diff --git a/docs/web/agent-branch-experiments.mdx b/docs/web/agent-branch-experiments.mdx index 59bcf689b..3f4f1cbfa 100644 --- a/docs/web/agent-branch-experiments.mdx +++ b/docs/web/agent-branch-experiments.mdx @@ -1,6 +1,6 @@ --- title: "Run experiments on branches" -sidebarTitle: "Run experiments on branches" +sidebarTitle: "Branch Experiments" description: "Use LanceDB branches to isolate agent-driven experiments from main, evaluate them on a fixed test set, and promote only the winner." icon: "flask" keywords: ["AI agents", "branches", "experiments", "embeddings", "evaluation"] diff --git a/docs/web/build-with-ai-agents.mdx b/docs/web/build-with-ai-agents.mdx index 82964009a..808862c36 100644 --- a/docs/web/build-with-ai-agents.mdx +++ b/docs/web/build-with-ai-agents.mdx @@ -1,6 +1,6 @@ --- title: "Tutorial: Use the LanceDB agent plugin" -sidebarTitle: "LanceDB agent plugin" +sidebarTitle: "Agent Plugin" description: "Install the LanceDB plugin and use an AI coding agent to quickly build a multimodal ingestion pipeline." icon: "robot" keywords: ["AI agents", "agent plugins", "multimodal", "Pydantic", "branches", "embeddings"] diff --git a/docs/web/docs.json b/docs/web/docs.json index 53473f5a6..3c15ae601 100644 --- a/docs/web/docs.json +++ b/docs/web/docs.json @@ -308,48 +308,45 @@ ] }, { - "tab": "Tutorials and Use Cases", + "tab": "Use Cases", "groups": [ { - "group": "Tutorials", + "group": "General", "pages": [ "tutorials/index", - { - "group": "Search", - "expanded": true, - "pages": [ - "tutorials/search/index", - "tutorials/search/multivector-needle-in-a-haystack" - ] - }, - { - "group": "RAG & Agents", - "expanded": true, - "pages": [ - "tutorials/agents/index", - "tutorials/agents/nvidia-rag-blueprint/index", - "tutorials/agents/time-travel-rag/index", - "tutorials/agents/multimodal-agent/index" - ] - }, - "tutorials/feature-engineering/index", + "build-with-ai-agents" + ] + }, + { + "group": "Search", + "pages": [ + "tutorials/search/multivector-needle-in-a-haystack", + "tutorials/search/index" + ] + }, + { + "group": "RAG", + "pages": [ + "tutorials/agents/nvidia-rag-blueprint/index", + "tutorials/agents/time-travel-rag/index", + "tutorials/agents/multimodal-agent/index", + "tutorials/agents/index" + ] + }, + { + "group": "Feature Engineering", + "pages": [ + "agent-branch-experiments", + "tutorials/feature-engineering/index" + ] + }, + { + "group": "Training", + "pages": [ "training/object-detection", "training/vlm-finetuning" ] }, - { - "group": "AI Agents", - "pages": [ - "build-with-ai-agents", - "agent-branch-experiments" - ] - }, - { - "group": "Robotics", - "pages": [ - "integrations/lerobotdataset" - ] - }, { "group": "World Models", "pages": [ diff --git a/docs/web/training/object-detection.mdx b/docs/web/training/object-detection.mdx index 7704190ba..c7bd63686 100644 --- a/docs/web/training/object-detection.mdx +++ b/docs/web/training/object-detection.mdx @@ -1,6 +1,6 @@ --- title: "Object Detection for AV Perception" -sidebarTitle: "Example: Object Detection" +sidebarTitle: "Object Detection" description: End-to-end fine-tuning of a Faster R-CNN object detector on curated dashcam slices, using LanceDB as the data backbone from raw frames to checkpoints. icon: car --- diff --git a/docs/web/training/vlm-finetuning.mdx b/docs/web/training/vlm-finetuning.mdx index c0b38569c..89c385328 100644 --- a/docs/web/training/vlm-finetuning.mdx +++ b/docs/web/training/vlm-finetuning.mdx @@ -1,6 +1,6 @@ --- title: "Fine-tuning a VLM on TextVQA" -sidebarTitle: "Example: VLM finetuning" +sidebarTitle: "VLM Fine-tuning" description: End-to-end fine-tuning of Qwen2.5-VL on a curated TextVQA slice, using LanceDB and Geneva to materialize expensive vision-language features once and train from cached columns. icon: image --- diff --git a/docs/web/tutorials/agents/index.mdx b/docs/web/tutorials/agents/index.mdx index 448e78130..6738c06a8 100644 --- a/docs/web/tutorials/agents/index.mdx +++ b/docs/web/tutorials/agents/index.mdx @@ -1,7 +1,7 @@ --- -title: "RAG and