docs: list every use case in the sidebar

The three gallery pages held thirteen examples as rows in a table, reachable
only by opening the gallery first. Each is now its own page, so the sidebar
lists them and search finds them by name.

A page for an example that lives in vectordb-recipes says so and links to the
notebook and its source, rather than pretending the tutorial is here.

Overview moves above the groups -- the tab uses pages rather than groups, which
is what allows an entry to sit outside every group. Stable World Model joins
Training, since that is what it is doing. The agent plugin page is now Using
LanceDB Agent Skill.

Mintlify cannot link outward from a sidebar: an {anchor, href} entry is ignored
and a bare URL renders with its scheme mangled to a single slash, so a real page
per example is the only way to list them.

docs/web/tutorials/agents/agentic-rag.mdx

@@ -0,0 +1,23 @@
+---
+title: "Agentic RAG"
+sidebarTitle: "Agentic RAG"
+description: "Several agents collaborating to retrieve and answer."
+---
+
+Builds a RAG system where multiple agents collaborate -- retrieving
+information, checking it, and generating answers -- rather than a single
+retrieve-then-generate pass.
+
+<Note>
+This example is a runnable notebook in the
+[vectordb-recipes](https://github.com/lancedb/vectordb-recipes) repository rather than a page here.
+</Note>
+
+<CardGroup cols={2}>
+  <Card title="Open in Colab" icon="google" href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb">
+    Run it end to end in the browser.
+  </Card>
+  <Card title="View on GitHub" icon="github" href="https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Agentic_RAG">
+    Read the source.
+  </Card>
+</CardGroup>

docs/web/tutorials/agents/contextual-rag.mdx

@@ -0,0 +1,24 @@
+---
+title: "Contextual RAG"
+sidebarTitle: "Contextual RAG"
+description: "Prepend LLM-generated context to each chunk before embedding it."
+---
+
+Addresses the "lost in the middle" problem in retrieval. An LLM generates a
+succinct piece of context for each document chunk, which is prepended to the
+chunk before embedding -- so a chunk carries enough surrounding meaning to be
+retrieved for the right queries.
+
+<Note>
+This example is a runnable notebook in the
+[vectordb-recipes](https://github.com/lancedb/vectordb-recipes) repository rather than a page here.
+</Note>
+
+<CardGroup cols={2}>
+  <Card title="Open in Colab" icon="google" href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Contextual-RAG/Anthropic_Contextual_RAG.ipynb">
+    Run it end to end in the browser.
+  </Card>
+  <Card title="View on GitHub" icon="github" href="https://github.com/lancedb/vectordb-recipes/tree/main/examples/Contextual-RAG">
+    Read the source.
+  </Card>
+</CardGroup>

docs/web/tutorials/agents/hyde.mdx

@@ -0,0 +1,24 @@
+---
+title: "HyDE: hypothetical document embeddings"
+sidebarTitle: "HyDE"
+description: "Generate a hypothetical answer, then retrieve documents similar to it."
+---
+
+An LLM writes a hypothetical document answering the query, and that document --
+not the query -- is embedded and used for retrieval. It works because a
+plausible answer sits nearer the real answers in embedding space than a question
+does.
+
+<Note>
+This example is a runnable notebook in the
+[vectordb-recipes](https://github.com/lancedb/vectordb-recipes) repository rather than a page here.
+</Note>
+
+<CardGroup cols={2}>
+  <Card title="Open in Colab" icon="google" href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advance-RAG-with-HyDE/main.ipynb">
+    Run it end to end in the browser.
+  </Card>
+  <Card title="View on GitHub" icon="github" href="https://github.com/lancedb/vectordb-recipes/tree/main/examples/Advance-RAG-with-HyDE">
+    Read the source.
+  </Card>
+</CardGroup>

