{"id":26569152,"url":"https://github.com/hamza-cpp/llm-vllm_platform","last_synced_at":"2026-05-04T09:32:53.212Z","repository":{"id":282901264,"uuid":"950023642","full_name":"Hamza-cpp/llm-vllm_platform","owner":"Hamza-cpp","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-28T21:01:53.000Z","size":83,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-23T01:49:48.149Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/Hamza-cpp.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}},"created_at":"2025-03-17T14:08:39.000Z","updated_at":"2025-03-28T21:01:57.000Z","dependencies_parsed_at":"2025-06-13T06:05:32.314Z","dependency_job_id":"daf67386-cdcc-4efe-af4b-d05c815a8e4f","html_url":"https://github.com/Hamza-cpp/llm-vllm_platform","commit_stats":null,"previous_names":["hamza-cpp/llm-vllm_platform"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Hamza-cpp/llm-vllm_platform","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hamza-cpp%2Fllm-vllm_platform","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hamza-cpp%2Fllm-vllm_platform/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hamza-cpp%2Fllm-vllm_platform/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hamza-cpp%2Fllm-vllm_platform/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Hamza-cpp","download_url":"https://codeload.github.com/Hamza-cpp/llm-vllm_platform/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hamza-cpp%2Fllm-vllm_platform/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32601531,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"online","status_checked_at":"2026-05-04T02:00:06.625Z","response_time":58,"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":[],"created_at":"2025-03-22T20:20:23.556Z","updated_at":"2026-05-04T09:32:53.189Z","avatar_url":"https://github.com/Hamza-cpp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM/VLLM Chatbot Platform\n\nA comprehensive platform for running text and vision-based language models locally using Ollama and llama.cpp.\n\n## Overview\n\nThis project provides a complete solution for deploying and interacting with multiple language models through a clean web interface. It consists of:\n\n- FastAPI backend for handling text and vision requests\n- Ollama integration for text-based language models\n- llama.cpp integration for vision-based language models\n- Docker containerization for easy deployment\n\n## Architecture\n\nThe system consists of three main services:\n\n1. **Ollama Service**: Handles text-based LLM requests\n2. **llama.cpp Service**: Processes vision-based (multimodal) requests\n3. **FastAPI Backend**: Provides API endpoints and orchestrates between services\n\n## Available Models\n\n### Text Models (via Ollama)\n\n- qwen2.5:0.5b\n- qwen2.5:1.5b\n- phi3.5:3.8b\n- qwen2.5:3b\n- phi:2.7b\n- tinyllama:1.1b\n\n### Vision Models (via llama.cpp)\n\n- Qwen2-VL-2B-Instruct\n\n## Installation\n\n### Prerequisites\n\n- Docker\n- Docker Compose\n\n### Setup\n\n1. Clone this repository:\n\n    ```bash\n    git clone https://github.com/Hamza-cpp/llm-vllm_platform.git\n    cd llm-vllm_platform\n    ```\n\n2. Create Docker network:\n\n    ```bash\n    docker network create chatbot_network\n    ```\n\n3. (Optional) Edit `models.txt` to specify which Ollama models to download during startup.\n\n4. Build and start the services:\n\n    ```bash\n    docker-compose up -d\n    ```\n\n## API Endpoints\n\n### Text Generation\n\n```text\nPOST /api/generate\n```\n\nRequest body:\n\n```json\n{\n  \"context\": \"Optional context information\",\n  \"user_question\": \"Your question to the model\",\n  \"model\": \"qwen2.5:0.5b\"\n}\n```\n\n### Vision Generation\n\n```text\nPOST /api/generate-vision\n```\n\n- Send as form-data:\n  - `user_question`: Text question about the image\n  - `image`: Image file (.jpg, .jpeg, or .png)\n\n## Development\n\n### Project Structure\n\n- `api.py`: FastAPI backend for text and vision API endpoints\n- `ui.py`: Gradio UI for interacting with the models\n- `llama_cpp_api.py`: Implementation for vision model using llama.cpp\n- `Dockerfile.*`: Docker configurations for each service\n- `docker-compose.yaml`: Docker Compose configuration\n\n### Environment Variables\n\n- `OLLAMA_API_URL`: URL for the Ollama API service\n- `LLAMACPP_API_URL`: URL for the llama.cpp vision API service\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhamza-cpp%2Fllm-vllm_platform","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhamza-cpp%2Fllm-vllm_platform","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhamza-cpp%2Fllm-vllm_platform/lists"}