fix(api_client): correct Google Gemini API integration

- Change JSON field names from camelCase to snake_case as required by Gemini API
  (generation_config, max_output_tokens, system_instruction)
- Improve message handling to ensure proper role alternation (user/model)
- Add safety checks for empty contents and ensure first message is always from user
- Implement robust error handling and response parsing
- Handle edge cases where candidatesTokenCount might be returned as a list

Fixes #6

.gitignore

@@ -1,41 +0,0 @@
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-*.so
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-
-# Home Assistant
-.storage
-.cloud
-.google.token
-
-# IDE
-.idea/
-.vscode/
-*.swp
-*.swo
-*~
-
-# OS
-.DS_Store
-Thumbs.db
-*.psd
-*.zip
-*.txt
-*.pdf

README.md

@@ -2,8 +2,8 @@
 
 <div align="center">  
 
-  ![GitHub release](https://img.shields.io/github/release/smkrv/ha-text-ai.svg?style=flat-square) ![GitHub last commit](https://img.shields.io/github/last-commit/smkrv/ha-text-ai.svg?style=flat-square) [![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg?style=flat-square)](https://creativecommons.org/licenses/by-nc-sa/4.0/) [![hacs_badge](https://img.shields.io/badge/HACS-Custom-41BDF5.svg?style=flat-square)](https://github.com/hacs/integration)  
-![Deutsch](https://img.shields.io/badge/de-Deutsch-blue?style=flat-square) ![English](https://img.shields.io/badge/en-English-blue?style=flat-square) ![Español](https://img.shields.io/badge/es-Español-blue?style=flat-square) ![हिन्दी](https://img.shields.io/badge/hi-हिन्दी-blue?style=flat-square) ![Italiano](https://img.shields.io/badge/it-Italiano-blue?style=flat-square) ![Русский](https://img.shields.io/badge/ru-Русский-blue?style=flat-square) ![Српски](https://img.shields.io/badge/sr-Српски-blue?style=flat-square) ![中文](https://img.shields.io/badge/zh-中文-blue?style=flat-square)
+  ![GitHub release](https://img.shields.io/github/v/release/smkrv/ha-text-ai?style=flat-square) ![GitHub last commit](https://img.shields.io/github/last-commit/smkrv/ha-text-ai?style=flat-square) [![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg?style=flat-square)](https://creativecommons.org/licenses/by-nc-sa/4.0/) [![hacs_badge](https://img.shields.io/badge/HACS-Custom-41BDF5.svg?style=flat-square)](https://github.com/hacs/integration)  
+  ![Deutsch](https://img.shields.io/badge/lang-DE-blue?style=flat-square) ![English](https://img.shields.io/badge/lang-EN-blue?style=flat-square) ![Español](https://img.shields.io/badge/lang-ES-blue?style=flat-square) ![हिन्दी](https://img.shields.io/badge/lang-HI-blue?style=flat-square) ![Italiano](https://img.shields.io/badge/lang-IT-blue?style=flat-square) ![Русский](https://img.shields.io/badge/lang-RU-blue?style=flat-square) ![Српски](https://img.shields.io/badge/lang-SR-blue?style=flat-square) ![中文](https://img.shields.io/badge/lang-ZH-blue?style=flat-square)
 
 
   <img src="https://github.com/smkrv/ha-text-ai/blob/15c717fcb0204bf4a0d4b4b4c6f0bb93e9f6c9a9/custom_components/ha_text_ai/icons/logo%402x.png" alt="HA Text AI" style="width: 50%; max-width: 256px; max-height: 128px; aspect-ratio: 2/1; object-fit: contain;"/>
@@ -12,22 +12,23 @@
 </div>
 
 <p align="center">
-Transform your smart home experience with powerful AI assistance powered by multiple AI providers including OpenAI GPT and Anthropic Claude models. Get intelligent responses, automate complex scenarios, and enhance your home automation with advanced natural language processing.
+Transform your smart home experience with powerful AI assistance powered by multiple AI providers including OpenAI GPT, DeepSeek and Anthropic Claude models. Get intelligent responses, automate complex scenarios, and enhance your home automation with advanced natural language processing.
 
