panda/bettafish-company
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.

Browse Source
This commit is contained in:
666ghj
2025-10-09 14:50:44 +08:00
parent a3f6aa4ff7
commit 9b16ff60f6
2 changed files with 70 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README-EN.md
+35 -47
View File
@@ -23,7 +23,9 @@
## ⚡ Project Overview ## ⚡ Project Overview
**"WeiYu"** is an innovative multi-agent public opinion analysis system built from scratch, not limited to Weibo, and features universal simplicity and applicability across all platforms. **"BettaFish"** is an innovative multi-agent public opinion analysis system built from scratch. It helps break information cocoons, restore the original public sentiment, predict future trends, and assist decision-making. Users only need to raise analysis needs like chatting; the agents automatically analyze 30+ mainstream social platforms at home and abroad and millions of public comments.
> Betta is a small yet combative and beautiful fish, symbolizing "small but powerful, fearless of challenges".
See the system-generated research report on "Wuhan University Public Opinion": [In-depth Analysis Report on Wuhan University's Brand Reputation](./final_reports/final_report__20250827_131630.html) See the system-generated research report on "Wuhan University Public Opinion": [In-depth Analysis Report on Wuhan University's Brand Reputation](./final_reports/final_report__20250827_131630.html)
@@ -103,10 +105,7 @@ Weibo_PublicOpinion_AnalysisSystem/
├── InsightEngine/ # Private database mining Agent ├── InsightEngine/ # Private database mining Agent
│ ├── agent.py # Agent main logic │ ├── agent.py # Agent main logic
│ ├── llms/ # LLM interface wrapper │ ├── llms/ # LLM interface wrapper
│ │ ├── deepseek.py # DeepSeek API │ │ └── base.py # Unified OpenAI-compatible client
│ │ ├── kimi.py # Kimi API
│ │ ├── openai_llm.py # OpenAI format API
│ │ └── base.py # LLM base class
│ ├── nodes/ # Processing nodes │ ├── nodes/ # Processing nodes
│ │ ├── base_node.py # Base node class │ │ ├── base_node.py # Base node class
│ │ ├── formatting_node.py # Formatting node │ │ ├── formatting_node.py # Formatting node
@@ -130,7 +129,6 @@ Weibo_PublicOpinion_AnalysisSystem/
├── ReportEngine/ # Multi-round report generation Agent ├── ReportEngine/ # Multi-round report generation Agent
│ ├── agent.py # Agent main logic │ ├── agent.py # Agent main logic
│ ├── llms/ # LLM interfaces │ ├── llms/ # LLM interfaces
│ │ └── gemini.py # Gemini API dedicated
│ ├── nodes/ # Report generation nodes │ ├── nodes/ # Report generation nodes
│ │ ├── template_selection.py # Template selection node │ │ ├── template_selection.py # Template selection node
│ │ └── html_generation.py # HTML generation node │ │ └── html_generation.py # HTML generation node
@@ -230,7 +228,7 @@ playwright install chromium
#### 4.1 Configure API Keys #### 4.1 Configure API Keys
Edit the `config.py` file and fill in your API keys (you can also choose your own models and search proxies; please see the config file for details): Edit the `config.py` file and fill in your API keys (you can also choose your own models and search proxies; see the config file for details):
```python ```python
# MySQL Database Configuration # MySQL Database Configuration
@@ -238,26 +236,18 @@ DB_HOST = "localhost"
DB_PORT = 3306 DB_PORT = 3306
DB_USER = "your_username" DB_USER = "your_username"
DB_PASSWORD = "your_password" DB_PASSWORD = "your_password"
DB_NAME = "weibo_analysis" DB_NAME = "your_db_name"
DB_CHARSET = "utf8mb4" DB_CHARSET = "utf8mb4"
# DeepSeek API (Apply at: https://www.deepseek.com/) # LLM configuration
DEEPSEEK_API_KEY = "your_deepseek_api_key" # You can switch each Engine's LLM provider as long as it follows the OpenAI-compatible request format
# Tavily Search API (Apply at: https://www.tavily.com/) # Insight Agent
TAVILY_API_KEY = "your_tavily_api_key" INSIGHT_ENGINE_API_KEY = "your_api_key"
INSIGHT_ENGINE_BASE_URL = "https://api.moonshot.cn/v1"
# Kimi API (Apply at: https://www.kimi.com/) INSIGHT_ENGINE_MODEL_NAME = "kimi-k2-0711-preview"
KIMI_API_KEY = "your_kimi_api_key" # Media Agent
...
