{"id":24713945,"url":"https://github.com/asshejan/image-description-locally-using-llava","last_synced_at":"2026-05-07T14:41:34.632Z","repository":{"id":274374115,"uuid":"922701202","full_name":"asshejan/Image-Description-Locally-using-LLava","owner":"asshejan","description":"A Streamlit app that uses the Ollama llava model to describe uploaded images. Simply upload an image, and the model generates a description. Easy setup and interactive interface!","archived":false,"fork":false,"pushed_at":"2025-01-26T22:25:39.000Z","size":3940,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-22T07:53:28.158Z","etag":null,"topics":["ai","chatbot","image","image-vision","lava","llama"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/asshejan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-01-26T21:49:00.000Z","updated_at":"2025-01-27T20:42:40.000Z","dependencies_parsed_at":null,"dependency_job_id":"ae368704-f7c8-4aee-9ca1-396028ccaf08","html_url":"https://github.com/asshejan/Image-Description-Locally-using-LLava","commit_stats":null,"previous_names":["asshejan/local-image-recognition-ai-chatbot-llava-"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/asshejan/Image-Description-Locally-using-LLava","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asshejan%2FImage-Description-Locally-using-LLava","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asshejan%2FImage-Description-Locally-using-LLava/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asshejan%2FImage-Description-Locally-using-LLava/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asshejan%2FImage-Description-Locally-using-LLava/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/asshejan","download_url":"https://codeload.github.com/asshejan/Image-Description-Locally-using-LLava/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asshejan%2FImage-Description-Locally-using-LLava/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281371746,"owners_count":26489526,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-27T02:00:05.855Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","chatbot","image","image-vision","lava","llama"],"created_at":"2025-01-27T08:14:12.653Z","updated_at":"2025-10-28T01:33:15.474Z","avatar_url":"https://github.com/asshejan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image Description with Ollama\n\nThis project is a simple Streamlit-based web application that allows users to upload an image and get a description of it using the Ollama `llava` model. The app provides an intuitive interface for interacting with the model, making it easy to describe uploaded images.\n\n## Features\n\n- Upload images in `.jpg`, `.jpeg`, or `.png` formats.\n- Display the uploaded image for user confirmation.\n- Use the `ollama` model to generate a description of the image.\n- Streamlit interface for simplicity and accessibility.\n\n## Requirements\n\nTo run this project, you need the following:\n\n- Python 3.7 or higher\n- Required Python libraries:\n  - `streamlit`\n  - `ollama`\n\n## Installation\n\n1. Clone this repository:\n   ```bash\n   git clone https://github.com/your-username/your-repo-name.git\n   cd your-repo-name\n   ```\n\n2. Install the required dependencies:\n   ```bash\n   pip install streamlit ollama\n   ```\n\n3. Run the Streamlit app:\n   ```bash\n   streamlit run test.py\n   ```\n\n## Usage\n\n1. Launch the app locally by running the above command.\n2. Upload an image using the file uploader.\n3. Click the \"Describe Image\" button to get the model's description of the image.\n\n## Code Overview\n\nThe main functionality is implemented in the `test.py` file:\n\n- **Image Upload:**\n  Allows users to upload an image via Streamlit's `file_uploader` widget.\n\n- **Image Display:**\n  The uploaded image is displayed using `st.image()`.\n\n- **Model Interaction:**\n  The uploaded image is saved temporarily and passed to the `ollama.chat` function to get a description.\n\n- **Error Handling:**\n  Handles exceptions to ensure a smooth user experience.\n\n## Screenshot\n\n![App Screenshot](preview.png)\n\n## Folder Structure\n\n```plaintext\n.\n├── test.py               # Main application file\n├── images/              # Folder for storing example images or screenshots\n└── README.md            # Project documentation\n```\n\n## Example Output\n\n- **Input:** An uploaded image of a cat.\n- **Output:**\n  \"This is an image of a cat sitting on a windowsill, looking outside.\"\n\n## Future Improvements\n\n- Add support for multiple image uploads.\n- Provide additional model configuration options.\n- Enhance the UI with more styling and interactivity.\n\n## Contributing\n\nContributions are welcome! Please fork this repository and submit a pull request for any enhancements or bug fixes.\n\n## License\n\nThis project is licensed under the MIT License. See the `LICENSE` file for details.\n\n## Acknowledgments\n\n- [Ollama](https://www.ollama.com) for the `llava` model.\n- [Streamlit](https://streamlit.io/) for making web app development so accessible.\n\n---\n\nFeel free to reach out if you have any questions or suggestions!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasshejan%2Fimage-description-locally-using-llava","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fasshejan%2Fimage-description-locally-using-llava","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasshejan%2Fimage-description-locally-using-llava/lists"}