 </p>
 
 ---
 
 > [!IMPORTANT]
-> 🤝 Community Driven  
+> 🤝 Community Driven: for more details on the integration,   
+> check out the discussion on the **[Home Assistant Community forum](https://community.home-assistant.io/t/ha-text-ai-transforming-home-automation-through-multi-llm-integration/799741)**
 >
->  <a href="https://community.home-assistant.io/t/ha-text-ai-transforming-home-automation-with-multi-provider-language-models/799741"><img src="https://img.shields.io/badge/Community-blue?style=for-the-badge&logo=homeassistant&logoColor=white&color=03a9f4"/></a>  
+>  <a href="https://my.home-assistant.io/redirect/hacs_repository/?owner=smkrv&repository=ha-text-ai&category=Integration"><img src="https://my.home-assistant.io/badges/hacs_repository.svg" width="210" height="auto"></a>
 >  
 > [Screenshots](assets/images/screenshots/screenshot.jpg)
 
 ## 🌟 Features
 
-- 🧠 **Multi-Provider AI Integration**: Support for OpenAI GPT and Anthropic Claude models
+- 🧠 **Multi-Provider AI Integration**: Support for OpenAI GPT, DeepSeek and Anthropic Claude models
 - 💬 **Advanced Language Processing**: Context-aware, multi-turn conversations
 - 📝 **Enhanced Memory Management**: Secure file-based history storage
 - ⚡ **Performance Optimization**: Efficient token usage and smart rate limiting
@@ -42,6 +43,7 @@ Transform your smart home experience with powerful AI assistance powered by mult
 ### 🧠 **Multi-Provider AI Integration**
 - Support for OpenAI GPT models
 - Anthropic Claude integration
+- DeepSeek integration
 - Custom API endpoints
 - Flexible model selection
 
@@ -104,12 +106,13 @@ Transform your smart home experience with powerful AI assistance powered by mult
 
 ## 📋 Prerequisites
 
-- Home Assistant 2024.11 or later
+- Home Assistant 2024.2.2 or later
 - Active API key from:
   - OpenAI ([Get key](https://platform.openai.com/account/api-keys))
   - Anthropic ([Get key](https://console.anthropic.com/))
-  - DeepSeek 🆕 ([Get key](https://platform.deepseek.com/api_keys)) 
+  - DeepSeek ([Get key](https://platform.deepseek.com/api_keys))
   - OpenRouter ([Get key](https://openrouter.ai/keys))
+  - Google Gemini 🆕 ([Get key](https://ai.google.dev/gemini-api/docs/api-key)) thanks to ([@Azzedde](https://github.com/Azzedde))
   - Any OpenAI-compatible API provider
 - Python 3.9 or newer
 - Stable internet connection
@@ -117,7 +120,7 @@ Transform your smart home experience with powerful AI assistance powered by mult
 ## Configuration Options
 
 ### 🔧 **Core Configuration Settings**
-- 🌐 **API Provider**: OpenAI/Anthropic
+- 🌐 **API Provider**: OpenAI/Anthropic/DeepSeek
 - 🔑 **API Key**: Provider-specific authentication
 - 🤖 **Model Selection**: Flexible, provider-specific models
 - 🌡️ **Temperature**: Creativity control (0.0-2.0)
@@ -157,6 +160,9 @@ To be compatible, a provider should support:
 ## ⚡ Installation
 