# Gemini API (Apply at: https://api.chataiapi.com/)
GEMINI_API_KEY = "your_gemini_api_key"
# Bocha Search API (Apply at: https://open.bochaai.com/)
BOCHA_Web_Search_API_KEY = "your_bocha_api_key"
# Silicon Flow API (Apply at: https://siliconflow.cn/)
GUIJI_QWEN3_API_KEY = "your_guiji_api_key"
``` ```
#### 4.2 Database Initialization #### 4.2 Database Initialization
@@ -373,30 +363,28 @@ SENTIMENT_CONFIG = {
### Integrate Different LLM Models ### Integrate Different LLM Models
The system supports multiple LLM providers, switchable in each agent's configuration: The system supports any LLM provider that follows the OpenAI request format. You only need to fill in KEY, BASE_URL, and MODEL_NAME in `config.py`.
```python > What is the OpenAI request format? Here's a simple example:
# Configure in each Engine's utils/config.py >```python
class Config: >from openai import OpenAI
default_llm_provider = "deepseek" # Options: "deepseek", "openai", "kimi", "gemini", "qwen" >
>client = OpenAI(api_key="your_api_key",
# DeepSeek configuration > base_url="https://api.siliconflow.cn/v1")
deepseek_api_key = "your_api_key" >
deepseek_model = "deepseek-chat" >response = client.chat.completions.create(
> model="Qwen/Qwen2.5-72B-Instruct",
# OpenAI compatible configuration > messages=[
openai_api_key = "your_api_key" > {
openai_model = "gpt-3.5-turbo" > 'role': 'user',
openai_base_url = "https://api.openai.com/v1" > 'content': "What new opportunities will reasoning models bring to the market?"
> }
# Kimi configuration > ],
kimi_api_key = "your_api_key" >)
kimi_model = "moonshot-v1-8k" >
>complete_response = response.choices[0].message.content
# Gemini configuration >print(complete_response)
gemini_api_key = "your_api_key" >```
gemini_model = "gemini-pro"
```
### Change Sentiment Analysis Models ### Change Sentiment Analysis Models
README.md
+35 -46
View File
@@ -23,7 +23,9 @@
## ⚡ 项目概述 ## ⚡ 项目概述
“**微舆**” 是一个从0实现的创新型 多智能体 舆情分析系统，不止微博，全平台简洁通用。 “**微舆**” 是一个从0实现的创新型 多智能体 舆情分析系统，帮助大家破除信息茧房，还原舆情原貌，预测未来走向，辅助决策。用户只需像聊天一样提出分析需求，智能体开始全自动分析 国内外30+主流社媒 与 数百万条大众评论。
> “微舆”谐音“微鱼”，BettaFish是一种体型很小但非常好斗、漂亮的鱼，它象征着“小而强大，不畏挑战”。
查看系统以“武汉大学舆情”为例，生成的研究报告：[武汉大学品牌声誉深度分析报告](./final_reports/final_report__20250827_131630.html) 查看系统以“武汉大学舆情”为例，生成的研究报告：[武汉大学品牌声誉深度分析报告](./final_reports/final_report__20250827_131630.html)
@@ -103,10 +105,7 @@ Weibo_PublicOpinion_AnalysisSystem/
├── InsightEngine/ # 私有数据库挖掘Agent ├── InsightEngine/ # 私有数据库挖掘Agent
│ ├── agent.py # Agent主逻辑 │ ├── agent.py # Agent主逻辑
│ ├── llms/ # LLM接口封装 │ ├── llms/ # LLM接口封装
│ │ ├── deepseek.py # DeepSeek API │ │ └── base.py # 统一的 OpenAI 兼容客户端
│ │ ├── kimi.py # Kimi API
│ │ ├── openai_llm.py # OpenAI格式API
│ │ └── base.py # LLM基类
│ ├── nodes/ # 处理节点 │ ├── nodes/ # 处理节点
│ │ ├── base_node.py # 基础节点类 │ │ ├── base_node.py # 基础节点类
