diff --git a/docs/mkdocs.yml b/docs/mkdocs.yml
index b703e389..feb2a318 100644
--- a/docs/mkdocs.yml
+++ b/docs/mkdocs.yml
@@ -141,12 +141,15 @@ nav:
- Overview: examples/index.md
- π Python:
- Overview: examples/examples_python.md
- - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
- - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
- - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
- - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
- - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
- - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+ - Build From Scratch: examples/python_examples/build_from_scratch.md
+ - Multimodal: examples/python_examples/multimodal.md
+ - Rag: examples/python_examples/rag.md
+ - Miscellaneous:
+ - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
+ - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+ - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+ - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+ - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
- πΎ JavaScript:
- Overview: examples/examples_js.md
- Serverless Website Chatbot: examples/serverless_website_chatbot.md
@@ -221,14 +224,24 @@ nav:
- PromptTools: integrations/prompttools.md
- Examples:
- examples/index.md
- - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
- - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
- - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
- - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
- - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
- - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
- - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
- - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+ - π Python:
+ - Overview: examples/examples_python.md
+ - Build From Scratch: examples/python_examples/build_from_scratch.md
+ - Multimodal: examples/python_examples/multimodal.md
+ - Rag: examples/python_examples/rag.md
+ - Miscellaneous:
+ - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
+ - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+ - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+ - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+ - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+ - πΎ JavaScript:
+ - Overview: examples/examples_js.md
+ - Serverless Website Chatbot: examples/serverless_website_chatbot.md
+ - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+ - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+ - π¦ Rust:
+ - Overview: examples/examples_rust.md
- API reference:
- Overview: api_reference.md
- Python: python/python.md
diff --git a/docs/src/assets/colab.svg b/docs/src/assets/colab.svg
new file mode 100644
index 00000000..e5830d53
--- /dev/null
+++ b/docs/src/assets/colab.svg
@@ -0,0 +1 @@
+
diff --git a/docs/src/assets/ghost.svg b/docs/src/assets/ghost.svg
new file mode 100644
index 00000000..c8118157
--- /dev/null
+++ b/docs/src/assets/ghost.svg
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/docs/src/assets/github.svg b/docs/src/assets/github.svg
new file mode 100644
index 00000000..d5704c13
--- /dev/null
+++ b/docs/src/assets/github.svg
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/docs/src/assets/python.svg b/docs/src/assets/python.svg
new file mode 100644
index 00000000..13b39348
--- /dev/null
+++ b/docs/src/assets/python.svg
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/docs/src/examples/python_examples/build_from_scratch.md b/docs/src/examples/python_examples/build_from_scratch.md
new file mode 100644
index 00000000..f7469726
--- /dev/null
+++ b/docs/src/examples/python_examples/build_from_scratch.md
@@ -0,0 +1,13 @@
+# Build from Scratch with LanceDB π
+
+Start building your GenAI applications from the ground up using LanceDB's efficient vector-based document retrieval capabilities! π
+
+#### Get Started in Minutes β±οΈ
+
+These examples provide a solid foundation for building your own GenAI applications using LanceDB. Jump from idea to proof of concept quickly with applied examples. Get started and see what you can create! π»
+
+| **Build From Scratch** | **Description** | **Links** |
+|:-------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| **Build RAG from Scratchππ»** | π Create a **Retrieval-Augmented Generation** (RAG) model from scratch using LanceDB. | [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/RAG-from-Scratch) []() |
+| **Local RAG from Scratch with Llama3π₯π‘** | π« Build a local RAG model using **Llama3** and **LanceDB** for fast and efficient text generation. | [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Local-RAG-from-Scratch) [](https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Local-RAG-from-Scratch/rag.py) |
+| **Multi-Head RAG from Scratchππ»** | π€― Develop a **Multi-Head RAG model** from scratch, enabling generation of text based on multiple documents. | [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Multi-Head-RAG-from-Scratch) [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Multi-Head-RAG-from-Scratch) |
diff --git a/docs/src/examples/python_examples/multimodal.md b/docs/src/examples/python_examples/multimodal.md
new file mode 100644
index 00000000..6f1de8ed
