{"id":14964792,"url":"https://github.com/kspviswa/pyollamx","last_synced_at":"2025-10-27T02:02:18.797Z","repository":{"id":220654926,"uuid":"750619250","full_name":"kspviswa/pyOllaMx","owner":"kspviswa","description":"Your gateway to both Ollama \u0026 Apple MlX models","archived":false,"fork":false,"pushed_at":"2025-03-02T19:42:24.000Z","size":5447,"stargazers_count":115,"open_issues_count":1,"forks_count":8,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-06T20:09:22.740Z","etag":null,"topics":["ai","assistant-chat-bots","huggingface","llamacpp","mlx","ollama-app","ollama-gui"],"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/kspviswa.png","metadata":{"files":{"readme":"README.md","changelog":"history.py","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":"2024-01-31T01:26:41.000Z","updated_at":"2025-04-04T08:51:14.000Z","dependencies_parsed_at":"2024-03-02T03:27:26.478Z","dependency_job_id":"bd491254-fc1f-45bf-8db4-d3e06805a268","html_url":"https://github.com/kspviswa/pyOllaMx","commit_stats":{"total_commits":48,"total_committers":1,"mean_commits":48.0,"dds":0.0,"last_synced_commit":"535a7ac4febbe39762d00232e121b0df11282399"},"previous_names":["kspviswa/pyollamx"],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kspviswa%2FpyOllaMx","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kspviswa%2FpyOllaMx/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kspviswa%2FpyOllaMx/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kspviswa%2FpyOllaMx/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kspviswa","download_url":"https://codeload.github.com/kspviswa/pyOllaMx/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247543589,"owners_count":20955865,"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":["ai","assistant-chat-bots","huggingface","llamacpp","mlx","ollama-app","ollama-gui"],"created_at":"2024-09-24T13:33:47.247Z","updated_at":"2025-10-27T02:02:18.726Z","avatar_url":"https://github.com/kspviswa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![](assets/logos/combined_logos.png)\n# PyOllaMx (Ollama + MlX)\n#### `Your gateway to both Ollama \u0026 Apple MlX models`\n\n### ![Downloads](https://img.shields.io/github/downloads/kspviswa/pyOllaMx/total.svg)\n\nInspired by [Ollama](https://github.com/ollama/ollama), [Apple MlX](https://github.com/ml-explore/mlx) projects and frustrated by the dependencies from external applications like Bing, Chat-GPT etc, I wanted to have my own personal chatbot as a native MacOS application. Sure there are alternatives like streamlit, gradio (which are based, thereby needing a browser) or others like Ollamac, LMStudio, mindmac etc which are good but then restrictive in some means (either by license, or paid or not versatile). Also I wanted to enjoy both Ollama (based on `llama.cpp`) and Mlx models (which are suitable for image generation, audio generation etc and heck I own a mac with Apple silicon 👨🏻‍💻) through a single uniform interface.\n\nAll these lead to this project (PyOllaMx) and another sister project called [PyOMlx](https://github.com/kspviswa/PyOMlx).\n\nI'm using these in my day to day workflow and I intend to keep develop these for my use and benefit.\n\nIf you find this valuable, feel free to use it and contribute to this project as well. Please ⭐️ this repo to show your support and make my day!\n\nI'm planning on work on next items on this [roadmap.md](roadmap.md). Feel free to comment your thoughts (if any) and influence my work (if interested)\n\nMacOS DMGs are available in [Releases](https://github.com/kspviswa/pyOllaMx/releases)\n\n## PyOllaMx vs PyOMlx\n\n[PyOllaMx](https://github.com/kspviswa/pyOllaMx) : ChatBot application capable of chatting with both Ollama and Apple MlX models. For this app to function, it needs both [Ollama](https://github.com/ollama/ollama) \u0026 [PyOMlx](https://github.com/kspviswa/PyOMlx) macos app running. These 2 apps will serve their respective models on localhost for PyOllaMx to chat.\n\n[PyOMlx](https://github.com/kspviswa/PyOMlx) : A Macos App capable of discovering, loading \u0026 serving Apple MlX models downloaded from [Apple MLX Community repo in hugging face](https://huggingface.co/mlx-community) 🤗\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=kspviswa/pyOllaMx\u0026type=Date)](https://star-history.com/#kspviswa/pyOllaMx\u0026Date)\n\n## How to use?