│ │ ├── formatting_node.py # 格式化节点 │ │ ├── formatting_node.py # 格式化节点
@@ -130,7 +129,6 @@ Weibo_PublicOpinion_AnalysisSystem/
├── ReportEngine/ # 多轮报告生成Agent ├── ReportEngine/ # 多轮报告生成Agent
│ ├── agent.py # Agent主逻辑 │ ├── agent.py # Agent主逻辑
│ ├── llms/ # LLM接口 │ ├── llms/ # LLM接口
│ │ └── gemini.py # Gemini API专用
│ ├── nodes/ # 报告生成节点 │ ├── nodes/ # 报告生成节点
│ │ ├── template_selection.py # 模板选择节点 │ │ ├── template_selection.py # 模板选择节点
│ │ └── html_generation.py # HTML生成节点 │ │ └── html_generation.py # HTML生成节点
@@ -238,31 +236,26 @@ DB_HOST = "localhost"
DB_PORT = 3306 DB_PORT = 3306
DB_USER = "your_username" DB_USER = "your_username"
DB_PASSWORD = "your_password" DB_PASSWORD = "your_password"
DB_NAME = "weibo_analysis" DB_NAME = "your_db_name"
DB_CHARSET = "utf8mb4" DB_CHARSET = "utf8mb4"
# DeepSeek API（申请地址：https://www.deepseek.com/） # LLM配置
DEEPSEEK_API_KEY = "your_deepseek_api_key" # 您可以更改每个部分LLM使用的API，只要兼容OpenAI请求格式都可以
# Tavily搜索API（申请地址：https://www.tavily.com/） # Insight Agent
TAVILY_API_KEY = "your_tavily_api_key" INSIGHT_ENGINE_API_KEY = "your_api_key"
INSIGHT_ENGINE_BASE_URL = "https://api.moonshot.cn/v1"
# Kimi API（申请地址：https://www.kimi.com/） INSIGHT_ENGINE_MODEL_NAME = "kimi-k2-0711-preview"
KIMI_API_KEY = "your_kimi_api_key" # Media Agent
...
# Gemini API（申请地址：https://api.chataiapi.com/）
GEMINI_API_KEY = "your_gemini_api_key"
# 博查搜索API（申请地址：https://open.bochaai.com/）
BOCHA_Web_Search_API_KEY = "your_bocha_api_key"
# 硅基流动API（申请地址：https://siliconflow.cn/）
GUIJI_QWEN3_API_KEY = "your_guiji_api_key"
``` ```
#### 4.2 数据库初始化 #### 4.2 数据库初始化
**选择1：使用本地数据库** **选择1：使用本地数据库**
> MindSpider爬虫系统跟舆情系统是各自独立的，所以需要再去`MindSpider\config.py`配置一下
```bash ```bash
# 本地MySQL数据库初始化 # 本地MySQL数据库初始化
cd MindSpider cd MindSpider
@@ -373,30 +366,26 @@ SENTIMENT_CONFIG = {
### 接入不同的LLM模型 ### 接入不同的LLM模型
系统支持多种LLM提供商，可在各Agent的配置中切换： 支持任意openAI调用格式的LLM提供商，只需要在/config.py中填写对应的KEY、BASE_URL、MODEL_NAME即可。
```python > 什么是openAI调用格式？下面提供一个简单的例子：
# 在各Engine的utils/config.py中配置 >```python
class Config: >from openai import OpenAI
default_llm_provider = "deepseek" # 可选: "deepseek", "openai", "kimi", "gemini"，"qwen"等 >
>client = OpenAI(api_key="your_api_key",
# DeepSeek配置 > base_url="https://api.siliconflow.cn/v1")
deepseek_api_key = "your_api_key" >
deepseek_model = "deepseek-chat" >response = client.chat.completions.create(
> model="Qwen/Qwen2.5-72B-Instruct",
# OpenAI兼容配置 > messages=[
openai_api_key = "your_api_key" > {'role': 'user',
openai_model = "gpt-3.5-turbo" > 'content': "推理模型会给市场带来哪些新的机会"}
openai_base_url = "https://api.openai.com/v1" > ],
>)
# Kimi配置 >
kimi_api_key = "your_api_key" >complete_response = response.choices[0].message.content
kimi_model = "moonshot-v1-8k" >print(complete_response)
>```
# Gemini配置
gemini_api_key = "your_api_key"
gemini_model = "gemini-pro"
```
### 更改情感分析模型 ### 更改情感分析模型