--- /dev/null
+++ b/docs/src/examples/python_examples/multimodal.md
@@ -0,0 +1,28 @@
+# Multimodal Search with LanceDB ππ‘
+
+Experience the future of search with LanceDB's multimodal capabilities. Combine text and image queries to find the most relevant results in your corpus and unlock new possibilities! ππ‘
+
+#### Explore the Future of Search π
+
+Unlock the power of multimodal search with LanceDB, enabling efficient vector-based retrieval of text and image data! ππ»
+
+
+
+| **Multimodal** | **Description** | **Links** |
+|:----------------|:-----------------|:-----------|
+| **Multimodal CLIP: DiffusionDB ππ₯** | Revolutionize search with Multimodal CLIP and DiffusionDB, combining text and image understanding for a new dimension of discovery! π | [][Clip_diffusionDB_github] [][Clip_diffusionDB_colab] [][Clip_diffusionDB_python] [][Clip_diffusionDB_ghost] |
+| **Multimodal CLIP: Youtube Videos πΉπ** | Search Youtube videos using Multimodal CLIP, finding relevant content with ease and accuracy! π― | [][Clip_youtube_github] [][Clip_youtube_colab] [][Clip_youtube_python] [][Clip_youtube_python] |
+| **Multimodal Image + Text Search πΈπ** | Discover relevant documents and images with a single query, using LanceDB's multimodal search capabilities to bridge the gap between text and visuals! π | [](https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_search) [](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_search/main.ipynb) [](https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_search/main.py) [](https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/) |
+| **Cambrian-1: Vision-Centric Image Exploration ππ** | Dive into vision-centric exploration of images with Cambrian-1, powered by LanceDB's multimodal search to uncover new insights! π | [](https://www.kaggle.com/code/prasantdixit/cambrian-1-vision-centric-exploration-of-images/) []() []() [](https://blog.lancedb.com/cambrian-1-vision-centric-exploration/) |
+
+
+[Clip_diffusionDB_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb
+[Clip_diffusionDB_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb/main.ipynb
+[Clip_diffusionDB_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb/main.py
+[Clip_diffusionDB_ghost]: https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/
+
+
+[Clip_youtube_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search
+[Clip_youtube_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.ipynb
+[Clip_youtube_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.py
+[Clip_youtube_ghost]: https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/
\ No newline at end of file
diff --git a/docs/src/examples/python_examples/rag.md b/docs/src/examples/python_examples/rag.md
new file mode 100644
index 00000000..c2c41d0c
--- /dev/null
+++ b/docs/src/examples/python_examples/rag.md
@@ -0,0 +1,85 @@
+
+**ππ‘ RAG: Revolutionize Information Retrieval with LanceDB π**
+====================================================================
+
+Unlock the full potential of Retrieval-Augmented Generation (RAG) with LanceDB, the ultimate solution for efficient vector-based information retrieval π. Input text queries and retrieve relevant documents with lightning-fast speed β‘οΈ and accuracy β . Generate comprehensive answers by combining retrieved information, uncovering new insights π and connections.
+
+### Experience the Future of Search π
+
+Experience the future of search with RAG, transforming information retrieval and answer generation. Apply RAG to various industries, streamlining processes π, saving time β°, and resources π°. Stay ahead of the curve with innovative technology π, powered by LanceDB. Discover the power of RAG with LanceDB and transform your industry with innovative solutions π‘.
+
+
+| **RAG** | **Description** | **Links** |
+|----------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|
+| **RAG with Matryoshka Embeddings and LlamaIndex** πͺπ | Utilize **Matryoshka embeddings** and **LlamaIndex** to improve the efficiency and accuracy of your RAG models. πβ¨ | [][matryoshka_github] [][matryoshka_colab] |
+| **Improve RAG with Re-ranking** ππ | Enhance your RAG applications by implementing **re-ranking strategies** for more relevant document retrieval. ππ | [][rag_reranking_github] [][rag_reranking_colab] [][rag_reranking_ghost] |
+| **Instruct-Multitask** π§ π― | Integrate the **Instruct Embedding Model** with LanceDB to streamline your embedding API, reducing redundant code and overhead. ππ | [][instruct_multitask_github] [][instruct_multitask_colab] [][instruct_multitask_python] [][instruct_multitask_ghost] |
+| **Improve RAG with HyDE** ππ | Use **Hypothetical Document Embeddings** for efficient, accurate, and unsupervised dense retrieval. ππ | [][hyde_github] [][hyde_colab] [][hyde_ghost] |
+| **Improve RAG with LOTR** π§ββοΈπ | Enhance RAG with **Lord of the Retriever (LOTR)** to address 'Lost in the Middle' challenges, especially in medical data. ππ | [][lotr_github] [][lotr_colab] [][lotr_ghost] |
+| **Advanced RAG: Parent Document Retriever** ππ | Use **Parent Document & Bigger Chunk Retriever** to maintain context and relevance when generating related content. π΅π | [][parent_doc_retriever_github] [][parent_doc_retriever_colab] [][parent_doc_retriever_ghost] |
