[AIConfig Cookbook] Updated Readme for Basic Prompt Routing Demo

aiconfig-docs/docs/introduction/getting-started.md

@@ -8,9 +8,7 @@ import constants from '@site/core/tabConstants';
 
 # Getting Started
 
-:::tip
 Please read [AIConfig Basics](/docs/introduction/basics) to understand the motivation behind storing prompts and model parameters as configs.
-:::
 
 ## Installation
 
@@ -62,11 +60,13 @@ Make sure to specify the API keys (such as `OPENAI_API_KEY`) in your environment
 
 ## Quickstart
 
-In this quickstart, you will create a customizable NYC travel itinerary using `aiconfig`.
+In this quickstart, you will create a customizable NYC travel itinerary using `aiconfig`. We will start with a pre-built AIConfig that we generated from this [AI Workbook](https://lastmileai.dev/workbooks/clooqs3p200kkpe53u6n2rhr9).
+
+### 1. Download the AIConfig.
 
-### 1. Download the AIConfig - `travel.aiconfig.json`.
+This AIConfig `travel.aiconfig.json` contains a prompt chain to get a list of travel activities from an LLM and then customize the activities based on user preferences (defined as parameters of the prompt). It also contains the specific models and model parameters for the LLMs.
 
-This AIConfig contains a prompt chain to get a list of travel activities from an LLM and then customize the activities based on user preferences (defined as parameters of the prompt). It also contains the specific models and model parameters for the LLMs.
+Download AIConfig [here](https://github.com/lastmile-ai/aiconfig/blob/main/cookbook/Getting-Started/travel.aiconfig.json).
 
 <details>
 <summary>`travel.aiconfig.json`</summary>
@@ -147,7 +147,7 @@ from aiconfig import AIConfigRuntime, InferenceOptions
 config = AIConfigRuntime.load('travel.aiconfig.json')
 
 # Run a single prompt
-await config.run("get_activities", params=None)
+await config.run("get_activities")
 ```
 
 </TabItem>
@@ -195,7 +195,7 @@ config = AIConfigRuntime.load('travel.aiconfig.json')
 
 # Run a single prompt (with streaming)
 inference_options = InferenceOptions(stream=True)
-await config.run("get_activities", params=None, options=inference_options)
+await config.run("get_activities", options=inference_options)
 ```
 
 </TabItem>
@@ -326,3 +326,7 @@ We are working on a local editor that you can run yourself. For now, please use
 ```
 
 ```
+
+### Code for Getting Started
+
+Python and typescript implementation [here](https://github.com/lastmile-ai/aiconfig/tree/ad38040ec3d9f0273e006464e01e02b06f2809e9/cookbook/Getting-Started).

cookbook/Basic-Prompt-Routing/README.md

@@ -1,12 +1,19 @@
-# Basic Prompting Routing Demo - AI Teaching Assistant
+# Basic Prompting Routing - AI Teaching Assistant
 
-This demo shows how a simple use case of prompt routing with AI config.
+This demo shows how a simple use case of prompt routing with AIConfig. We used streamlit to host the app so you can interact with the assistant!
+
+![image](https://github-production-user-asset-6210df.s3.amazonaws.com/81494782/282203473-f779feb6-339d-4331-9aed-1761b845100a.png)
 
 ### How does it work?
 
 The user asks a question. The LLM decides the topic as math, physics, or general. Based on the topic, the LLM selects a different "assistant" to respond. These assistants have different system prompts and respond with varying introductions and style of response.
 
 ### Setup with AIConfig
 
-1. Create an AIConfig for the prompts, models, and model parameters to be used for the different assistants: `create_config.py`.
-2. Build assistant app to handle prompt routing logic among the prompts (uses AIConfig): `assistant_app.py`.
+- `create_config.py` - create an AIConfig for the prompts, models, and model parameters to be used for the different assistants.
+- `assistant_aiconfig.json` - generated automatically from running create_config.py
+- `assistant_app.py` - build app to handle prompt routing logic among the prompts (uses AIConfig). Uses streamlit to create frontend.
+
+### Run with Streamlit
+
+`streamlit run assistant_app.py`