 ### HACS Installation (Recommended)
+>[!TIP]
+>HA Text AI is available in the default HACS repository. You can install it directly through HACS or click the button below to open it there.
+
 <a href="https://my.home-assistant.io/redirect/hacs_repository/?owner=smkrv&repository=ha-text-ai&category=Integration"><img src="https://my.home-assistant.io/badges/hacs_repository.svg" width="170" height="auto"></a>
 1. Open HACS in Home Assistant
 2. Click on "Integrations"
@@ -167,8 +173,6 @@ To be compatible, a provider should support:
 7. Click "Download"
 8. Restart Home Assistant
 
-Note: Also Integration has been submitted to HACS store and is currently pending review in [pull request #2896](https://github.com/hacs/default/pull/2896).
-
 ### Manual Installation
 1. Download the latest release
 2. Extract and copy `custom_components/ha_text_ai` to your `custom_components` directory

custom_components/ha_text_ai/__init__.py

@@ -40,13 +40,16 @@ from .const import (
     API_PROVIDER_OPENAI,
     API_PROVIDER_ANTHROPIC,
     API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_GEMINI,
     DEFAULT_MODEL,
     DEFAULT_DEEPSEEK_MODEL,
+    DEFAULT_GEMINI_MODEL,
     DEFAULT_TEMPERATURE,
     DEFAULT_MAX_TOKENS,
     DEFAULT_OPENAI_ENDPOINT,
     DEFAULT_ANTHROPIC_ENDPOINT,
     DEFAULT_DEEPSEEK_ENDPOINT,
+    DEFAULT_GEMINI_ENDPOINT,
     DEFAULT_REQUEST_INTERVAL,
     DEFAULT_CONTEXT_MESSAGES,
     API_TIMEOUT,

custom_components/ha_text_ai/api_client.py

@@ -20,6 +20,7 @@ from .const import (
     API_PROVIDER_ANTHROPIC,
     API_PROVIDER_DEEPSEEK,
     API_PROVIDER_OPENAI,
+    API_PROVIDER_GEMINI,
     MIN_TEMPERATURE,
     MAX_TEMPERATURE,
     MIN_MAX_TOKENS,
@@ -115,6 +116,10 @@ class APIClient:
                 return await self._create_deepseek_completion(
                     model, messages, temperature, max_tokens
                 )
+            elif self.api_provider == API_PROVIDER_GEMINI:
+                return await self._create_gemini_completion(
+                    model, messages, temperature, max_tokens
+                )
             else:
                 return await self._create_openai_completion(
                     model, messages, temperature, max_tokens
@@ -238,6 +243,124 @@ class APIClient:
             _LOGGER.error(f"Connection check failed: {str(e)}")
             return False
 
