Supports integration of two models from DeepSeek for analysis!

2025-02-12 01:45:45 +08:00
parent 12a8732bd2
commit 82089852c9
3 changed files with 74 additions and 6 deletions
@@ -42,7 +42,10 @@
 - [MySQL](https://www.mysql.com/) 数据库
 - [Conda](https://docs.conda.io/en/latest/)（可选，用于环境管理）
 - 合法的微博账号（用于数据采集）
- OpenAI API密钥或Anthropic（Claude）API密钥（用于AI分析功能）
+- 以下API密钥中至少需要一个（用于AI分析功能）：
+  - OpenAI API密钥
+  - Anthropic（Claude）API密钥
+  - DeepSeek API密钥

 ### 安装步骤

@@ -78,9 +81,17 @@
   
   # Anthropic API配置（使用Claude模型必需）
   export ANTHROPIC_API_KEY="你的anthropic密钥"
+   
+   # DeepSeek API配置（使用DeepSeek模型必需）
+   export DEEPSEEK_API_KEY="你的deepseek密钥"
   ```
   
   注意：至少需要配置一个API密钥才能使用AI分析功能。
+   
+   支持的AI模型：
+   - OpenAI：GPT-3.5-Turbo、GPT-4
+   - Anthropic：Claude-3（Opus、Sonnet、Haiku）
+   - DeepSeek：DeepSeek-V3（deepseek-chat）、DeepSeek-R1（deepseek-reasoner）

 5. 启动Flask应用：

@@ -106,6 +117,7 @@
 - **[TensorFlow](https://www.tensorflow.org/)** 或 **[PyTorch](https://pytorch.org/)** - 深度学习框架，用于高级模型开发。
 - **[OpenAI GPT](https://openai.com/)** - 先进的语言模型，用于文本分析。
 - **[Anthropic Claude](https://www.anthropic.com/)** - 智能AI模型，用于复杂文本分析。
+- **[DeepSeek](https://deepseek.com/)** - 先进的中英双语AI模型。

 ## 🤝 贡献

@@ -40,7 +40,10 @@ Follow the steps below to run the project on your system.
 - [MySQL](https://www.mysql.com/) Database
 - [Conda](https://docs.conda.io/en/latest/) (optional, for environment management)
 - A valid Weibo account (for data collection)
- OpenAI API key or Anthropic (Claude) API key for AI analysis features
+- At least one of the following API keys for AI analysis features:
+  - OpenAI API key
+  - Anthropic (Claude) API key
+  - DeepSeek API key

 ### Installation Steps

@@ -76,9 +79,17 @@ Follow the steps below to run the project on your system.
   
   # For Anthropic API (Required for Claude models)
   export ANTHROPIC_API_KEY="your-anthropic-key"
+   
+   # For DeepSeek API (Required for DeepSeek models)
+   export DEEPSEEK_API_KEY="your-deepseek-key"
   ```
   
   Note: At least one API key must be configured to use AI analysis features.
+   
+   Supported AI Models:
+   - OpenAI: GPT-3.5-Turbo, GPT-4
+   - Anthropic: Claude-3 (Opus, Sonnet, Haiku)
+   - DeepSeek: DeepSeek-V3 (deepseek-chat), DeepSeek-R1 (deepseek-reasoner)

 6. Start the Flask application:

@@ -104,6 +115,7 @@ The Weibo Public Opinion Analysis and Prediction System employs a range of moder
 - **[TensorFlow](https://www.tensorflow.org/)** 或 **[PyTorch](https://pytorch.org/)** - Deep learning frameworks used for advanced model development.
 - **[OpenAI GPT](https://openai.com/)** - Advanced language models for text analysis.
 - **[Anthropic Claude](https://www.anthropic.com/)** - AI models for sophisticated text analysis.
+- **[DeepSeek](https://deepseek.com/)** - Advanced Chinese-English bilingual AI models.

