io.github.hzy9981/aviation-accident-analysis
Allows the MCP server to connect to a Neo4j graph database for storing and managing the knowledge graph of entities and relationships extracted from aviation accident reports.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.hzy9981/aviation-accident-analysis Generate extraction prompt for the accident report at data/input_reports/report1.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
航空事故致因抽取与知识图谱项目 (Aviation Accident Analysis)
本项目基于 Microsoft GraphRAG 框架 ,旨在自动从航空事故报告中抽取实体与因果关系,并构建符合“人-机-环-管”框架的知识图谱。
项目结构
data/: 原始数据与地标数据。input/: GraphRAG 输入目录(清洗后的文本)。output/: GraphRAG 输出结果(Parquet, GraphML 等)。prompts/: 自定义的 GraphRAG 提取提示词。src/:ingest.py: PDF/DOCX 解析与文本清洗。evaluate.py: 提取准确率与 F1 分数评测脚本。
run.sh: 一键运行脚本。settings.yaml: GraphRAG 配置文件。
Related MCP server: docsearch
环境要求
Python 3.10+
uv (推荐)
环境配置注意事项
若遇到 LLM 连接错误,请检查
settings.yaml中的api_base是否配置正确。在某些 Docker 或受限环境中,建议将localhost修改为127.0.0.1。本项目已对
prompts/extract_graph.txt中的抽取示例进行了优化,通过引入复杂场景示例,提升了在航空事故报告中的实体抽取表现。
Prompt 优化与评估记录 (2026-07-24)
优化策略
针对航空事故报告的复杂性,对 prompts/extract_graph.txt 进行了多轮手动迭代优化:
实体原子化:强制拆分复杂短语(如“燃油管路破裂”拆分为实体“燃油管路”与关系“破裂导致”),提升知识图谱的结构化程度。
严格去噪:建立了否定约束,排除通用职衔(如单独的“机长”)和指示代词(如“该部件”),提升精确率。
少样本增强:集成了
few_shot_data.csv中的高质量航空事故致因链示例,引导模型识别长程因果关系。因果链强制构建:明确
[因素] -> [事件] -> [结果]的链条要求。
评估结果 (Fuzzy Match)
通过 scripts/run_automated_evaluation.py 运行自动化评估,对比 data/ground_truth.json 得到以下指标:
指标 | 实体 (Entities) | 关系 (Relationships) |
精确率 (Precision) | 0.4348 | 0.0556 |
召回率 (Recall) | 0.7143 | 0.0909 |
F1 分数 (F1 Score) | 0.5405 | 0.0690 |
结论:实体抽取的精确率和 F1 分数相比基准版本有显著提升。关系抽取受限于本地模型的指令遵循能力,仍有优化空间。
MCP 服务 (Model Context Protocol)
本项目提供了一个 MCP 服务,方便通过 MCP 客户端(如 Claude Desktop)直接调用文档解析与提示词生成功能。
核心功能
文档解析:支持 PDF、DOCX、TXT 格式的自动解析与清洗。
提示词注入:将解析出的文档内容自动注入到指定的提示词模板中。
启动方式
uv run mcp_server.py可用工具
upload_and_generate_prompt:参数
file_path: 文档路径。参数
template_name:prompts/目录下的模板名(默认extract_entities)。
list_available_templates: 列出所有可用的提示词模板。
🐳 一键启动 (Docker)
如果你想快速启动整个分析环境(包含 Neo4j 数据库和 MCP 服务),可以使用 Docker Compose:
docker-compose up -d启动后:
Neo4j 控制台: http://localhost:7474 (默认账号:
neo4j, 密码:password)MCP 服务: 已在容器内运行,并自动连接到容器内的 Neo4j。
运行流程
将事故报告(PDF/DOCX/TXT)放入
data/input_reports。运行流水线:
bash run.sh
使用 Ollama (本地 LLM)
在 settings.yaml 中修改 completion_models 和 embedding_models:
completion_models:
default_completion_model:
model_provider: openai
api_base: http://localhost:6006/v1
model: llama3 # 或其他模型
api_key: ollama # 占位符注意:GraphRAG 对本地模型的支持取决于模型的遵循指令能力。
提取 Schema (人-机-环-管)
实体类型: person (人), equipment (机), environment (环), organization (管), procedure, event, weather, violation.
关系类型: leads to, limited by, violates, not executed, belongs to.
Neo4j 知识图谱导入
本项目支持将 GraphRAG 提取的实体与关系导入 Neo4j 图数据库。
使用
src/export_to_neo4j.py脚本完成导入。已配置 Docker 容器运行 Neo4j 实例,确保能够正常连接。
Available Tools
3 toolslist_available_reportsB
List all available reports in a specified directory.
Inputs: directory. Returns: result
list_available_templatesA
List all available prompt templates in the prompts/ directory.
Inputs: no named parameters. Returns: result
upload_and_generate_promptA
Upload an aviation accident report (PDF, DOCX, TXT), parse it, and wrap it in a specified prompt template.
Inputs: file_path (required), template_name. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: uploading and generating a prompt, listing templates, and listing reports. There is no overlap or ambiguity between them.
All tool names use snake_case and follow a verb-first pattern. The first tool uses a compound verb 'upload_and_generate' while the others use 'list_available', which is a minor deviation but still predictable and readable.
Three tools is a slightly thin but reasonable set for the narrow scope of uploading reports and managing available templates/reports. It is within the acceptable range and does not feel excessive.
The tool surface is incomplete for a server named 'aviation-accident-analysis'. It only supports uploading a report and listing templates/reports, with no tools to actually perform analysis, manage templates (create/update/delete), or retrieve detailed content. This leaves significant gaps that would require external actions.
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceMCP server for exporting PDF to markdown, optimized for LLM consumption.698 PyPI73AGPL 3.0- AlicenseAqualityDmaintenanceMCP server that enables searching and reading binary document files (PDF, DOCX, PPTX, XLSX, ODT, ODS, ODP, RTF, EPUB) using regex patterns and retrieving content by sections.2MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server for document parsing, ingestion, query (including multimodal), and lightweight knowledge graph inspection, enabling RAG workflows via the Model Context Protocol.-
- AlicenseNot gradedqualityDmaintenanceMCP server that extracts clean text, tables, and structured data from documents, images, code, and audio files, supporting 97 formats with OCR, transcription, and code intelligence.MIT