Hass/ha-text-ai
1
0
Fork 0
mirror of https://github.com/smkrv/ha-text-ai.git synced 2026-07-29 12:33:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs:(README)

Browse Source
This commit is contained in:
SMKRV
2024-12-05 01:54:09 +03:00
parent 95f3d6506e
commit de194e425c
1 changed files with 37 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+37 -28
View File
@@ -99,38 +99,44 @@ Transform your smart home experience with powerful AI assistance powered by mult
- Python 3.9 or newer - Python 3.9 or newer
- Stable internet connection - Stable internet connection
### Configuration Options ## Configuration Options
- API Provider (OpenAI/Anthropic)
- API Key (provider-specific)
- Model Selection (flexible, provider-specific models)
- Temperature (Creativity control, 0.0-2.0)
- Max Tokens (Response length limit)
- Request Interval (API call throttling)
- Number of messages in history to keep (controls conversation memory size)
- Custom API Endpoint (optional)
#### ⓘ Potentially Compatible Providers ### 🔧 **Core Configuration Settings**
The integration is designed to be flexible and may work with other providers offering OpenAI-compatible APIs: - 🌐 **API Provider**: OpenAI/Anthropic
- Groq - 🔑 **API Key**: Provider-specific authentication
- Together AI - 🤖 **Model Selection**: Flexible, provider-specific models
- Perplexity AI - 🌡️ **Temperature**: Creativity control (0.0-2.0)
- Mistral AI - 📏 **Max Tokens**: Response length limit
- Google AI - ⏱️ **Request Interval**: API call throttling
- Local AI servers (like Ollama) - 💾 **History Size**: Number of messages to retain
- Custom OpenAI-compatible endpoints - 🌍 **Custom API Endpoint**: Optional advanced configuration
#### Additional Notes <details>
- Not all providers guarantee full compatibility <summary>🌐 Potentially Compatible Providers</summary>
- Performance may vary between providers
- Check individual provider's documentation #### Flexible Provider Ecosystem
The integration is designed to be flexible and may work with other providers offering OpenAI-compatible APIs:
- Groq
- Together AI
- Perplexity AI
- Mistral AI
- Google AI
- Local AI servers (like Ollama)
- Custom OpenAI-compatible endpoints
#### 🚨 Compatibility Notes
- Not all providers guarantee full compatibility
- Performance may vary between providers
- Check individual provider's documentation
- Ensure your API key has sufficient credits/quota - Ensure your API key has sufficient credits/quota
#### Provider Compatibility Requirements #### 🔍 Provider Compatibility Requirements
To be compatible, a provider should support: To be compatible, a provider should support:
- OpenAI-like REST API structure - OpenAI-like REST API structure
- JSON request/response format - JSON request/response format
- Standard authentication method - Standard authentication method
- Similar model parameter handling - Similar model parameter handling
</details>
## ⚡ Installation ## ⚡ Installation
@@ -159,7 +165,8 @@ To be compatible, a provider should support:
3. Search for "HA Text AI" 3. Search for "HA Text AI"
4. Follow the configuration steps 4. Follow the configuration steps
### Via YAML (Advanced) <details>
<summary>📦 Via YAML (Advanced)</summary>
### Platform Configuration (Global Settings) ### Platform Configuration (Global Settings)
@@ -217,6 +224,8 @@ sensor:
| `temperature` | Float | ❌ | Platform setting | Override global temperature | | `temperature` | Float | ❌ | Platform setting | Override global temperature |
| `max_tokens` | Integer | ❌ | Platform setting | Override global max tokens | | `max_tokens` | Integer | ❌ | Platform setting | Override global max tokens |
</details>
## 🛠️ Available Services ## 🛠️ Available Services
### ask_question ### ask_question