From 4eee789dd37a474e9e83275c0978f99a90d9d23d Mon Sep 17 00:00:00 2001
From: Greg Richardson <greg.nmr@gmail.com>
Date: Fri, 22 Sep 2023 09:18:56 -0600
Subject: [PATCH] Docs: Using SupabaseVectorStore with existing documents 
 (#10907)

## Description
Adds additional docs on how to use `SupabaseVectorStore` with existing
data in your DB (vs inserting new documents each time).
---
 .../integrations/vectorstores/supabase.ipynb  | 91 ++++++++++++++-----
 1 file changed, 66 insertions(+), 25 deletions(-)

diff --git a/docs/extras/integrations/vectorstores/supabase.ipynb b/docs/extras/integrations/vectorstores/supabase.ipynb
index 9a5f583adb..961ac208da 100644
--- a/docs/extras/integrations/vectorstores/supabase.ipynb
+++ b/docs/extras/integrations/vectorstores/supabase.ipynb
@@ -92,7 +92,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "id": "19846a7b-99bc-47a7-8e1c-f13c2497f1ae",
    "metadata": {},
    "outputs": [],
@@ -105,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "c71c3901-d44b-4d09-92c5-3018628c28fa",
    "metadata": {},
    "outputs": [],
@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "id": "8b91ecfa-f61b-489a-a337-dff1f12f6ab2",
    "metadata": {},
    "outputs": [],
@@ -138,67 +138,108 @@
     "load_dotenv()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "924d4df5",
+   "metadata": {},
+   "source": [
+    "First we'll create a Supabase client and instantiate a OpenAI embeddings class."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 19,
    "id": "5ce44f7c",
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "from supabase.client import Client, create_client\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import SupabaseVectorStore\n",
     "\n",
     "supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
     "supabase_key = os.environ.get(\"SUPABASE_SERVICE_KEY\")\n",
-    "supabase: Client = create_client(supabase_url, supabase_key)"
+    "supabase: Client = create_client(supabase_url, supabase_key)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c707d4c",
+   "metadata": {},
+   "source": [
+    "Next we'll load and parse some data for our vector store (skip if you already have documents with embeddings stored in your DB)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 20,
    "id": "aac9563e",
    "metadata": {
     "tags": []
    },
    "outputs": [],
    "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import SupabaseVectorStore\n",
-    "from langchain.document_loaders import TextLoader"
+    "from langchain.document_loaders import TextLoader\n",
+    "\n",
+    "loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5abb9b93",
+   "metadata": {},
+   "source": [
+    "Insert the above documents into the database. Embeddings will automatically be generated for each document."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "a3c3999a",
+   "execution_count": 6,
+   "id": "efec97f8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.document_loaders import TextLoader\n",
     "\n",
-    "loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
-    "documents = loader.load()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "docs = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
+    "vector_store = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e169345d",
+   "metadata": {},
+   "source": [
+    "Alternatively if you already have documents with embeddings in your database, simply instantiate a new `SupabaseVectorStore` directly:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "efec97f8",
+   "execution_count": 10,
+   "id": "397e3e7d",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# We're using the default `documents` table here. You can modify this by passing in a `table_name` argument to the `from_documents` method.\n",
-    "vector_store = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase)"
+    "vector_store = SupabaseVectorStore(embedding=embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e28ce092",
+   "metadata": {},
+   "source": [
+    "Finally, test it out by performing a similarity search:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "5eabdb75",
    "metadata": {},
    "outputs": [],
@@ -209,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "4b172de8",
    "metadata": {},
    "outputs": [
@@ -431,7 +472,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,