\n\n1) Install [Ollama Application](https://ollama.ai/download) \u0026 use Ollama CLI to download your desired models\n```\nollama pull \u003cmodel name\u003e\nollama pull mistral\n```\nThis command will download the Ollama models in a known location to PyOllaMx\n\n\u003e [!TIP]\n\u003e As of PyOllaMx v0.0.4, you can download \u0026 manage ollama models right within PyOllaMx's ModelHub. Check the [v0.0.4 release page](https://github.com/kspviswa/pyOllaMx/releases/tag/v0.0.4) for more details\n\n2) Install [MlX Models from Hugging Face repo](https://huggingface.co/mlx-community).\n\nuse hugging-face cli\n```\npip install huggingface_hub hf_transfer\n\nexport HF_HUB_ENABLE_HF_TRANSFER=1\nhuggingface-cli download mlx-community/CodeLlama-7b-Python-4bit-MLX\n```\nThis command will download the MlX models in a known location to PyOllaMx\n\n3) Now simply open the **PyOllaMx** and start chatting\n\n![sample](assets/pyollamx_sample_updated.png)\n\n## [v0.0.7 Features](https://github.com/kspviswa/pyOllaMx/releases/tag/v0.0.7)\n\n### New Functionality\n\nAdded supported to **thinking tokens** for reasoning models like DeepSeek-R1\n\n## [v0.0.4 Features](https://github.com/kspviswa/pyOllaMx/releases/tag/v0.0.4)\n\n### New Functionality\nNow you can download Ollama models right within 🤌🏻 PyOllaMx's Model Hub tab. You can also inspect existing models 🧐, delete models 🗑️ right within PyOllaMx instead of using Ollama CLI. This greatly simplifies the user experience 🤩🤩. And you before you ask, yes I'm working to bring similar functionality for MLX models from huggingface hub. Please stay tuned 😎\n\n### BugFixes\n1. Updated DDGS dependency to fix some of the rate limit issues\n\nClick the release version link above ☝🏻 to view demo gifs explaining the features.\n\n## [v0.0.3 Features](https://github.com/kspviswa/pyOllaMx/releases/tag/v0.0.3)\n\n1. Dark mode support - Toggle between Dark \u0026 Light mode with a click of the icon\n2. Model settings menu - Brand new settings menu to set the model name and the temperature along with Ollama \u0026 MlX model toggle\n3. Streaming support - Streaming support for both chat \u0026 search tasks\n4. Brand New Status bar - Status bar that displays the selected mode name, model type \u0026 model temperature\n5. Web search enabled for Apple MlX models - Now you can use Apple MlX models to power the web search when choosing the search tab\n\nClick the release version link above ☝🏻 to view demo gifs explaining the features.\n\n## [v0.0.2 Features](https://github.com/kspviswa/pyOllaMx/releases/tag/v0.0.2)\n\n1. Web search capability _(powered by DuckDuckGo search engine via https://github.com/deedy5/duckduckgo_search)_\n    a. Web search powered via basic RAG using prompt engineering. More advanced techniques are in pipeline\n    b. Search response will cite clickable sources for easy follow-up / deep dive\n    c. Beneath every search response, search keywords are also shown to verify the search scope\n    d. Easy toggle between chat and search operations \n2. Clear / Erase history \n3. Automatic scroll on chat messages for better user experience\n4. Basic error \u0026 exception handling for searches\n\nLimitations:\n\n- Web search only enabled for Ollama models. Use dolphin-mistral:7b model for better results. MlX model support is planned for next release\n- Search results aren't deterministic and vary vastly among the chosen models. So play with different models to find your optimum\n- Sometimes search results are gibberish. It is due to the fact that search engine RAG is vanilla i.e done via basic prompt engineering without any library support. So re-trigger the same search prompt and see the response once again if the results aren't satisfactory.\n\nClick the release version link above ☝🏻 to view demo gifs explaining the features.\n\n## [v0.0.1 Features](https://github.com/kspviswa/pyOllaMx/releases/tag/v0.0.1)\n\n- Auto discover Ollama \u0026 MlX models. Simply download the models as you do with respective tools and pyOllaMx would pull the models seamlessly\n- Markdown support on chat messages for programming code\n- Selectable Text\n- Temperature control\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkspviswa%2Fpyollamx","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkspviswa%2Fpyollamx","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkspviswa%2Fpyollamx/lists"}