Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A copilot sample that uses python to ground the copilot responses in company data.
| Date | Stars |
|---|---|
| 2026-07-31 | 290 |
| 2026-08-05 | 289 |
| 2026-08-06 | 289 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Copilot application that implements RAG
This is a sample copilot that application that implements RAG via custom Python code, and can be used with the Azure AI Studio. This sample aims to provide a starting point for an enterprise copilot grounded in custom data that you can further customize to add additional intelligence or capabilities.
Following the below steps, you will: set up your development environment, create or reference your Azure AI resources, explore prompts, build an index containing product information, run your copilot, evaluate it, and deploy your copilot to a managed endpoint.
> [!IMPORTANT]
> We do not guarantee the quality of responses produced by these samples or their suitability for use in your scenarios, and responses will vary as development of the samples is ongoing. You must perform your own validation the outputs of the application and its suitability for use within your company.
## Step 1: Az login
If you haven't already done so, run `az login` to authenticate to Azure in your terminal.
- Note: if you are running from within a Codespace or the curated VS Code cloud container, you will need to use `az login --use-device-code`
## Step 2: Reference Azure AI resources
Based on the instructions [here](https://microsoft-my.sharepoint.com/:w:/p/mesameki/Ed5UKepTDSpCpUCwigrxFrsBKMBZrEugqhSrosnz8jtdZQ?e=cudeiv), you already have everything you need. Navigate to your hub and project, click on "Settings" from the left menu, scroll down to "Connected Resource" and click on "View all". We need the information here to fill some of the details of our yaml file below. Open your ./provisioning/provision.yaml file and let's fill it together step by step:
### For the section under "ai":
Under your AI Studio project's "Settings" tab, there is a section called "Project properties". Copy paste all the info you need from there into this part of the yaml file. Note that:
- "hub_name": copy paste what you see under "hub resource name" in the UI
- "project_name"= The string under field "Name" in the UI
### For the section under "aoai":
Click on "Settings" from the left menu of Azure AI Studio, scroll down to "Connected Resource" and click on "View all". Click on the table row whose type is "Azure OpenAI". Once opened:
- aoai_resource_name: What comes under "Resource" in your table
- kind: "OpenAI" (keep it as is)
- connection_name: Title of the page (written above "Connection Details")
### For the section under "deployments":
Click on the "Deployments" tab from the left menu of Azure AI Studio. If you followed all the steps in the workshop guide doc, you already have two deployments here. One embedding model and one GPT model. Insert information from that table here (the table has column headers name, model name, and version. Exactly what you will use here):
- name: from your Deployments table, copy what is under "name". Example: "gpt-4"
model: from your Deployments table, copy what is under "model name". Example: "gpt-4"
version: from your Deployments table, copy what is under "Model version". Example: 1106.
Repeat this for your embedding model:
- name: from your Deployments table, copy what is under "name"/ Example: "text-embedding-ada-002"
model: from your Deployments table, copy what is under "model name". Example: "gpt-4""text-embedding-ada-002"
version: from your Deployments table, copy what is under "Model version". Example: "2" # if you don't know, comment this line and we'll pick default
### For the section under "search":
Click on "Settings" from the left menu of Azure AI Studio, scroll down to "Connected Resource" and click on "View all". Click on the table row whose type is "Azure AI Search (Cognitive Search)". Once opened:
- search_resource_name: What comes under "Resource" in your table
- connection_name: Title of the page (written above "Connection Details")
Once you set up those parameters, run:
```bash
# Note: make sure you run this command from the src/ direcExcerpt of 13,567 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:26ec440b7ea2ff04, llm:description: 'A copilot sample that uses python to ground the copilot responses in company data.' No topics provided.
matched fp:26ec440b7ea2ff04, llm:description: 'A copilot sample that uses python to ground the copilot responses in company data.' No topics provided.
matched fp:26ec440b7ea2ff04, llm:description: 'A copilot sample that uses python to ground the copilot responses in company data.' No topics provided.