB.
+LangChain has a number of components designed to help build Q&A applications,
+and RAG applications more generally.
+This feature uses CrateDB's [](#vector-store) implementation.
+
+- [LangChain and CrateDB: Code Examples]
+
+- CrateDB's `FLOAT_VECTOR` type and its `KNN_MATCH` function can be used for storing and
+  retrieving embeddings, and for conducting similarity searches.
+
+  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/vector_search.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/vector_search.ipynb) [![Launch Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/crate/cratedb-examples/main?labpath=topic%2Fmachine-learning%2Fllm-langchain%2Fvector_search.ipynb)
+
+- Database tables in CrateDB can be used as a source provider for LangChain documents.
+
+  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/document_loader.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/document_loader.ipynb) [![Launch Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/crate/cratedb-examples/main?labpath=topic%2Fmachine-learning%2Fllm-langchain%2Fdocument_loader.ipynb)
+
+- CrateDB supports managing LangChain's conversation history.
+
+  [![Open on GitHub](https://img.shields.io/badge/Open%20on-GitHub-lightgray?logo=GitHub)](https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/conversational_memory.ipynb) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/llm-langchain/conversational_memory.ipynb) [![Launch Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/crate/cratedb-examples/main?labpath=topic%2Fmachine-learning%2Fllm-langchain%2Fconversational_memory.ipynb)
+
+- What can you build with LangChain?
+
+  - [LangChain: Retrieval augmented generation]
+  - [LangChain: Analyzing structured data]
+  - [LangChain: Chatbots]
+
+
+
+(mlops)=
+## ML Operations
+Blubb.
+
+
+(vector-store)=
+## Vector Store
+Blubb.
+
+
+## More Information
+
+CrateDB provides a rich data model including container-, geospatial-, and
+vector-data types, and capabilities for full-text search.
+
+
 
 ```{toctree}
 :hidden:
@@ -89,7 +198,6 @@ tensorflow
 
 
 [AutoML with PyCaret and CrateDB]: https://github.com/crate/cratedb-examples/tree/main/topic/machine-learning/automl
-[Introduction to Time Series Modeling using Machine Learning]: https://cratedb.com/blog/introduction-to-time-series-modeling-with-cratedb-machine-learning-time-series-data
 [Jupyter Notebook]: https://jupyter.org/
 [LangChain]: https://python.langchain.com/
 [LangChain: Analyzing structured data]: https://python.langchain.com/docs/use_cases/qa_structured/sql
@@ -101,6 +209,11 @@ tensorflow
 [Machine Learning and CrateDB: Experiment Design & Linear Regression]: https://cratedb.com/blog/machine-learning-and-cratedb-part-three-experiment-design-and-linear-regression
 [MLflow]: https://mlflow.org/
 [MLflow and CrateDB]: https://github.com/crate/cratedb-examples/tree/main/topic/machine-learning/mlops-mlflow
+[MLOps]: https://en.wikipedia.org/wiki/MLOps
 [pandas]: https://pandas.pydata.org/
 [PyCaret]: https://www.pycaret.org
 [scikit-learn]: https://scikit-learn.org/
+[Time Series Modeling using Machine Learning]: https://cratedb.com/blog/introduction-to-time-series-modeling-with-cratedb-machine-learning-time-series-data
+[tracking-merlion-colab]: https://colab.research.google.com/github/crate/cratedb-examples/blob/main/topic/machine-learning/mlops-mlflow/tracking_merlion.ipynb
+[tracking-merlion-github]: https://github.com/crate/cratedb-examples/blob/main/topic/machine-learning/mlops-mlflow/tracking_merlion.ipynb
+[Vector database]: https://en.wikipedia.org/wiki/Vector_database