{"id":21141648,"url":"https://github.com/wendellast/gui","last_synced_at":"2025-07-09T05:32:07.242Z","repository":{"id":214917343,"uuid":"737673882","full_name":"wendellast/Gui","owner":"wendellast","description":" 👽 GUI is a personal AI developed in Python3. It is a great tool that can be used to improve communication and understanding.","archived":false,"fork":false,"pushed_at":"2024-11-12T20:56:51.000Z","size":224,"stargazers_count":9,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-12T21:35:40.301Z","etag":null,"topics":["assistive-technology","chatbot","gpt","ia","llm","personal-assistant","python3","streamlit","textual"],"latest_commit_sha":null,"homepage":"https://gui-ia.streamlit.app/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wendellast.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":"2024-01-01T02:56:15.000Z","updated_at":"2024-11-12T20:56:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"aa26935d-42d8-4bad-95cc-ad5100472659","html_url":"https://github.com/wendellast/Gui","commit_stats":null,"previous_names":["wendellast/gui"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wendellast%2FGui","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wendellast%2FGui/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wendellast%2FGui/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wendellast%2FGui/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wendellast","download_url":"https://codeload.github.com/wendellast/Gui/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225486803,"owners_count":17481972,"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":["assistive-technology","chatbot","gpt","ia","llm","personal-assistant","python3","streamlit","textual"],"created_at":"2024-11-20T07:32:44.682Z","updated_at":"2024-11-20T07:32:45.551Z","avatar_url":"https://github.com/wendellast.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GUI IA\n\nWelcome! The GUI is a virtual assistant designed to answer your questions in a friendly, fun, and interactive way. Created to be your digital companion, it provides engaging responses to make your experience more enjoyable.\n\n- **Model Used**: By default, we use the **meta-llama/Llama-3.2-3B-Instruct** model, but you can easily change it to any other model of your choice.\n\n## Recommended\n\n- Python 3.11.0 or higher\n- A Hugging Face account to obtain your API token\n\n## Installation\n\n1. **Clone the repository**:\n   ```bash\n   git clone https://github.com/wendellast/Gui.git\n   cd Gui\n   ```\n\n2. **Install the dependencies**:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. **Configure the `.env` file**:\n   - Rename the `.env-example` file to `.env`:\n     ```bash\n     mv .env-example .env\n     ```\n   - Edit the `.env` file and add your Hugging Face token:\n     ```\n     HUGGINGFACEHUB_API_TOKEN=your_token_here\n     ```\n   \u003e **Note**: You can get your Hugging Face API token at [Hugging Face Tokens](https://huggingface.co/settings/tokens).\n\n   \u003e **Note**: If you're using a graphical interface with `Python gui.py` you don't need the Hugging Face token; it works without it.\n\n## How to Run\n\n\n### option 1: Running via Server\nTo start the server, run:\n\n```bash\npython server.py\n```\n\nOpen your browser and go to `http://localhost:7860` to interact with the AI chatbot.\n\n\n### Option 2: Running via Graphical Interface\n\nTo start the server and open the graphical interface, simply run the following command:\n\n```bash\npython gui.py\n```\n\nThis will launch the application with the virtual assistant interface, where you can interact using voice or buttons.\n\n---\n\n## Speech Configuration\n\nThe virtual assistant uses speech synthesis to respond to the user. jWe recommend using the **Letícia** voice, a high-quality Brazilian voice, for the best experience.\n\n### 1. Using the **Letícia** Voice\n\nWe recommend using the **Letícia** voice. jTo set it up, follow these steps:\n\n- Visit the [Louderpages - Letícia](https://louderpages.org/leticia) website.\n- Github [Rhvoices](https://github.com/RHVoice/RHVoice)\n- Follow the instructions to configure the **Letícia** voice.\n\n### 2. Other Alternatives\n\nIf you prefer, you can also use other speech synthesis options:\n\n- **Espeak**: jAn open-source alternative.\n- **SAPI5 (Windows)**: jThe native speech synthesis API for Windows.\n\n## API\n\n### Example Usage via API:\n\n```python\nfrom gradio_client import Client\n\n# ==========TEST API==========\n\ndef response_gui(input_text):\n    client = Client(\"wendellast/GUI\")\n    result = client.predict(\n        message=input_text,\n        max_tokens=512,\n        temperature=0.7,\n        top_p=0.95,\n        api_name=\"/chat\",\n    )\n    return result\n\n# Example call:\ninput_text = \"Hello, how are you?\"\nresponse = response_gui(input_text)\nprint(\"AI Response:\", response)\n```\n\n### Usage via LangChain Model\n\nYou can also use the model directly via LangChain:\n\n- **Define the model** you want to use, such as `meta-llama/Llama-3.2-3B-Instruct`.\n- Configure your access token in the `.env` file.\n- Instantiate the wrapper for the model using the `GuiChat` class.\n\n### Supported Parameters:\n- `temperature`: Controls the randomness of the response.\n- `top_p`: Controls the diversity of the responses.\n- `repetition_penalty`: Penalizes repetitions for more varied answers.\n- `max_new_tokens`: Maximum number of tokens generated in the response.\n\n**Example usage**:\n```python\nfrom util.token_access import load_token\nfrom your_package import GuiChat\n\ntoken = load_token()\nchatbot = GuiChat(auth_token=token)\n\nwhile True:\n    question = input(\"Ask here: \")\n    answer = chatbot._call(question)\n    print(f\"Response: {answer}\")\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwendellast%2Fgui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwendellast%2Fgui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwendellast%2Fgui/lists"}