{"id":20655410,"url":"https://github.com/bhimrazy/chat-with-phi-3-vision","last_synced_at":"2026-06-23T03:31:24.887Z","repository":{"id":241281285,"uuid":"804769986","full_name":"bhimrazy/chat-with-phi-3-vision","owner":"bhimrazy","description":"Chat with Phi 3.5/3 Vision LLMs. Phi-3.5-vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.","archived":false,"fork":false,"pushed_at":"2025-01-02T14:24:27.000Z","size":3483,"stargazers_count":34,"open_issues_count":0,"forks_count":11,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-09T09:51:01.376Z","etag":null,"topics":["chat-application","huggingface","litserve","phi-3-vision","streamlit"],"latest_commit_sha":null,"homepage":"https://lightning.ai/bhimrajyadav/studios/deploy-and-chat-with-phi-3-vision-128k-instruct","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bhimrazy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2024-05-23T08:30:21.000Z","updated_at":"2025-07-22T13:46:25.000Z","dependencies_parsed_at":"2024-05-23T10:25:06.016Z","dependency_job_id":null,"html_url":"https://github.com/bhimrazy/chat-with-phi-3-vision","commit_stats":null,"previous_names":["bhimrazy/chat-with-phi-3-vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bhimrazy/chat-with-phi-3-vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bhimrazy%2Fchat-with-phi-3-vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bhimrazy%2Fchat-with-phi-3-vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bhimrazy%2Fchat-with-phi-3-vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bhimrazy%2Fchat-with-phi-3-vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bhimrazy","download_url":"https://codeload.github.com/bhimrazy/chat-with-phi-3-vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bhimrazy%2Fchat-with-phi-3-vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34674702,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-23T02:00:07.161Z","response_time":65,"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":["chat-application","huggingface","litserve","phi-3-vision","streamlit"],"created_at":"2024-11-16T18:10:54.043Z","updated_at":"2026-06-23T03:31:24.870Z","avatar_url":"https://github.com/bhimrazy.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\r\n  \u003cimg src=\"https://github.com/user-attachments/assets/ed441961-912a-4db2-9043-3ba4c7cf0b0e\" height=\"150\"/\u003e\r\n  \u003cbr/\u003e\r\n  \u003ch1\u003eChat with Phi 3.5/3 Vision LLMs\u003c/h1\u003e\r\n  \u003ca target=\"_blank\" href=\"https://lightning.ai/bhimrajyadav/studios/deploy-and-chat-with-phi-3-vision-128k-instruct\"\u003e\r\n  \u003cimg src=\"https://pl-bolts-doc-images.s3.us-east-2.amazonaws.com/app-2/studio-badge.svg\" alt=\"Open In Studio\"/\u003e\r\n  \u003c/a\u003e\u003cbr/\u003e\r\n\u003c!--   \u003ca target=\"_blank\" href=\"https://lightning.ai/bhimrajyadav/studios/deploy-and-chat-with-phi-3-vision-128k-instruct\"\u003e\u003c/a\u003e --\u003e\r\n\u003c!--   \u003cimg src=\"https://github.com/user-attachments/assets/3cfab380-0fa6-4430-af21-ac5fff3928ee\" alt=\"Chat with Phi 3.5/3 Vision LLMs\" width=\"640\" height=\"360\"\u003e --\u003e\r\n\u003cvideo src=\"https://github.com/user-attachments/assets/9af93c91-7d27-48f5-8cee-5f7dbfb024a3\" \r\n       type=\"video/mp4\" \r\n       controls \r\n       style=\"max-width: 640px; width: 100%; height: auto;\"\u003e\r\n\u003c/video\u003e\r\n\u003c/div\u003e\r\n\r\n## Overview\r\n\r\n[**Phi-3.5-vision**](https://huggingface.co/microsoft/Phi-3.5-vision-instruct) is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.\r\n\r\nThis model enables multi-frame image understanding, image comparison, multi-image summarization/storytelling, and video summarization, which have broad applications in office scenarios.\r\n\r\n## Getting Started\r\n\r\nFollow these steps to set up and run the project:\r\n\r\n### 1. Install Dependencies  \r\n\r\ni. **Download and Install NVIDIA CUDA**  \r\n   Visit the [NVIDIA CUDA Toolkit Downloads page](https://developer.nvidia.com/cuda-downloads) and follow the instructions to install CUDA compatible with your system.  \r\n\r\nii. **Install Required Python Packages**  \r\n   Ensure you have all the necessary dependencies installed by running the following commands:  \r\n\r\n   ```bash  \r\n   pip install -r requirements.txt  \r\n   pip install flash_attn  \r\n   ```  \r\n\r\n   If you encounter any issues while installing `flash_attn`, refer to the [FlashAttention Installation Guide](https://github.com/Dao-AILab/flash-attention?tab=readme-ov-file#installation-and-features) for troubleshooting tips and additional setup details.  \r\n\r\n### 2. Start the API Server\r\n\r\nLaunch the API server powered by [LitServe](https://github.com/Lightning-AI/LitServe):\r\n\r\n```bash\r\npython server.py\r\n```\r\n\r\n### 3. Launch the Streamlit App\r\n\r\nStart the Streamlit application with the following command:\r\n\r\n```bash\r\nstreamlit run app.py\r\n```\r\n\r\n## About\r\n\r\nThis project is developed and maintained with ❤️ by [Bhimraj Yadav](https://github.com/bhimrazy).\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbhimrazy%2Fchat-with-phi-3-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbhimrazy%2Fchat-with-phi-3-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbhimrazy%2Fchat-with-phi-3-vision/lists"}