+| **Corrective RAG with Langgraph** π§π | Enhance RAG reliability with **Corrective RAG (CRAG)** by self-reflecting and fact-checking for accurate and trustworthy results. β π |[][corrective_rag_github] [][corrective_rag_colab] [][corrective_rag_ghost] |
+| **Contextual Compression with RAG** ποΈπ§ | Apply **contextual compression techniques** to condense large documents while retaining essential information. πποΈ | [][compression_rag_github] [][compression_rag_colab] [][compression_rag_ghost] |
+| **Improve RAG with FLARE** π₯| Enable users to ask questions directly to academic papers, focusing on ArXiv papers, with Forward-Looking Active REtrieval augmented generation.ππ | [][flare_github] [][flare_colab] [][flare_ghost] |
+| **Query Expansion and Reranker** ππ | Enhance RAG with query expansion using Large Language Models and advanced **reranking methods** like Cross Encoders, ColBERT v2, and FlashRank for improved document retrieval precision and recall ππ | [][query_github] [][query_colab] |
+| **RAG Fusion** β‘π | Revolutionize search with RAG Fusion, utilizing the **RRF algorithm** to rerank documents based on user queries, and leveraging LanceDB and OPENAI Embeddings for efficient information retrieval β‘π | [][fusion_github] [][fusion_colab] |
+| **Agentic RAG** π€π | Unlock autonomous information retrieval with **Agentic RAG**, a framework of **intelligent agents** that collaborate to synthesize, summarize, and compare data across sources, enabling proactive and informed decision-making π€π | [][agentic_github] [][agentic_colab] |
+
+
+
+
+
+
+
+
+
+
+
+
+[matryoshka_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex
+[matryoshka_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex/RAG_with_MatryoshkaEmbedding_and_Llamaindex.ipynb
+
+[rag_reranking_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/RAG_Reranking
+[rag_reranking_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/RAG_Reranking/main.ipynb
+[rag_reranking_ghost]: https://blog.lancedb.com/simplest-method-to-improve-rag-pipeline-re-ranking-cf6eaec6d544
+
+
+[instruct_multitask_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/instruct-multitask
+[instruct_multitask_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/instruct-multitask/main.ipynb
+[instruct_multitask_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/instruct-multitask/main.py
+[instruct_multitask_ghost]: https://blog.lancedb.com/multitask-embedding-with-lancedb-be18ec397543
+
+[hyde_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Advance-RAG-with-HyDE
+[hyde_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advance-RAG-with-HyDE/main.ipynb
+[hyde_ghost]: https://blog.lancedb.com/advanced-rag-precise-zero-shot-dense-retrieval-with-hyde-0946c54dfdcb
+
+[lotr_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Advance_RAG_LOTR
+[lotr_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advance_RAG_LOTR/main.ipynb
+[lotr_ghost]: https://blog.lancedb.com/better-rag-with-lotr-lord-of-retriever-23c8336b9a35
+
+[parent_doc_retriever_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/parent_document_retriever
+[parent_doc_retriever_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/parent_document_retriever/main.ipynb
+[parent_doc_retriever_ghost]: https://blog.lancedb.com/modified-rag-parent-document-bigger-chunk-retriever-62b3d1e79bc6
+
+[corrective_rag_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Corrective-RAG-with_Langgraph
+[corrective_rag_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Corrective-RAG-with_Langgraph/CRAG_with_Langgraph.ipynb
+[corrective_rag_ghost]: https://blog.lancedb.com/implementing-corrective-rag-in-the-easiest-way-2/
+
+[compression_rag_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Contextual-Compression-with-RAG
+[compression_rag_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Contextual-Compression-with-RAG/main.ipynb
+[compression_rag_ghost]: https://blog.lancedb.com/enhance-rag-integrate-contextual-compression-and-filtering-for-precision-a29d4a810301/
+
+[flare_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/better-rag-FLAIR
+[flare_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/better-rag-FLAIR/main.ipynb
+[flare_ghost]: https://blog.lancedb.com/better-rag-with-active-retrieval-augmented-generation-flare-3b66646e2a9f/
+
+[query_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/QueryExpansion&Reranker
+[query_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/QueryExpansion&Reranker/main.ipynb
+
+
+[fusion_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/RAG_Fusion
+[fusion_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/RAG_Fusion/main.ipynb
+
+[agentic_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG
+[agentic_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb
+
+
diff --git a/docs/test/requirements.txt b/docs/test/requirements.txt
index 4bb793af..671940a5 100644
--- a/docs/test/requirements.txt
+++ b/docs/test/requirements.txt
@@ -5,4 +5,5 @@ pylance
duckdb
--extra-index-url https://download.pytorch.org/whl/cpu
torch
-polars
+polars>=0.19, <=1.3.0
+