{"id":15165769,"url":"https://github.com/gyanbardhan/medichat","last_synced_at":"2025-10-01T01:31:00.369Z","repository":{"id":246941197,"uuid":"824690376","full_name":"Gyanbardhan/MediChat","owner":"Gyanbardhan","description":"MediChat: An AI-powered medical chatbot using the Llama-2-7B-Chat model for precise clinical responses. Integrates Chroma DB and all-MiniLM-L6-v2 embeddings trained on medical literature, including texts like Clinical Emergency Medicine and Gale Encyclopedia. Accurate, fast, and reliable for healthcare queries.","archived":false,"fork":false,"pushed_at":"2024-07-05T18:30:46.000Z","size":23171,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-17T23:03:46.139Z","etag":null,"topics":["all-minilm-l6-v2","chromadb","flask","generative-ai","langchain","llama2","llm","llms","meta","sentence-transformers","vector-database"],"latest_commit_sha":null,"homepage":"https://drive.google.com/file/d/1Z2c27T0WiH8-AycAJbTcVged6y0ng6rG/view?usp=drive_link","language":"Jupyter Notebook","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/Gyanbardhan.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}},"created_at":"2024-07-05T17:41:19.000Z","updated_at":"2024-11-05T21:23:11.000Z","dependencies_parsed_at":"2024-07-06T00:06:50.106Z","dependency_job_id":null,"html_url":"https://github.com/Gyanbardhan/MediChat","commit_stats":null,"previous_names":["gyanbardhan/medichat"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyanbardhan%2FMediChat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyanbardhan%2FMediChat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyanbardhan%2FMediChat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyanbardhan%2FMediChat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Gyanbardhan","download_url":"https://codeload.github.com/Gyanbardhan/MediChat/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230788230,"owners_count":18280300,"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","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":["all-minilm-l6-v2","chromadb","flask","generative-ai","langchain","llama2","llm","llms","meta","sentence-transformers","vector-database"],"created_at":"2024-09-27T04:01:48.076Z","updated_at":"2025-10-01T01:30:58.809Z","avatar_url":"https://github.com/Gyanbardhan.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MediChat\nMediChat is an advanced medical chatbot designed to assist with clinical queries and provide information based on medical literature. It leverages state-of-the-art models and embeddings to deliver accurate and reliable responses.\n### [Demo for MediChat](https://drive.google.com/file/d/1Z2c27T0WiH8-AycAJbTcVged6y0ng6rG/view?usp=drive_link)\n## Features\n### Medical Expertise: \nProvides information based on extensive training on medical literature.\n### Advanced Model: \nUtilizes the [Llama-2-7B-Chat](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML) model from Hugging Face.\n### Vector Database: \nIncorporates Chroma DB for efficient data retrieval.\n### High-Quality Embeddings: \nUses [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) embeddings from Hugging Face.\n## Model Details\n### Llama-2-7B-Chat Model:\n- Source: [Link](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q4_0.bin)\n- Description: An open-source large language model optimized for chat-based interactions, capable of understanding and generating human-like text.\n## Database and Embeddings\n### Chroma DB: \nA vector database that allows for efficient storage and retrieval of embeddings.\n### Embeddings Model:\n- Source: [Link](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)\n- Description: A small, fast, and high-quality embedding model that provides dense vector representations of text.\n## Training Data\nMediChat is trained on embeddings derived from the following medical books:\n\n- Clinical Emergency Medicine (PDFDrive.com)\n- Current Essentials of Medicine\n- Gale Encyclopedia of Medicine Vol. 4 (N-S)\n## Installation\nTo set up MediChat, follow these steps:\n\nClone the Repository:\n\n- git clone https://github.com/Gyanbardhan/MediChat.git\n- cd MediChat\n## Install Dependencies:\n\n\n- pip install -r requirements.txt\n## Download the Model and Embeddings:\n\n- Llama-2-7B-Chat model: Download from Hugging Face and place it in the models directory.\n- Sentence-Transformers embeddings: Download from Hugging Face and place them in the embeddings directory.\n- Set Up Chroma DB\n\n#### Run the MediChat application with the following command:\n\n\n- python app.py\n#### Interact with MediChat via the provided interface, asking medical questions and receiving expert responses based on the embedded medical literature.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgyanbardhan%2Fmedichat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgyanbardhan%2Fmedichat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgyanbardhan%2Fmedichat/lists"}