RAG Copilot Extension LP #1611
RAG Copilot Extension LP #1611
Conversation
Co-authored-by: Joe Stech <JoeStech@users.noreply.github.com>
Initial Vector and GitHub writeup
…ment and configuration sections
annietllnd
left a comment
annietllnd
left a comment
There was a problem hiding this comment.
Some comments from me!
| - A GitHub account. | ||
| - A Linux-based computer with Python installed. | ||
|
|
||
| author_primary: Avin Zarlez, Joe Stech |
There was a problem hiding this comment.
Should be author and a JSON like list. This is currently breaking the site's building process. I try to run hugo before submitting a PR, just to check things aren't breaking
There was a problem hiding this comment.
Ah this was different on Joe's fork, looks like it had been updated. Fixed.
|
|
||
| ## What is a RAG system? | ||
|
|
||
| RAG stands for "Retrieval Augmented Generation". It describes an AI framework that combines information retrieval with text generation to improve the quality and accuracy of AI-generated content. |
There was a problem hiding this comment.
IMO the abbreviation should be presented in the introduction at its first mention
There was a problem hiding this comment.
Added to introduction page
|
|
||
| 1. Retrieval: The system searches a knowledge base, usually using some combination of vector and/or text search. | ||
| 2. Augmentation: The retrieved information is then provided as context to a generative AI model to provide additional context for the user's query. | ||
| 3. The AI model uses both thye retrieved knowledge and its internal understanding to generate a more useful response to the user. |
|
|
||
| Then for any given vector (like the embedding of a question asked by a user) we can query our vector database to find embedded data that is most similar. | ||
|
|
||
| For example, for our use case let's say we want to know which Arm learning path is most relevant to a question a user asks. |
There was a problem hiding this comment.
"For example, for our use case" seems double, I'd use one of them
|
|
||
| By copying the FAISS database into every deployment, we achieve a scalable, high-performance solution that can handle a large number of requests efficiently. | ||
|
|
||
| ## Collecting Data into Chunks |
There was a problem hiding this comment.
I'd put the git clone here, trying to keep commands closer to where they are used
|
|
||
| Copy the generated `bin` and `json` files to the root directory of your Flask application. | ||
|
|
||
| THey should be in the `vectorstore/chunks` folder. Since you are likely still in the `vectorstore` folder, run this command to copy: |
| layout: learningpathall | ||
| --- | ||
|
|
||
| ## Test it out |
There was a problem hiding this comment.
Change this to something less generic, it looks a lot like the title of this section
| - Configure a GitHub Copilot Extension for your RAG application. | ||
|
|
||
| prerequisites: | ||
| - The "[Build a GitHub Copilot Extension in Python](../gh-copilot-simple/)" Learning Path. |
There was a problem hiding this comment.
IMO the LP titles renders more nicely without the quotes
|
|
||
| Another possibility is adding another copilot invocation to rephrase the previous conversation prior to your main copilot invocation. This yields more robust results, if users reference previous elements of the conversation in their question. | ||
|
|
||
| You can precisely tailor your RAG extension to your use case, to make your extension as useful as possible. No newline at end of file |
There was a problem hiding this comment.
I'd add something here to wrap things up
There was a problem hiding this comment.
Added simple Conclusion
| - conda | ||
| - AWS CDK | ||
| operatingsystems: | ||
| - Linux, MacOS |
There was a problem hiding this comment.
Should be a JSON like list. It doesn't break anything this way but the mapping doesn't seem to work this way
|
Thanks Avin! 💪 |
|
@madeline-underwood merging into main for your editorial review |
5 participants
Before submitting a pull request for a new Learning Path, please review Create a Learning Path
Please do not include any confidential information in your contribution. This includes confidential microarchitecture details and unannounced product information.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the Creative Commons Attribution 4.0 International License.