In this tutorial, we use the aider AI coding assistant, along with the Claude 3.5 Sonnet LLM to generate an AI Retrieval-Augmented Generation (RAG) app without writing a line of code.
🚀 Ready to Level Up? Join the Coding the Future Skool community!
👉 www.skool.com/coding-the-future-with-ai
aider first builds a command line RAG app for use. Then, it adds a Web UI. Then, we have aider upgrade our UI's theme.
Finally, we show how AI coding assistants can not only help us BUILD apps, but also TEACH us about the apps and the underlying technologies. We get to build AND learn at the same time, in the same place!
-------------------------------------------------------------------
Get the source code for the final RAG app
-------------------------------------------------------------------
github.com/timkitch/yt-coding-assistants-rag-tutor…
--------------------------------------------------------------------------------------------
✅Tutorial setup
(see video below the description for a step-by-step guide)
--------------------------------------------------------------------------------------------
Install any of the below that you do NOT already have:
git: git-scm.com/downloads
Python 3.10 or later: wiki.python.org/moin/BeginnersGuide/Download
aider: aider.chat/docs/install.html
VS Code: code.visualstudio.com/download
Cody AI (optional): sourcegraph.com/cody
Create Anthropic API key (save this - you'll need it to configure aider below): console.anthropic.com/settings/keys
Create OpenAI API key (save this - you'll need it to configure aider below): platform.openai.com/api-keys
Create an empty folder for the project (any name you choose) and open in VS Code
-------------------------------------------------------------------------------------
URL and User Query Used in Tutorial to Test RAG App
(you can use any web page you choose as well)
------------------------------------------------------------------------------------
blog.continue.dev/ollama-code-assistant/
Briefly summarize how can I fine-tune StarCoder with my own development data when using the Continue coding assistant. Format the output as Markdown.
----------------------------
📝aider Prompts
----------------------------
/web python.langchain.com/v0.2/docs/tutorials/rag/
Use the LangChain RAG tutorial documentation, which I provided to you previously to generate a simple RAG app in Python that uses the LangChain v0.2 framework. The app will allow the user to provide the URL for a web page and ask questions related to the contents of the page. The user interface will be the command line for now. The app should use OpenAI models and APIs. Generate all the required files, functions, methods, imports, etc. but don't implement any functions yet. Instead, just insert comments. Also, generate the Python requirements.txt file. Only implement the features I've requested.
Implement the loading of a web page. Let the user provide the URL to be loaded. Print the contents of the page to the console. Leave the rest of the code as is.
Generate the implementation for loading the web page contents into the vector store. Leave the rest of the code as is.
Implement the code required to complete the retrieval chain and allow the user to ask questions based on the web page content that's been stored in the vector database. Use GPT 4o (gpt-4o) as the chat LLM.
Add a simple Streamlit UI for this app that allows the user to do the same things they can currently do from the command line, but in a web browser. Also, give me instructions for running the Streamlit UI
Add more color to the UI. I want to see some blues and purples, with a splash of red
Generate a README file in markdown format for this project. Explain what the app does, the main technologies and components and how to run and use the app.
--------------------------------
📝Cody AI Prompts
--------------------------------
I'm new to Langchain and RAG. I've also never seen this code before. Explain this code, what it's doing and the major components and their roles. When explaining code and components, be sure to restrict you answers to the files and code that exist within this codebase.
Can you explain to me in simple terms the basic flow of this app? I want to understand the RAG process better.
✉️ Subscribe to our "Coding the Future With AI" bi-weekly newsletter: coding-the-future-with-ai.ck.page/315a88776d
00:00 Introduction
00:38 Overview of RAG
02:08 Installing Prerequisites
02:42 Launching aider
03:51 aider Generates initial App Version
08:49 aider Implements Web Page Fetching
10:08 aider Populates Vector Store
11:29 aider Implements the Retrieval Chain
13:21 Time to Run Our RAG App!
14:34 aider Adds a Web UI for Our App
16:17 Testing v1 of Our Web UI
16:54 aider Snazzes Up Our Web UI!
17:29 Testing Our Updated Web UI
18:04 AI Assistants Teach Us About Our
Coding the Future With AI
コメント