+    async def _create_gemini_completion(
+        self,
+        model: str,
+        messages: List[Dict[str, str]],
+        temperature: float,
+        max_tokens: int,
+    ) -> Dict[str, Any]:
+        """Create completion using Gemini API."""
+        # Extract API key from headers (Bearer token)
+        api_key = self.headers.get("Authorization", "").replace("Bearer ", "")
+        url = f"{self.endpoint}/models/{model}:generateContent?key={api_key}"
+
+        # Convert messages to Gemini format
+        contents = []
+        system_instruction = ""
+
+        # Process messages and ensure proper role alternation
+        current_role = None
+        current_content = ""
+
+        for msg in messages:
+            if msg['role'] == 'system':
+                system_instruction += msg['content'] + "\n"
+            else:
+                role = "user" if msg['role'] == 'user' else "model"
+
+                # If same role as previous, combine content
+                if role == current_role:
+                    current_content += "\n" + msg['content']
+                else:
+                    # Add previous message if exists
+                    if current_role is not None:
+                        contents.append({
+                            "role": current_role,
+                            "parts": [{"text": current_content}]
+                        })
+                    # Start new message
+                    current_role = role
+                    current_content = msg['content']
+
+        # Add the last message if exists
+        if current_role is not None:
+            contents.append({
+                "role": current_role,
+                "parts": [{"text": current_content}]
+            })
+
+        # Ensure contents starts with user message if not empty
+        if contents and contents[0]["role"] != "user":
+            # Add a placeholder user message if needed
+            contents.insert(0, {
+                "role": "user",
+                "parts": [{"text": "I need your assistance."}]
+            })
+
+        # Ensure contents is not empty
+        if not contents:
+            contents.append({
+                "role": "user",
+                "parts": [{"text": "I need your assistance."}]
+            })
+
+        # Create payload with snake_case keys as required by Gemini API
+        payload = {
+            "contents": contents,
+            "generation_config": {  # Changed from camelCase to snake_case
+                "temperature": temperature,
+                "max_output_tokens": max_tokens  # Changed from camelCase to snake_case
+            }
+        }
+
+        if system_instruction:
+            payload["system_instruction"] = {  # Changed from camelCase to snake_case
+                "parts": [{"text": system_instruction.strip()}]
+            }
+
+        try:
+            data = await self._make_request(url, payload)
+
+            # Safely extract response data with fallbacks
+            candidates = data.get("candidates", [])
+            if not candidates:
+                raise HomeAssistantError("Gemini API returned no candidates")
+
+            content = candidates[0].get("content", {})
+            parts = content.get("parts", [])
+            if not parts:
+                raise HomeAssistantError("Gemini API response contains no content parts")
+
+            answer_text = parts[0].get("text", "")
+
+            # Safely extract usage data
+            usage = data.get("usageMetadata", {})
+            prompt_tokens = usage.get("promptTokenCount", 0)
+            completion_tokens = usage.get("candidatesTokenCount", 0)
+
+            # Handle case where candidatesTokenCount might be a list
+            if isinstance(completion_tokens, list):
+                completion_tokens = sum(completion_tokens)
+
+            total_tokens = usage.get("totalTokenCount", prompt_tokens + completion_tokens)
+
+            return {
+                "choices": [{
+                    "message": {
+                        "content": answer_text
+                    }
+                }],
+                "usage": {
+                    "prompt_tokens": prompt_tokens,
+                    "completion_tokens": completion_tokens,
+                    "total_tokens": total_tokens
+                }
+            }
+        except Exception as e:
+            _LOGGER.error(f"Gemini API error: {str(e)}")
+            raise HomeAssistantError(f"Gemini API error: {str(e)}")
+
     async def shutdown(self) -> None:
         """Shutdown API client."""
         _LOGGER.debug("Shutting down API client")

custom_components/ha_text_ai/config_flow.py

@@ -29,15 +29,18 @@ from .const import (
     API_PROVIDER_OPENAI,
     API_PROVIDER_ANTHROPIC,
     API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_GEMINI,
     API_PROVIDERS,
     DEFAULT_MODEL,
     DEFAULT_DEEPSEEK_MODEL,
+    DEFAULT_GEMINI_MODEL,
     DEFAULT_TEMPERATURE,
     DEFAULT_MAX_TOKENS,
     DEFAULT_REQUEST_INTERVAL,
     DEFAULT_OPENAI_ENDPOINT,
     DEFAULT_ANTHROPIC_ENDPOINT,
     DEFAULT_DEEPSEEK_ENDPOINT,
+    DEFAULT_GEMINI_ENDPOINT,
     DEFAULT_CONTEXT_MESSAGES,
     MIN_TEMPERATURE,
     MAX_TEMPERATURE,
@@ -93,15 +96,20 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
         self._errors = {}
 
         if user_input is None:
-            # Выбор endpoint по провайдеру
+            # Selecting an endpoint by provider
             default_endpoint = {
                 API_PROVIDER_OPENAI: DEFAULT_OPENAI_ENDPOINT,
                 API_PROVIDER_ANTHROPIC: DEFAULT_ANTHROPIC_ENDPOINT,
                 API_PROVIDER_DEEPSEEK: DEFAULT_DEEPSEEK_ENDPOINT,
+                API_PROVIDER_GEMINI: DEFAULT_GEMINI_ENDPOINT,
             }.get(self._provider, DEFAULT_OPENAI_ENDPOINT)
 