docs/web/tutorials/agents/index.mdx

@@ -1,17 +0,0 @@
----
-title: "More RAG examples"
-sidebarTitle: "More Examples"
-description: "Notebooks covering contextual RAG, HyDE, late chunking, agentic RAG and more."
----
-
-The table below lists example notebooks we've prepared for a variety of RAG (Retrieval-Augmented Generation)
-and agent applications built with LanceDB.
-
-| Project | Description |
-|:----------|:------------|
-| **Contextual RAG** <br /> <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Contextual-RAG/Anthropic_Contextual_RAG.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>[View on GitHub](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Contextual-RAG) | Improves retrieval by combatting the "lost in the middle" problem. This technique uses an LLM to generate succinct context for each document chunk, then prepends that context to the chunk before embedding, leading to more accurate retrieval. |
-| **NVIDIA RAG Blueprint with LanceDB** <br /> [Read the tutorial](/tutorials/agents/nvidia-rag-blueprint/)<br />[View on GitHub](https://github.com/lancedb/vectordb-recipes/tree/main/examples/nvidia-rag-blueprint-lancedb) | Shows how to use LanceDB as the retrieval layer for NVIDIA RAG Blueprint with a Docker-first, retrieval-only integration path that includes hybrid search and pluggable rerankers. |
-| **Matryoshka Embeddings** <br /> <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex/main.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>[View on GitHub](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex) | Demonstrates a RAG pipeline using Matryoshka Embeddings with LanceDB and LlamaIndex. This method allows for efficient storage and retrieval of nested, variable-sized embeddings. |
-| **HyDE (Hypothetical Document Embeddings)** <br /> <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advance-RAG-with-HyDE/main.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>[View on GitHub](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Advance-RAG-with-HyDE) | An advanced RAG technique that uses an LLM to generate a "hypothetical" document in response to a query. This hypothetical document is then used to retrieve actual, similar documents, improving relevance. |
-| **Late Chunking** <br /> <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advanced_RAG_Late_Chunking/Late_Chunking_(Chunked_Pooling).ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>[View on GitHub](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Advanced_RAG_Late_Chunking) | An advanced RAG method where documents are retrieved first, and then chunking is performed on the retrieved documents just before synthesis. This helps maintain context that might be lost with pre-chunking. |
-| **Agentic RAG** <br /> <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>[View on GitHub](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Agentic_RAG) | This tutorial demonstrates how to build a RAG system where multiple AI agents collaborate to retrieve information and generate answers, leading to more robust and intelligent applications. |

docs/web/tutorials/agents/late-chunking.mdx

@@ -0,0 +1,23 @@
+---
+title: "Late chunking"
+sidebarTitle: "Late Chunking"
+description: "Retrieve whole documents first, chunk them afterwards."
+---
+
+Inverts the usual order: documents are retrieved first and chunked just before
+synthesis. Chunking late preserves context that pre-chunking discards, since a
+chunk is cut with knowledge of the query it is answering.
+
+<Note>
+This example is a runnable notebook in the
+[vectordb-recipes](https://github.com/lancedb/vectordb-recipes) repository rather than a page here.
+</Note>
+
+<CardGroup cols={2}>
+  <Card title="Open in Colab" icon="google" href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advanced_RAG_Late_Chunking/Late_Chunking_(Chunked_Pooling).ipynb">
+    Run it end to end in the browser.
+  </Card>
+  <Card title="View on GitHub" icon="github" href="https://github.com/lancedb/vectordb-recipes/tree/main/examples/Advanced_RAG_Late_Chunking">
+    Read the source.
+  </Card>
+</CardGroup>

docs/web/tutorials/agents/matryoshka-embeddings.mdx

@@ -0,0 +1,23 @@
+---
+title: "Matryoshka embeddings"
+sidebarTitle: "Matryoshka Embeddings"
+description: "Nested, variable-size embeddings with LanceDB and LlamaIndex."
+---
+
+A RAG pipeline built on Matryoshka embeddings with LlamaIndex. The embeddings
+nest, so one model serves several dimensionalities -- store the full vector and
+retrieve with a truncated one when the cheaper comparison is good enough.
+
+<Note>
+This example is a runnable notebook in the
+[vectordb-recipes](https://github.com/lancedb/vectordb-recipes) repository rather than a page here.
+</Note>
+
+<CardGroup cols={2}>
+  <Card title="Open in Colab" icon="google" href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex/main.ipynb">
+    Run it end to end in the browser.
+  </Card>
+  <Card title="View on GitHub" icon="github" href="https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex">
+    Read the source.
+  </Card>
+</CardGroup>