Update notebooks, docs

Co-authored-by: Saavrm26 <[email protected]>

docs/hr/content/docs/data_integrations/sql.md

@@ -83,22 +83,26 @@ db.execute(
 ... the first query above is equivalent to:
 
 ```python
-db.execute(
-    'SELECT img FROM my-table WHERE rating > 3 LIMIT 5;'
-)
+from superduperdb.backends.ibis.query import RawSQL
+
+db.execute(RawSQL('SELECT img FROM my-table WHERE rating > 3 LIMIT 5;'))
 ```
 
 ... the second will be equivalent to:
 
 ```python
-db.execute(
+from superduperdb.backends.ibis.query import RawSQL
+
+raw_sql = RawSQL(
     '''
     SELECT img FROM my-table 
     LIKE text = 'something like this'
     WHERE rating > 3
     LIMIT 5;
     '''
-)
+    )
+
+db.execute(raw_sql)
 ```
 
 ## Updating data

docs/hr/content/use_cases/question-answering/chat_with_your_database.md

@@ -6,6 +6,8 @@ Imagine chatting with your database using just a few lines of code. Sounds unbel
 
 Here is the behemoth 10M dataset: [FREE COMPANY DATASET](https://app.snowflake.com/marketplace/listing/GZSTZRRVYL2/people-data-labs-free-company-dataset)
 
+Here is the [Google Colab Notebook](https://colab.research.google.com/drive/1YXzAuuQdqkWEQKchglxUuAMzNTKLu5rC#scrollTo=0Zf4Unc_fNBp) for you to quickstart!
+
 Chatting with this type of massive dataset using the standard RAG pipeline is next to impossible due to the cost and scale. However, with SuperDuperDB, you can achieve the same functionality with just a few lines of code.
 
 You can control the low level code while enjoying writing the high level code! So that, you can increase the capacity of it! Whether you're using `Snowflake` or `any other SQL dataset`, we've got your back.
@@ -25,7 +27,7 @@ Let's bring AI into your database! 🚀
 
 ```python
 # Only one dependency
-# %pip install superduperdb
+# !pip install superduperdb openai
 
 # Import SuperDuperDB and connect your database
 from superduperdb import superduper

docs/hr/docusaurus.config.js

@@ -335,8 +335,7 @@ const config = {
       ],
       announcementBar: {
         id: 'support_us',
-        content:
-          '🔮 We are officially launching SuperDuperDB with the release of v0.1 on December 5th on Github! 🔮',
+        content: '🔮 We officially released v0.1 on Github! 🔮',
         backgroundColor: '#7628f8',
         textColor: '#fff',
         isCloseable: true,

examples/chat_with_your_database.ipynb

@@ -12,6 +12,8 @@
     "\n",
     "Here is the behemoth 10M dataset: [FREE COMPANY DATASET](https://app.snowflake.com/marketplace/listing/GZSTZRRVYL2/people-data-labs-free-company-dataset)\n",
     "\n",
+    "Here is the [Google Colab Notebook](https://colab.research.google.com/drive/1YXzAuuQdqkWEQKchglxUuAMzNTKLu5rC#scrollTo=0Zf4Unc_fNBp) for you to quickstart!\n",
+    "\n",
     "Chatting with this type of massive dataset using the standard RAG pipeline is next to impossible due to the cost and scale. However, with SuperDuperDB, you can achieve the same functionality with just a few lines of code.\n",
     "\n",
     "You can control the low level code while enjoying writing the high level code! So that, you can increase the capacity of it! Whether you're using `Snowflake` or `any other SQL dataset`, we've got your back.\n",
@@ -36,7 +38,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# %pip install superduperdb"
+    "# !pip install git+https://github.com/SuperDuperDB/superduperdb.git@66b457eb99f5ad9b88d10bb46f8c2d62ddbc1a1d "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install openai"
    ]
   },
   {
@@ -346,13 +357,22 @@
     "# If you see no result, Run this codeblock multiple times to make the gpt-3.5-turbo work better and change your query as well. Idea: start with a simple query. Then make it gradually complex.\n",
     "\n",
     "table_name = \"FREECOMPANYDATASET\"\n",
-    "query = \"Find me some company in germany in berlin in dortmund in automotive industry. Keep all in lower case\"\n",
+    "query = \"Find me some company in germany in berlin. Keep all in lower case.\"\n",
     "\n",
     "result = chat_with_your_database(table_name, query)\n",
     "\n",
     "result"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Let's explain the table\n",
+    "\n",
+    "Table doen't make sense to you, let LLM explain the table above"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 42,
@@ -396,7 +416,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Let's generate result on the fly by model chaining\n",
+    "### Let's generate result on the fly by prompt chaining\n",
     "\n",
     "Now you can do model-chaining as well, if you only care about the explanations. Here we found from the dataset about the company "
    ]