Skip to content

A curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases.

audit: fix multimodal_rag - add env comment, add uv prerequisite and install step

Tiioluwanicce47009f85c
diff --git a/multimodal/multimodal_rag/.env.example b/multimodal/multimodal_rag/.env.example
index 39bb49f..4c745b4 100644
--- a/multimodal/multimodal_rag/.env.example
+++ b/multimodal/multimodal_rag/.env.example
@@ -1 +1,3 @@
+# Google API key (required)
+# Get your free key at https://aistudio.google.com
GOOGLE_API_KEY=your_google_api_key_here
diff --git a/multimodal/multimodal_rag/README.md b/multimodal/multimodal_rag/README.md
index 3d3d051..669bfd0 100644
--- a/multimodal/multimodal_rag/README.md
+++ b/multimodal/multimodal_rag/README.md
@@ -36,6 +36,7 @@ For media files (images, audio, video), Gemini first extracts a text description
## Prerequisites
- Python 3.10 or later
+- [uv](https://docs.astral.sh/uv/) for dependency management
- A Google API key. Get one free at [aistudio.google.com](https://aistudio.google.com)
## Installation
@@ -48,6 +49,12 @@ cp .env.example .env
Add your Google API key to `.env`.
+Install dependencies:
+
+```bash
+uv sync
+```
+
## Usage
```bash
@@ -116,3 +123,7 @@ Content parts assembled for Gemini 3 Flash:
▼
Gemini 3 Flash generates a grounded answer with source citations
```
+
+---
+
+[Back to Top](#multimodal-rag)