-            # Выбор модели по умолчанию по провайдеру
-            default_model = DEFAULT_DEEPSEEK_MODEL if self._provider == API_PROVIDER_DEEPSEEK else DEFAULT_MODEL
+            # Selecting the default model by provider
+            default_model = (
+                DEFAULT_DEEPSEEK_MODEL if self._provider == API_PROVIDER_DEEPSEEK else
+                DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else
+                DEFAULT_MODEL
+            )
 
             return self.async_show_form(
                 step_id="provider",
@@ -256,7 +264,11 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
 
         unique_id = f"{DOMAIN}_{normalized_name}_{self._provider}".lower()
 
-        default_model = DEFAULT_DEEPSEEK_MODEL if self._provider == API_PROVIDER_DEEPSEEK else DEFAULT_MODEL
+        default_model = (
+            DEFAULT_DEEPSEEK_MODEL if self._provider == API_PROVIDER_DEEPSEEK else
+            DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else
+            DEFAULT_MODEL
+        )
 
         entry_data = {
             CONF_API_PROVIDER: self._provider,
@@ -304,6 +316,13 @@ class OptionsFlowHandler(config_entries.OptionsFlow):
             return self.async_create_entry(title="", data=user_input)
 
         current_data = {**self.config_entry.data, **self.config_entry.options}
+        provider = current_data.get(CONF_API_PROVIDER)
+
+        default_model = (
+            DEFAULT_DEEPSEEK_MODEL if provider == API_PROVIDER_DEEPSEEK else
+            DEFAULT_GEMINI_MODEL if provider == API_PROVIDER_GEMINI else
+            DEFAULT_MODEL
+        )
 
         return self.async_show_form(
             step_id="init",

custom_components/ha_text_ai/const.py

@@ -12,6 +12,8 @@ from typing import Final
 import voluptuous as vol
 from homeassistant.const import Platform, CONF_API_KEY, CONF_NAME
 from homeassistant.helpers import config_validation as cv
+import logging
+_LOGGER = logging.getLogger(__name__)
 
 # Domain and platforms
 DOMAIN: Final = "ha_text_ai"
@@ -22,11 +24,13 @@ CONF_API_PROVIDER: Final = "api_provider"
 API_PROVIDER_OPENAI: Final = "openai"
 API_PROVIDER_ANTHROPIC: Final = "anthropic"
 API_PROVIDER_DEEPSEEK: Final = "deepseek"
+API_PROVIDER_GEMINI: Final = "gemini"
 
 API_PROVIDERS: Final = [
     API_PROVIDER_OPENAI,
     API_PROVIDER_ANTHROPIC,
-    API_PROVIDER_DEEPSEEK
+    API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_GEMINI
 ]
 
 # Read version from manifest.json
@@ -49,6 +53,7 @@ except Exception as err:
 DEFAULT_OPENAI_ENDPOINT: Final = "https://api.openai.com/v1"
 DEFAULT_ANTHROPIC_ENDPOINT: Final = "https://api.anthropic.com"
 DEFAULT_DEEPSEEK_ENDPOINT: Final = "https://api.deepseek.com"
+DEFAULT_GEMINI_ENDPOINT: Final = "https://generativelanguage.googleapis.com/v1beta"
 
 # Configuration constants
 CONF_MODEL: Final = "model"
@@ -69,6 +74,7 @@ ICONS_SUBDOMAIN = "icons"
 # Default values
 DEFAULT_MODEL: Final = "gpt-4o-mini"
 DEFAULT_DEEPSEEK_MODEL: Final = "deepseek-chat"
+DEFAULT_GEMINI_MODEL: Final = "gemini-pro"
 DEFAULT_TEMPERATURE: Final = 0.1
 DEFAULT_MAX_TOKENS: Final = 1000
 DEFAULT_REQUEST_INTERVAL: Final = 1.0

