{"repo":"Leon-Sander/Local-Multimodal-AI-Chat","free":true,"listed":false,"github":"https://github.com/Leon-Sander/Local-Multimodal-AI-Chat","clone":"git clone https://github.com/Leon-Sander/Local-Multimodal-AI-Chat.git","description":"Self-hostable multimodal chat with local LLMs (Ollama/OpenAI): PDF RAG, image chat, and Whisper voice, Streamlit + Docker.","language":"Python","stars":205,"topics":["chromadb","docker","langchain","llm","local-llm","multimodal","ollama","openai","rag","speech-to-text"],"license":"GPL-3.0","category":"ai-agents","readme_excerpt":"Local Multimodal AI Chat A self-hostable, multimodal chat application that runs open-source models locally. Chat with text, images, PDFs, and voice in one interface, powered by local models via Ollama (with an optional OpenAI API fallback), retrieval-augmented generation over your own PDFs, and speech-to-text with Whisper . Demo / setup walkthrough: YouTube video Overview Local Multimodal AI Chat integrates several AI models behind a single Streamlit interface, with a focus on data privacy (everything can run on your own machine) and modularity (each capability lives in its own handler). - Chat with local models through the Ollama API, or switch to the OpenAI API at runtime. - Talk to your PDFs via retrieval-augmented generation (RAG) backed by a Chroma vector database. - Send images to vision-capable models (e.g. LLaVA). - Speak instead of type : audio is transcribed with Whisper. - Keep your history : chat sessions, messages, and settings are persisted in SQLite. Features - Local-first inference (Ollama): run models on your own hardware, no cloud dependency required. - Optional OpenAI API: switch endpoint and model at runtime from the sidebar. - PDF chat (RAG): upload PDFs, chunk and embed them (Ollama nomic-embed-text ), and query them through Chroma. - Image chat: pass images to multimodal models via the same chat bar. - Voice input (Whisper): record or upload audio; it is transcribed and fed into the conversation. - Persistent, multi-session history: SQLite-backed sessio","default_branch":null,"files":null,"tree":[],"storefront":"/r/Leon-Sander","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Leon-Sander/Local-Multimodal-AI-Chat/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}