 ## 🤝 Contribution

@@ -11,14 +11,21 @@ class AIAnalyzer:
        # 从环境变量获取API密钥
        self.openai_key = os.getenv('OPENAI_API_KEY')
        self.claude_key = os.getenv('ANTHROPIC_API_KEY')
+        self.deepseek_key = os.getenv('DEEPSEEK_API_KEY')
        
-        if not self.openai_key and not self.claude_key:
-            raise ValueError("请至少设置一个API密钥 (OPENAI_API_KEY 或 ANTHROPIC_API_KEY)")
+        if not any([self.openai_key, self.claude_key, self.deepseek_key]):
+            raise ValueError("请至少设置一个API密钥 (OPENAI_API_KEY, ANTHROPIC_API_KEY 或 DEEPSEEK_API_KEY)")
        
        if self.openai_key:
            openai.api_key = self.openai_key
        if self.claude_key:
            self.claude_client = anthropic.Anthropic(api_key=self.claude_key)
+        if self.deepseek_key:
+            # 配置DeepSeek API
+            self.deepseek_client = openai.OpenAI(
+                api_key=self.deepseek_key,
+                base_url="https://api.deepseek.com/v1"
+            )
        
        # 支持的模型列表
        self.supported_models = {
@@ -35,7 +42,11 @@ class AIAnalyzer:
            'claude-3-haiku-20240307': {'provider': 'anthropic', 'max_tokens': 2000, 'cost_per_1k': 0.0025},
            'claude-2.1': {'provider': 'anthropic', 'max_tokens': 100000, 'cost_per_1k': 0.008},
            'claude-2.0': {'provider': 'anthropic', 'max_tokens': 100000, 'cost_per_1k': 0.008},
-            'claude-instant-1.2': {'provider': 'anthropic', 'max_tokens': 100000, 'cost_per_1k': 0.0015}
+            'claude-instant-1.2': {'provider': 'anthropic', 'max_tokens': 100000, 'cost_per_1k': 0.0015},
+            
+            # DeepSeek 模型
+            'deepseek-chat': {'provider': 'deepseek', 'max_tokens': 4000, 'cost_per_1k': 0.002},  # DeepSeek-V3
+            'deepseek-reasoner': {'provider': 'deepseek', 'max_tokens': 4000, 'cost_per_1k': 0.003}  # DeepSeek-R1
        }
        
        # 不同深度的分析提示词
@@ -129,13 +140,20 @@ class AIAnalyzer:
                        model_type, 
                        max_tokens
                    )
-                else:  # anthropic
+                elif provider == 'anthropic':
                    result = await self._analyze_with_claude(
                        messages_text, 
                        system_prompt, 
                        model_type, 
                        max_tokens
                    )
+                elif provider == 'deepseek':
+                    result = await self._analyze_with_deepseek(
+                        messages_text,
+                        system_prompt,
+                        model_type,
+                        max_tokens
+                    )
                
                if result:
                    all_results.extend(result)
@@ -235,6 +253,32 @@ class AIAnalyzer:
            logging.error(f"Claude API调用失败: {e}")
            return []
    
+    async def _analyze_with_deepseek(self, messages_text: str, system_prompt: str, 
+                                   model: str, max_tokens: int) -> List[Dict]:
+        """使用DeepSeek API进行分析"""
+        try:
+            response = await self.deepseek_client.chat.completions.create(
+                model=model,
+                messages=[
+                    {"role": "system", "content": system_prompt},
+                    {"role": "user", "content": f"请分析以下消息:\n{messages_text}"}
+                ],
+                temperature=0.3,
+                max_tokens=max_tokens,
+                response_format={"type": "json_object"}  # 强制JSON响应格式
+            )
+            
+            result = json.loads(response.choices[0].message.content)
+            if isinstance(result, dict) and 'analysis_results' in result:
+                return result['analysis_results']
+            else:
+                logging.error(f"DeepSeek API返回格式不正确: {response.choices[0].message.content}")
+                return []
+                
+        except Exception as e:
+            logging.error(f"DeepSeek API调用失败: {e}")
+            return []
+    
    def format_analysis_for_display(self, analysis: Dict) -> Dict:
        """将分析结果格式化为前端显示格式"""
        base_result = {