https://github.com/iamaziz/chat_with_images

Streamlit app to chat with images using Multi-modal LLMs.
https://github.com/iamaziz/chat_with_images

llava llms multimodal-llm streamlit

Last synced: about 2 months ago
JSON representation

Streamlit app to chat with images using Multi-modal LLMs.

• Host: GitHub
• URL: https://github.com/iamaziz/chat_with_images
• Owner: iamaziz
• License: mit
• Created: 2023-12-24T20:28:32.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-17T04:25:06.000Z (10 months ago)
• Last Synced: 2024-10-12T04:53:29.805Z (3 months ago)
• Topics: llava, llms, multimodal-llm, streamlit
• Language: Python
• Homepage:
• Size: 2.98 MB
• Stars: 6
• Watchers: 2
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Chat with images locally

Using `llava` and `bakllava` models (Ollama) to chat with images.

![image](https://github.com/iamaziz/chat_with_images/assets/3298308/f3ed37cb-b6a8-41c6-9de2-3da65838958f)

### Getting Started

Install required packages (venv recommended)

```bash

pip install -r requirements.txt

```

Start the app:

```bash

streamlit run app.py

```

### Prerquisites

- [Ollama](https://ollama.ai) should be installed with [`llava`](https://ollama.com/library/llava) and/or [`backllava`](https://ollama.com/library/bakllava).