Retrieval-Augmented Generation (RAG) with Pinecone

note

To see video of this example

In this example, you'll build a pipeline with Dagster that:

• Loads data from GitHub and Documentation site
• Translates the data into embeddings and tags metadata
• Stores the data in a vector database
• Retrieves relevant information to answer ad hoc questions

Prerequisites

To follow the steps in this guide, you'll need:

• Basic Python knowledge
• Python 3.9+ installed on your system. Refer to the Installation guide for information.

Step 1: Set up your Dagster environment

First, set up a new Dagster project.

1. Clone the Dagster repo and navigate to the project:

   cd examples/docs_projects/project_ask_ai_dagster

2. Create and activate a virtual environment:

   MacOS

   uv venv dagster_example
   source dagster_example/bin/activate

   Windows

   uv venv dagster_example
   dagster_example\Scripts\activate

3. Install Dagster and the required dependencies:

   uv pip install -e ".[dev]"

Step 2: Launch the Dagster webserver

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

dagster dev

Next steps

• Continue this example with sources