Create INSTALL.md

INSTALL.md

@@ -0,0 +1,147 @@
+# AI Writer — Installation Guide
+
+## Quick Start (Local)
+
+### 1. Prerequisites
+
+- Python 3.9 or higher
+- pip package manager
+
+### 2. Install Dependencies
+
+```bash
+cd "AI Writer"
+pip install -r requirements.txt
+```
+
+### 3. Run the Application
+
+```bash
+python app.py
+```
+
+The application will start on `http://localhost:7860`.
+
+---
+
+## Hugging Face Spaces Deployment
+
+### 1. Create a New Space
+
+1. Go to [huggingface.co/spaces](https://huggingface.co/spaces)
+2. Click **Create new Space**
+3. Choose **Gradio** as the SDK
+4. Name your Space (e.g., `ai-writer`)
+
+### 2. Upload Files
+
+Upload all files from the `AI Writer` folder to your Space repository:
+
+```
+├── app.py
+├── requirements.txt
+├── system_prompt.md
+├── editor_prompt.md
+├── INSTALL.md
+├── README.md
+└── utils/
+    ├── __init__.py
+    ├── api_client.py
+    ├── docx_parser.py
+    ├── editor.py
+    └── style_analyzer.py
+```
+
+### 3. Set Environment Variables (Optional)
+
+If you want to set the API token as a secret environment variable:
+
+1. Go to your Space **Settings**
+2. Under **Repository secrets**, add:
+   - Name: `GLM_API_TOKEN`
+   - Value: your API token
+
+### 4. Space Will Build Automatically
+
+Hugging Face will install the dependencies from `requirements.txt` and launch `app.py`.
+
+---
+
+## Changing the GLM API Key
+
+### Method 1: Through the UI (Recommended)
+
+1. Open the AI Writer application
+2. Go to the **⚙️ API Settings** tab
+3. In the **API Token** field, paste your new token
+4. Click **🔍 Test Connection** to verify the token works
+5. The new token will be used for all subsequent requests in the current session
+
+> **Note:** The token set through the UI is stored only in the current session. It will reset to the default when you reload the page.
+
+### Method 2: Change the Default Token in Code
+
+1. Open `utils/api_client.py` in a text editor
+2. Find the line:
+   ```python
+   DEFAULT_TOKEN = "modalresearch_-z6GDDZ_VYtv7RlIuppxp5Vll50nSaDLtAOO-A5OnrI"
+   ```
+3. Replace the token value with your new token:
+   ```python
+   DEFAULT_TOKEN = "your_new_token_here"
+   ```
+4. Save the file and restart the application
+
+### Method 3: Environment Variable (Hugging Face Spaces)
+
+1. Go to your Space **Settings**
+2. Under **Repository secrets**, add or update:
+   - Name: `GLM_API_TOKEN`
+   - Value: your new API token
+3. The Space will restart automatically
+
+To use the environment variable, modify the `DEFAULT_TOKEN` in `utils/api_client.py`:
+
+```python
+import os
+DEFAULT_TOKEN = os.environ.get("GLM_API_TOKEN", "modalresearch_-z6GDDZ_VYtv7RlIuppxp5Vll50nSaDLtAOO-A5OnrI")
+```
+
+---
+
+## Changing the Model
+
+By default, the application uses `zai-org/GLM-5.1-FP8`. To change the model:
+
+1. Open the **⚙️ API Settings** tab in the UI
+2. Change the **Model Name** field to your desired model
+3. Or edit `utils/api_client.py` and change `DEFAULT_MODEL`
+
+---
+
+## Troubleshooting
+
+### API Connection Fails
+
+- Check your internet connection
+- Verify the API token is correct
+- Ensure the API endpoint URL is accessible from your network
+- The default endpoint is: `https://api.us-west-2.modal.direct/v1/chat/completions`
+
+### DOCX Files Not Loading
+
+- Ensure files are in `.docx` format (not `.doc` or `.txt`)
+- Try re-saving the file in Microsoft Word or LibreOffice
+- Check that the file is not password-protected
+
+### Generation Takes Too Long
+
+- Reduce the `max_words` parameter
+- Lower the `temperature` slightly
+- The API may have rate limits; wait a moment and try again
+
+### Generated Text Contains Dashes or Quotation Marks
+
+- The automated editor should remove these, but the LLM editor pass may reintroduce them
+- The system runs two editor passes (automated + LLM) to minimize this
+- If issues persist, try regenerating the article