Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[docs] RAG Tutorial #27304

Merged
merged 6 commits into from
Jan 23, 2025
Merged

[docs] RAG Tutorial #27304

merged 6 commits into from
Jan 23, 2025

Conversation

dehume
Copy link
Contributor

@dehume dehume commented Jan 23, 2025

Summary & Motivation

Tutorial for Ask AI

How I Tested These Changes

Changelog

Insert changelog entry or delete this section.

@dehume dehume requested a review from neverett as a code owner January 23, 2025 10:37
@dehume dehume force-pushed the dennis/doc-765-pinecone-content branch from e2d233a to 5aef46b Compare January 23, 2025 11:10

To make sure Dagster and its dependencies were installed correctly, navigate to the project root directory and start the Dagster webserver:

followed by a bash code snippet for
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This line appears to be an incomplete sentence fragment that was likely left over during editing. Removing it will improve the documentation's clarity since the code block that follows stands on its own.

Spotted by Graphite Reviewer

Is this helpful? React 👍 or 👎 to let us know.


First, set up a new Dagster project.

1. Clone the the [Dagster repo](https://github.com/dagster-io/dagster) and navigate to the project:
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove the duplicate word "the" in "Clone the the [Dagster repo]"

Spotted by Graphite Reviewer

Is this helpful? React 👍 or 👎 to let us know.

Copy link
Contributor

@neverett neverett left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Left some feedback and suggestions, but overall LGTM! Feel free to merge once the relevant tests are green.

docs/docs-beta/docs/tutorials/category-two/rag/index.md Outdated Show resolved Hide resolved
docs/docs-beta/docs/tutorials/category-two/rag/index.md Outdated Show resolved Hide resolved
docs/docs-beta/docs/tutorials/category-two/rag/index.md Outdated Show resolved Hide resolved
docs/docs-beta/docs/tutorials/category-two/rag/sources.md Outdated Show resolved Hide resolved
docs/docs-beta/docs/tutorials/category-two/rag/sources.md Outdated Show resolved Hide resolved

<CodeExample path="project_ask_ai_dagster/project_ask_ai_dagster/assets/ingestion.py" language="python" lineStart="15" lineEnd="53"/>

The next asset will convert those `Documents` to vectors and upload them to Pinecone. In order to generate the embeddings, we will need an AI model. In this case, we will use OpenAI's `text-embedding-3-small` model to transform the text we have collected from GitHub into embeddings. Dagster provides an `OpenAIResource` to interact with the OpenAI client ,and we will use that to create the embeddings. This asset will also create the index in Pinecone:
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove the space before the comma in OpenAI client ,and to fix the punctuation.

Spotted by Graphite Reviewer

Is this helpful? React 👍 or 👎 to let us know.

@dehume dehume merged commit d547947 into master Jan 23, 2025
6 of 7 checks passed
@dehume dehume deleted the dennis/doc-765-pinecone-content branch January 23, 2025 17:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants