{"id":19723952,"url":"https://github.com/vs4vijay/ai-playground","last_synced_at":"2025-04-29T22:31:09.342Z","repository":{"id":224259223,"uuid":"653277776","full_name":"vs4vijay/AI-Playground","owner":"vs4vijay","description":"All-in-One AI Playground for LLM, Chat, RAG, Agents, etc.","archived":false,"fork":false,"pushed_at":"2025-02-06T16:31:59.000Z","size":169,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-19T12:14:58.151Z","etag":null,"topics":["agent","agents","ai","anthropic","autogen","autogpt","chatgpt","cohere","command-r","gemma","gpt-3","gpt-4","langchain","llama","llama2","llm","mistral","mixtral","prompt","semantic-kernel"],"latest_commit_sha":null,"homepage":"","language":"Python","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/vs4vijay.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":"2023-06-13T18:36:41.000Z","updated_at":"2025-03-08T09:13:04.000Z","dependencies_parsed_at":"2024-04-21T20:05:21.334Z","dependency_job_id":"8de44636-3c16-4609-b269-7dcd0d1da793","html_url":"https://github.com/vs4vijay/AI-Playground","commit_stats":{"total_commits":34,"total_committers":2,"mean_commits":17.0,"dds":0.05882352941176472,"last_synced_commit":"1a3ae50b4d250b19d8e7276f6a8cbfac8a311b7e"},"previous_names":["vs4vijay/ai-playground"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vs4vijay%2FAI-Playground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vs4vijay%2FAI-Playground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vs4vijay%2FAI-Playground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vs4vijay%2FAI-Playground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vs4vijay","download_url":"https://codeload.github.com/vs4vijay/AI-Playground/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251592994,"owners_count":21614453,"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":["agent","agents","ai","anthropic","autogen","autogpt","chatgpt","cohere","command-r","gemma","gpt-3","gpt-4","langchain","llama","llama2","llm","mistral","mixtral","prompt","semantic-kernel"],"created_at":"2024-11-11T23:24:02.975Z","updated_at":"2025-04-29T22:31:09.329Z","avatar_url":"https://github.com/vs4vijay.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI-Playground\n\n---\n\nAI Playground for trying out LLM Models, Embeddings, Vector Stores, Semantic Search, RAG, Azure OpenAI, LLaMa, Mistral\n\n\n## Installation\n\n```bash\npip install -U ai-playground\n```\n\n### Installation for development\n\nPre-requisites:\n\n- Python 3.10+ and pip\n\n```bash\n# Start virtual environment\nsource ./activate\n\n# Install requirements\npip install -r requirements.txt\n```\n\n\n### Running the full playground\n\n- Copy `.env.example` to `.env` and fill in the values\n\n- Run the following command to start the server\n\n```bash\npython ai_playground.py\n```\n\n---\n\n\n## Models\n\n- Llama 2 - https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF\n- Llama 3 Instruct - https://huggingface.co/lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF/tree/main\n\n\nwget -c https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF/resolve/main/mistral-7b-v0.1.Q8_0.gguf\nwget -c https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q8_0.gguf\nwget -c https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF/resolve/main/mistral-7b-openorca.Q8_0.gguf\n\nwget -c https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGUF/resolve/main/Wizard-Vicuna-7B-Uncensored.Q8_0.gguf\n\nwget -c https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q8_0.gguf\n\n---\n\n# Run Local LLM\n\n\n\n## Try with LLaMA.cpp\n\n- Extract LLaMA.cpp zip to bin/ directory \n\n```bash\n./bin/main.exe -m models/llama-2-7b-chat.Q8_0.gguf\n```\n\n## Try with ollama\n\n```bash\necho \"FROM ./models/llama-2-13b-chat.Q5_K_M.gguf\" \u003e llama-2-13b-chat.Modelfile\n\nollama create llama2-13b-chat -f ./llama-2-13b-chat.Modelfile\n\nollama run llama2-13b-chat\n# OR\nollama run llama3.1:7b\nollama serve llama3.1:7b\n\nollama ps\n\ncurl -X POST http://localhost:11434/api/generate -d '{\n    \"model\": \"wizardlm-uncensored\",\n    \"prompt\":\"Who made Rose promise that she would never let go?