{"id":27928545,"url":"https://github.com/dynamiclu/CeCeData-Agent","last_synced_at":"2026-01-17T03:58:59.047Z","repository":{"id":291721961,"uuid":"978010977","full_name":"dynamiclu/Mcp-ChatBI","owner":"dynamiclu","description":"基于 Mcp 架构的 ChatBI，是一种数据分析智能体解决方案","archived":false,"fork":false,"pushed_at":"2025-05-06T07:23:07.000Z","size":20,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-06T08:19:58.534Z","etag":null,"topics":["chat-bi","llm","llm-agent","llm-agents","mcp","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dynamiclu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-05T10:31:27.000Z","updated_at":"2025-05-06T08:15:56.000Z","dependencies_parsed_at":"2025-05-06T08:30:15.178Z","dependency_job_id":null,"html_url":"https://github.com/dynamiclu/Mcp-ChatBI","commit_stats":null,"previous_names":["dynamiclu/mcp-chatbi"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dynamiclu%2FMcp-ChatBI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dynamiclu%2FMcp-ChatBI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dynamiclu%2FMcp-ChatBI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dynamiclu%2FMcp-ChatBI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dynamiclu","download_url":"https://codeload.github.com/dynamiclu/Mcp-ChatBI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252802350,"owners_count":21806480,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chat-bi","llm","llm-agent","llm-agents","mcp","python"],"created_at":"2025-05-07T02:40:40.310Z","updated_at":"2026-01-17T03:58:59.039Z","avatar_url":"https://github.com/dynamiclu.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Mcp-ChatBI \n\n## 介绍\n\n 基于 [Mcp](https://mcp-docs.cn/) 架构的 ChatBI，是一种数据分析智能体的解决方案。\n\n本项目主要解决ChatBI常见的三个问题\n + 1、如何保障数据的100%的准确性？\n\n    由于模型存在幻觉，无论是NL2SQL、NL2Code，都无法保障数据100%的准确。且数据的准确性又是BI系统的红线，因此，本项目使用NL2Tools的方案，Tools可以是Headless BI的服务，也可是API。\n\n+  2、一次对话如何查询多个指标？\n\n   过去一次对话只能查一个指标，若多个指标需要工程层面去拆解，架构的复杂度非常高，本项目，利用模型的任务规划、推理能力，模型自动拆解多个指标，并按照顺序调用Tools，并返回结果。\n\n+ 3、如何让数据分析的链路自动化？\n\n   常见的数据分析方法，如对比分析、多维钻取、归因运算等，它常常伴有复杂的逻辑推理，当前大模型能力突飞猛进，已经具有复杂问题的推理能力，因此，本项目，利用模型推理能力，自动生成数据链路，并逐次调用Tools，返回结果，最后总结分析。\n\n\n## 部署\n\n### 1. 环境配置\n\n+ 确保你的机器安装了 Python 3.10 - 3.12\n```shell\n# 拉取仓库\n$ git clone https://github.com/dynamiclu/Mcp-ChatBI.git\n\n# 进入目录\n$ cd Mcp-ChatBI\n\n# 安装全部依赖\n$ pip3 install -r requirements.txt \n```\n\n+ 大模型配置\n```shell\n$ vim config/config.toml\n[model]\nqwen_api_key = \"sk-**********\"\nqwen_model_name = \"qwen-max\"\n```\n\n### 2. 启动接口\n```shell\n# 启动API\n$ python3 main-api.py\n```\n\n### 3. 启动Gradio\n```shell\n# 启动Gradio\n$ python3 main-webui.py\n```\n### 4. 演示\n[https://www.bilibili.com/video/BV1b95vzPEjf/](https://www.bilibili.com/video/BV1b95vzPEjf/)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdynamiclu%2FCeCeData-Agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdynamiclu%2FCeCeData-Agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdynamiclu%2FCeCeData-Agent/lists"}