custom_components/ha_text_ai/manifest.json

@@ -16,6 +16,7 @@
     "requirements": [
       "openai>=1.12.0",
       "anthropic>=0.8.0",
+      "google-generativeai>=0.3.0",
       "aiohttp>=3.8.0",
       "async-timeout>=4.0.0",
       "certifi>=2024.2.2"
@@ -23,6 +24,6 @@
   "single_config_entry": false,
   "ssdp": [],
   "usb": [],
-  "version": "2.1.1",
+  "version": "2.1.4",
   "zeroconf": []
 }

custom_components/ha_text_ai/services.yaml

@@ -63,13 +63,13 @@ ask_question:
 
     max_tokens:
       name: Max Tokens
-      description: Maximum length of the response (1-4096 tokens)
+      description: Maximum length of the response (tokens)
       required: false
       default: 1000
       selector:
         number:
           min: 1
-          max: 4096
+          max: 100000
           step: 1
           mode: box
 

custom_components/ha_text_ai/translations/de.json

@@ -88,12 +88,13 @@
   "selector": {
     "api_provider": {
       "options": {
-        "openai": "OpenAI (kompatibel)",
-        "anthropic": "Anthropic (kompatibel)",
-        "deepseek": "DeepSeek"
-      }
+        "openai": "OpenAI (compatible)",
+        "anthropic": "Anthropic (compatible)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
     }
-  },
+  }
+},
   "services": {
     "ask_question": {
       "name": "Frage stellen (HA Text AI)",

custom_components/ha_text_ai/translations/en.json

@@ -86,11 +86,12 @@
     }
   },
   "selector": {
-  "api_provider": {
-    "options": {
-      "openai": "OpenAI (compatible)",
-      "anthropic": "Anthropic (compatible)",
-      "deepseek": "DeepSeek"
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (compatible)",
+        "anthropic": "Anthropic (compatible)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
     }
   }
 },

custom_components/ha_text_ai/translations/es.json

@@ -90,10 +90,11 @@
       "options": {
         "openai": "OpenAI (compatible)",
         "anthropic": "Anthropic (compatible)",
-        "deepseek": "DeepSeek"
-      }
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
     }
-  },
+  }
+},
   "services": {
     "ask_question": {
       "name": "Hacer Pregunta (HA Text AI)",

custom_components/ha_text_ai/translations/hi.json

@@ -90,7 +90,8 @@
       "options": {
         "openai": "OpenAI (अनुकूलित)",
         "anthropic": "Anthropic (अनुकूलित)",
-        "deepseek": "DeepSeek"
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
       }
     }
   },

custom_components/ha_text_ai/translations/it.json

@@ -90,7 +90,8 @@
       "options": {
         "openai": "OpenAI (compatibile)",
         "anthropic": "Anthropic (compatibile)",
-        "deepseek": "DeepSeek"
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
       }
     }
   },

custom_components/ha_text_ai/translations/ru.json

@@ -90,7 +90,8 @@
       "options": {
         "openai": "OpenAI (совместимый)",
         "anthropic": "Anthropic (совместимый)",
-        "deepseek": "DeepSeek"
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
       }
     }
   },

custom_components/ha_text_ai/translations/sr.json

@@ -90,7 +90,8 @@
       "options": {
         "openai": "OpenAI (компатибилан)",
         "anthropic": "Anthropic (компатибилан)",
-        "deepseek": "DeepSeek"
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
       }
     }
   },

custom_components/ha_text_ai/translations/zh.json

@@ -90,7 +90,8 @@
       "options": {
         "openai": "OpenAI（兼容）",
         "anthropic": "Anthropic（兼容）",
-        "deepseek": "DeepSeek "
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
       }
     }
   },

hacs.json

@@ -1,5 +1,5 @@
 {
-  "name": "HA text AI",
+  "name": "HA Text AI",
   "render_readme": true,
   "homeassistant": "2024.11.0"
 }