From daedf1396bbb48a7fd5c0c62ac7cff306b5a7bcf Mon Sep 17 00:00:00 2001
From: Jai <jaichopra@gmail.com>
Date: Fri, 2 Jun 2023 16:08:56 -0700
Subject: [PATCH] =?UTF-8?q?update=20references=20to=20end=20to=20end=20exa?=
 =?UTF-8?q?mples,=20use=20s3=20for=20langchain=20exampl=E2=80=A6=20(#133)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                            |  2 +-
 docs/mkdocs.yml                      |  1 +
 docs/src/index.md                    |  7 ++++---
 docs/src/notebooks/code_qa_bot.ipynb | 24 +++++++++++++++++++++---
 python/pyproject.toml                |  2 +-
 5 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 26ff321b..bf0f2ad1 100644
--- a/README.md
+++ b/README.md
@@ -29,7 +29,7 @@ The key features of LanceDB include:
 
 * Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lanecdb.html), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
 
-LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/eto-ai/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
+LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/lancedb/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
 
 ## Quick Start
 
diff --git a/docs/mkdocs.yml b/docs/mkdocs.yml
index bfa62f7a..783e9061 100644
--- a/docs/mkdocs.yml
+++ b/docs/mkdocs.yml
@@ -44,6 +44,7 @@ nav:
 - Python examples:
   - YouTube Transcript Search using OpenAI: notebooks/youtube_transcript_search.ipynb
   - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+  - Multimodal search using OpenAI and CLIP: notebooks/multimodal_search.ipynb
 - API references:
   - Python API: python/python.md
   - Javascript API: javascript/modules.md
diff --git a/docs/src/index.md b/docs/src/index.md
index 7d720e38..669f95e2 100644
--- a/docs/src/index.md
+++ b/docs/src/index.md
@@ -14,7 +14,7 @@ The key features of LanceDB include:
 
 * Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lanecdb.html), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
 
-LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/eto-ai/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
+LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/lancedb/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
 
 ## Quick Start
 
@@ -50,11 +50,12 @@ LanceDB's core is written in Rust 🦀 and is built using <a href="https://githu
       const results = await table.search([100, 100]).limit(2).execute();
       ```
 
-## Complete Demos
+## Complete Demos (Python)
 
 We will be adding completed demo apps built using LanceDB.
 - [YouTube Transcript Search](notebooks/youtube_transcript_search.ipynb)
-
+- [Documentation QA Bot using LangChain](notebooks/code_qa_bot.ipynb)
+- [Multimodal search using OpenAI and CLIP](notebooks/multimodal_search.ipynb)
 
 ## Documentation Quick Links
 * [`Basic Operations`](basic.md) - basic functionality of LanceDB.
diff --git a/docs/src/notebooks/code_qa_bot.ipynb b/docs/src/notebooks/code_qa_bot.ipynb
index fe7b211a..311a6857 100644
--- a/docs/src/notebooks/code_qa_bot.ipynb
+++ b/docs/src/notebooks/code_qa_bot.ipynb
@@ -72,6 +72,8 @@
     "import lancedb\n",
     "import re\n",
     "import pickle\n",
+    "import requests\n",
+    "import zipfile\n",
     "from pathlib import Path\n",
     "\n",
     "from langchain.document_loaders import UnstructuredHTMLLoader\n",
@@ -85,10 +87,25 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "6ccf9b2b",
+   "id": "56cc6d50",
    "metadata": {},
    "source": [
-    "You can download the Pandas documentation from https://pandas.pydata.org/docs/. To make sure we're not littering our repo with docs, we won't include it in the LanceDB repo, so download this and store it locally first."
+    "To make this easier, we've downloaded Pandas documentation and stored the raw HTML files for you to download. We'll download them and then use LangChain's HTML document readers to parse them and store them in LanceDB as a vector store, along with relevant metadata."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7da77e75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pandas_docs = requests.get(\"https://eto-public.s3.us-west-2.amazonaws.com/datasets/pandas_docs/pandas.documentation.zip\")\n",
+    "with open('/tmp/pandas.documentation.zip', 'wb') as f:\n",
+    "    f.write(pandas_docs.content)\n",
+    "\n",
+    "file = zipfile.ZipFile(\"/tmp/pandas.documentation.zip\")\n",
+    "file.extractall(path=\"/tmp/pandas_docs\")"
    ]
   },
   {
@@ -137,7 +154,8 @@
     "docs = []\n",
     "\n",
     "if not docs_path.exists():\n",
-    "    for p in Path(\"./pandas.documentation\").rglob(\"*.html\"):\n",
+    "    for p in Path(\"/tmp/pandas_docs/pandas.documentation\").rglob(\"*.html\"):\n",
+    "        print(p)\n",
     "        if p.is_dir():\n",
     "            continue\n",
     "        loader = UnstructuredHTMLLoader(p)\n",
diff --git a/python/pyproject.toml b/python/pyproject.toml
index 95db43d7..643fa1b5 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -33,7 +33,7 @@ classifiers = [
 ]
 
 [project.urls]
-repository = "https://github.com/eto-ai/lancedb"
+repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
 tests = [