From 7eba9375871e8fe72828ca811a8fc835de487bca Mon Sep 17 00:00:00 2001
From: Florents Tselai <florents.tselai@gmail.com>
Date: Sun, 23 Jun 2024 19:54:06 +0300
Subject: [PATCH] Examples

---
 README.md | 87 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 69 insertions(+), 18 deletions(-)

diff --git a/README.md b/README.md
index f496301..550939b 100644
--- a/README.md
+++ b/README.md
@@ -6,11 +6,11 @@
 
   <h1 align="center">tsellm</h1>
   <p align="center">
-  <strong>SQLite with LLM Superpowers</strong>
+  <strong>Interactive SQLite shell with LLM support</strong>
     <br> <br />
-    <a href="#how"><strong> How </strong></a> |
-    <a href="#installation"><strong> Installation </strong></a> |
     <a href="#usage"><strong> Usage </strong></a> |
+    <a href="#installation"><strong> Installation </strong></a> |
+    <a href="#how"><strong> How </strong></a> |
     <a href="#roadmap"><strong> Roadmap </strong></a> 
 
    </p>
@@ -20,34 +20,85 @@
 <a href="https://pypi.org/project/tsellm/"><img src="https://img.shields.io/pypi/v/tsellm?label=PyPI"></a>
 <a href="https://github.com/Florents-Tselai/tsellm/actions/workflows/test.yml?branch=mainline"><img src="https://github.com/Florents-Tselai/tsellm/actions/workflows/test.yml/badge.svg"></a>
 <a href="https://codecov.io/gh/Florents-Tselai/tsellm"><img src="https://codecov.io/gh/Florents-Tselai/tsellm/branch/main/graph/badge.svg"></a>  
-<a href="https://opensource.org/licenses/BSD license"><img src="https://img.shields.io/badge/BSD license.0-blue.svg"></a>
+<a href="https://opensource.org/licenses/BSD license"><img src="https://img.shields.io/badge/BSD license-blue.svg"></a>
 <a href="https://github.com/Florents-Tselai/tsellm/releases"><img src="https://img.shields.io/github/v/release/Florents-Tselai/tsellm?include_prereleases&label=changelog"></a>
 
-**tsellm** is SQLite wrapper with LLM superpowers.
-It's available as Python package and as a SQLite shell wrapper.
+**tsellm** is an interactive SQLite shell with LLM Support.
+Available as `pip install tsellm`.
 
-## How
+## Usage
 
-**tsellm** relies on three facts:
+Let's create a simple SQLite database with some data.
 
-* SQLite is bundled with the standard Python library (`import sqlite3`)
-* one can create Python-written user-defined functions to be used in SQLite 
-  queries (see [create_function](https://github.com/simonw/llm))
-* [Simon Willison](https://github.com/simonw/) has gone through the process of 
-  creating the beautiful [llm](https://github.com/simonw/llm) Python 
-  library and CLI
+```bash
+sqlite3 prompts.db <<EOF
+CREATE TABLE [prompts] (
+   [prompt] TEXT
+);
+INSERT INTO prompts VALUES('hello world!');
+INSERT INTO prompts VALUES('how are you?');
+INSERT INTO prompts VALUES('is this real life?');
+INSERT INTO prompts VALUES('1+1=?');
+EOF
+```
 
-With that in mind, one can bring the whole `llm` library into SQLite.
-**tsellm** attempts to do just that
+### CLI
 
-## Installation
+You can use any of the [llm plugins](https://llm.datasette.io/en/stable/plugins/directory.html)
 
-## Usage
+You can execute LLM-powered SQL queries directly in the CLI, like so:
+
+First let's install a dummy plugin
+
+```shell
+llm install llm-markov
+```
+```shell
+tsellm prompts.db "select prompt(prompt, 'markov') from prompts"
+```
+Now let's try a more complex one, 
+
+```shell
+llm install llm-gpt4all
+```
+
+```shell
+tsellm prompts.db "select prompt(prompt, 'orca-2-7b') from prompts"
+```
+
+### Interactive Shell
+
+You can enter an interactive REPL-style shell to manipulate your database.
+
+```shell
+tsellm prompts.db
+```
+
+There you can do queries the normal way:
+```sql
+ALTER TABLE prompts ADD COLUMN orca;
+UPDATE PROMPTS SET orca=prompt(prompt, 'orca-2-7b');
+```
+
+
+## Installation
 
 ```bash
 pip install tsellm
 ```
 
+## How
+
+**tsellm** relies on the following facts:
+
+* SQLite is bundled with the standard Python library (`import sqlite3`)
+* Python 3.12 ships with a [SQLite interactive shell](https://docs.python.org/3/library/sqlite3.html#command-line-interface)
+* one can create Python-written user-defined functions to be used in SQLite 
+  queries (see [create_function](https://github.com/simonw/llm))
+* [Simon Willison](https://github.com/simonw/) has gone through the process of 
+  creating the beautiful [llm](https://github.com/simonw/llm) Python 
+  library and CLI
+
 ### Development
 
 ```bash