\"\n}'\n\nollama run starcoder2:3b\nollama pull nomic-embed-text\n\n```\n\n## Try with vLLM\n\n```bash\npip install -U vllm\n\npython -u -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --model mistralai/Mistral-7B-v0.1\n```\n\n## Try with FastChat\n\n```bash\npip install -U fastchat\n\npython -m fastchat.serve.openai_api_server --host localhost --port 8000\n```\n\n## Try with LeptonAI\n\n```bash\npip install -U leptonai\n\n```\n\n## Use StarCoder\n\npip install transformers\npip install torch torchvision\npip install accelerate bitsandbytes\npip install accelerate[torch]\n\nEdit:\n- `load_in_8bit=True`\n\npython starcoder.py\n- will download ~60 GB of model\n\n---\n\n## Specs\n\nRAM Required:\n\n| Model Size | RAM Required |\n|------------|--------------|\n| 3B         | 8 GB         |\n| 7B         | 16 GB        |\n| 13B        | 32 GB        |\n\n\n---\n\n## Chat UIs\n\n- OpenWebUI - https://github.com/open-webui/open-webui\n- kotaemon - https://github.com/Cinnamon/kotaemon\n- ChatBotUI - https://github.com/mckaywrigley/chatbot-ui\n- OpenUI\n- AnythingLLM\n- LobeChat\n- LibreChat - https://github.com/danny-avila/LibreChat\n- oterm\n- https://github.com/billmei/every-chatgpt-gui\n- https://github.com/Bin-Huang/chatbox\n- https://bettergpt.chat/\n- https://github.com/bionic-gpt/bionic-gpt\n- oterm - `pipx install oterm`\n\n\n---\n\n## Code Assistants / Copilots\n\n- Github Copilot\n- Continue.dev - https://github.com/continuedev/continue\n- Cursor\n- LlamaCoder\n- Zed AI\n- ClaudeDev\n- BlackBox AI\n- Tabnine AI\n- OpenHands - https://github.com/All-Hands-AI/OpenHands\n- https://github.com/TabbyML/tabby\n\n---\n\n## Agents\n\n- AutoGen\n- aider-chat - `pipx install aider-chat`\n- metagpt - `pipx install metagpt`\n- CrewAI - https://github.com/joaomdmoura/crewAI\n- AgentScript\n- https://github.com/browser-use/web-ui\n- https://github.com/browser-use/browser-use\n- https://github.com/steel-dev/steel-browser\n- https://github.com/phidatahq/phidata\n- LangGraph\n- https://github.com/elizaOS/eliza\n- SmolAgents\n- https://github.com/steel-dev/steel-browser\n- https://github.com/lightpanda-io/browser\n\n---\n\n## Other Tools\n\n- https://github.com/outlines-dev/outlines\n- guidance\n- https://leetgpu.com/\n- MindsDB\n\n---\n\n### Development Notes\n\n```bash\n\npip install uv\nuvx\n\n\nuv tool install autogenstudio\n\npip install pyautogen\n\nuvx autogenstudio\n\nautogenstudio ui --port 8080 --appdir ./my-app\n\nuvx markitdown\n\nuvx --from langroid-examples chat --model ollama/qwen2.5-coder:32b\n\nuvx --from flask python\n\ndspy\n\npip install openplayground\nopenplayground run\n\nuvx --python 3.13 open-webui serve\n\nollama run mistral\n\npip install -U jina\n\nRay Serve\npip install \"ray[serve]\"\nhttps://github.com/ray-project/ray-llm\n\ntxtai\n\nMLC AI - https://mlc.ai/package/\npip install --pre --force-reinstall mlc-ai-nightly mlc-chat-nightly -f https://mlc.ai/wheels\npython -m mlc_chat.rest \n\nOpenLLM\n\n\nhttps://github.com/FlowiseAI/Flowise\n\n\nwget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j\n\nhttps://github.com/go-skynet/LocalAI\ndocker pull quay.io/go-skynet/local-ai:latest\n\nnlpcloud\n\ncurl \"https://api.nlpcloud.io/v1/\u003cmodel_name\u003e/entities\" \\\n  -H \"Authorization: Token \u003ctoken\u003e\" \\\n  -H \"Content-Type: application/json\" \\\n  -X POST \\\n  -d '{\"text\":\"John Doe has been working for Microsoft in Seattle since 1999.\"}'\n\n\nhttps://github.com/microsoft/semantic-kernel\nhttps://github.com/microsoft/guidance\n\n\nhttps://skypilot.readthedocs.io/\n\nLater:\nhttps://github.com/Arize-ai/phoenix\nhttps://github.com/explodinggradients/ragas\nhttps://github.com/trypromptly/LLMStack\n\n\nQ5_K_M\n\n\n\npoetry export -f requirements.txt --output requirements.txt\npoetry publish --build\n\n\nlazypredict\n\nmito\n\npip install langchain-serve\n\nLangServe\n\npip install -U \"langserve[all]\"\npip install -U langchain-cli\n\n\nlangflow run\n\n\nflowise\n\npromptflow\npip install promptflow promptflow-tools\n\n\nPyGWalker\n\n# DSPy\npip install dspy-ai\n\n\n\n\n\nhttps://github.com/ShreyaR/guardrails\nhttps://github.com/guardrails-ai/guardrails\n\n\n\nguidance\nhttps://guidancelab.ai/\nhttps://github.com/1rgs/jsonformer\n\nLangChain\nhttps://github.com/jina-ai/langchain-serve\n\nLangFlow / Flowise / LangSmith\nChainLit\n\npromptflow\n\n\nLMQI\nhttps://github.com/eth-sri/lmql\n\nhttps://github.com/zilliztech/GPTCache\n\nhttps://github.com/argilla-io/argilla\n\nhttps://github.com/vllm-project/vllm\n\nhttps://github.com/TransformerOptimus/SuperAGI\n\naccelerate\n  - accelerate config\n  - accelerate env\nbitsandbytes\nwand\nhttps://github.com/huggingface/text-generation-inference\n\n\nctransformers\n\nspacy\nspacy-llm\ngorilla-cli\nhttps://github.com/langgenius/dify\ngptcache\n\nhttps://github.com/wandb/openui\n\n\nhttps://github.com/deepseek-ai/DeepSeek-Coder\n\n\nhttps://github.com/jgravelle/AutoGroq\n\n\nhttps://github.com/infiniflow/ragflow\n\nAutogen Studio\n\nhttps://docs.openlit.io/latest/introduction\n\n\nhttps://github.com/FujiwaraChoki/MoneyPrinterV2\nhttps://voidface.fly.dev/\n\n\nuv run ruff check\n\nuv python pin 3.13\nuv venv --python 3.11.6\nuv python install 3.12\n\nuv add --script smolagents.py smolagents\nuv run smolagents.py\n\nuv venv\n\nuvx posting\n```\n \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvs4vijay%2Fai-playground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvs4vijay%2Fai-playground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvs4vijay%2Fai-playground/lists"}