Agents" -sidebarTitle: "Notebooks" -description: "Explore a variety of RAG (Retrieval-Augmented Generation) and agent applications built with LanceDB." +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) diff --git a/docs/web/tutorials/feature-engineering/index.mdx b/docs/web/tutorials/feature-engineering/index.mdx index 2576dd026..f9e5bb526 100644 --- a/docs/web/tutorials/feature-engineering/index.mdx +++ b/docs/web/tutorials/feature-engineering/index.mdx @@ -1,7 +1,7 @@ --- -title: "Feature Engineering" -sidebarTitle: "Feature Engineering" -description: "Learn how to build features for your data in LanceDB." +title: "More feature engineering examples" +sidebarTitle: "More Examples" +description: "Notebooks covering derived features and materialized views." layout: wide --- diff --git a/docs/web/tutorials/index.mdx b/docs/web/tutorials/index.mdx index ec25dc003..c22c301c1 100644 --- a/docs/web/tutorials/index.mdx +++ b/docs/web/tutorials/index.mdx @@ -1,23 +1,27 @@ --- -title: "Tutorials" +title: "Use cases" sidebarTitle: "Overview" -description: "Step-by-step tutorials for building applications with LanceDB" +description: "Worked examples of building with LanceDB, by what you are building." --- -Explore tutorials organized by use case: +Each page here is one worked example, grouped by what it builds. The +documentation explains how a feature works; these show it doing something. -| Tutorial | Description | +| | | |:---------|:------------| -| [Search & advanced retrieval](/tutorials/search/) | Learn how to perform vector search and use advanced retrieval techniques. | -| [Agents](/tutorials/agents/) | Build Retrieval-Augmented Generation (RAG) applications and agents with LanceDB. | -| [Working with tables in LanceDB](/tables/) | Learn the basics of working with tables in LanceDB: creation, ingestion and schema evolution. | +| [Search](/tutorials/search/multivector-needle-in-a-haystack) | Vector, multi-vector, hybrid and full-text retrieval. | +| [RAG](/tutorials/agents/nvidia-rag-blueprint/) | Retrieval-augmented generation and agent applications. | +| [Feature engineering](/tutorials/feature-engineering/) | Deriving columns, materialized views, and experimenting on branches. | +| [Training](/training/object-detection) | Curating data and training models directly on a table. | + +Each category also has a **More examples** page collecting runnable notebooks +that live in the recipes repository rather than here. ## Recipes {#recipes} -If you're looking for ideas and hands-on code examples, we've worked on a collection of practical -projects in the repository linked below. +If you are looking for ideas and hands-on code, the repository below collects +practical projects beyond the ones documented here. -Check out past code examples and tutorials [here](https://github.com/lancedb/vectordb-recipes) -on GitHub. +Past code examples and tutorials on GitHub. diff --git a/docs/web/tutorials/search/index.mdx b/docs/web/tutorials/search/index.mdx index 035ab38c5..cfbb168c9 100644 --- a/docs/web/tutorials/search/index.mdx +++ b/docs/web/tutorials/search/index.mdx @@ -1,7 +1,7 @@ --- -title: "Search Tutorials" -sidebarTitle: "Overview" -description: "Learn how vector, full-text and hybrid search work in LanceDB." +title: "More search examples" +sidebarTitle: "More Examples" +description: "Notebooks covering hybrid search, multi-vector retrieval, video search and more." layout: wide --- diff --git a/docs/web/tutorials/search/multivector-needle-in-a-haystack.mdx b/docs/web/tutorials/search/multivector-needle-in-a-haystack.mdx index 7a030ae34..ba5cefe35 100644 --- a/docs/web/tutorials/search/multivector-needle-in-a-haystack.mdx +++ b/docs/web/tutorials/search/multivector-needle-in-a-haystack.mdx @@ -1,6 +1,6 @@ --- title: "Finding the Needle in a Haystack: Comparing Multi-vector Search Strategies" -sidebarTitle: "Multi-vector search: Needle in a Haystack" +sidebarTitle: "Needle in a Haystack" description: "Tutorial on token-level retrieval with LanceDB multivector search." ---