Update README.md

This commit is contained in:
smkrv
2024-11-14 18:43:19 +03:00
committed by GitHub
parent b00bd9530e
commit 5f129d9245
+83
View File
@@ -1,3 +1,5 @@
`README.md`:
```markdown
# HA Text AI Integration
A Home Assistant integration that provides a bridge to OpenAI-compatible API services with automatic Text Helper management.
@@ -55,3 +57,84 @@ data:
top_p: 1.0 # Optional
frequency_penalty: 0.0 # Optional
presence_penalty: 0.0 # Optional
```
### Using the Blueprint
1. Go to Settings -> Automations & Scenes
2. Click the "Add Blueprint" button
3. Import this URL: `[Your Repository URL]/blueprints/automation/ha_text_ai_request.yaml`
4. Create a new automation using the blueprint
5. Configure the trigger and prompt template
### Accessing Responses
Responses are automatically stored in Text Helpers with the format `input_text.text_ai_response_[response_id]`
Example template to access a response:
```yaml
{{ states('input_text.text_ai_response_automation_joke') }}
```
## Blueprint Configuration Example
```yaml
trigger_entity: sensor.temperature
prompt_template: "Tell me a joke about {{ states('sensor.temperature') }} degree weather"
response_id: weather_joke
model: gpt-3.5-turbo
temperature: 0.7
max_tokens: 150
```
## Advanced Usage
### Custom API Endpoints
To use with Azure OpenAI or other compatible services, set the API Base URL during configuration:
- Azure OpenAI: `https://your-resource-name.openai.azure.com`
- Other Compatible APIs: Your API endpoint URL
### Rate Limiting
The integration includes built-in rate limiting:
- Requests are queued and processed according to the configured interval
- Default interval is 2 seconds
- Can be adjusted in the integration options
## Troubleshooting
Common issues and solutions:
1. **Response not appearing:**
- Check if the Text Helper was created (`input_text.text_ai_response_[your_id]`)
- Verify your API key permissions
2. **API errors:**
- Check your API key
- Verify the API endpoint URL
- Ensure you have sufficient API credits
3. **Rate limiting:**
- Adjust the request interval in the integration options
- Check for multiple automations making simultaneous requests
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Open a Pull Request
## License
This project is licensed under the MIT License - see the LICENSE file for details.
## Support
If you have any questions or need help, please:
1. Open an [issue] https://github.com/smkrv/ha-text-ai/issues