av-safety-parser 2025.12.21191556

av-safety-parser extracts aviation incident details from unstructured text, outputting standardized data on incident type, aircraft, and risks.

av-safety-parser

A lightweight Python package for extracting and structuring aviation safety information from unstructured text.
It parses texts such as FAA warnings and news articles to return key details (incident type, affected aircraft, safety risks, etc.) in a consistent format.

Features

• Simple API that takes raw text and returns structured data.
• Uses the default ChatLLM7 model from langchain_llm7 for inference.
• Fully compatible with any LangChain LLM implementation (OpenAI, Anthropic, Google Gemini, etc.) by passing a custom instance.
• Supports API-key configuration via environment variable or explicit parameter.

Installation

pip install av_safety_parser

Quick Example

from av_safety_parser import av_safety_parser

user_input = """
FAA publishes new warning on rotor blade vibrations in twin‑prop aircraft.
There were several incidents where the vibrations caused structural fatigue.
"""

# Using the default ChatLLM7
results = av_safety_parser(user_input)
print(results)

You can also pass a custom LLM instance:

# Example with OpenAI's ChatOpenAI
from langchain_openai import ChatOpenAI
from av_safety_parser import av_safety_parser

llm = ChatOpenAI()
results = av_safety_parser(user_input, llm=llm)
print(results)

# Example with Anthropic's ChatAnthropic
from langchain_anthropic import ChatAnthropic
from av_safety_parser import av_safety_parser

llm = ChatAnthropic()
results = av_safety_parser(user_input, llm=llm)
print(results)

# Example with Google Gemini
from langchain_google_genai import ChatGoogleGenerativeAI
from av_safety_parser import av_safety_parser

llm = ChatGoogleGenerativeAI()
results = av_safety_parser(user_input, llm=llm)
print(results)

Parameters

Parameter	Type	Description
user_input	str	Raw text to parse.
llm	Optional[BaseChatModel]	LangChain LLM instance. If omitted, ChatLLM7 will be used automatically.
api_key	Optional[str]	API key for LLM7. If not provided, the library will look for the LLM7_API_KEY environment variable.

Default Rate Limits
The free tier of LLM7 offers enough rate limits for most use cases. If you require higher limits, pass your own api_key either through av_safety_parser(user_input, api_key="your_key") or by setting LLM7_API_KEY in your environment.

Getting an LLM7 API Key

1. Sign up at https://token.llm7.io/
2. Retrieve your API token
3. Set it as an environment variable:

   export LLM7_API_KEY="your_token_here"
   

Issue Tracker

If you encounter any problems or have feature requests, please open an issue at:
https://github.com/chigwell/av-safety-parser/issues

Author

• Name: Eugene Evstafev
• GitHub: @chigwell
• Email: [e-mail]

Enjoy using av-safety-parser to keep aviation data clear and consistent!