ecodynalyze 2025.12.20201125

A new package designed to analyze and summarize ecological studies, specifically focusing on the dynamics of species interactions. Users input text excerpts from research papers or field notes, and th

ecodynalyze – Ecological Study Analysis Package

Standardize and analyze ecological research data with structured insights.

---

Overview

ecodynalyze is a Python package designed to extract, structure, and summarize key findings from ecological studies. By analyzing text excerpts (e.g., research papers, field notes), it identifies species interactions, dominance hierarchies, and environmental impacts, enabling researchers to compare and synthesize data across diverse sources.

The package leverages LLM7 (default) or custom LLMs (via LangChain) to parse unstructured text and return structured outputs, ensuring consistency and comparability.

---

Key Features

✅ Structured Data Extraction – Parses species interactions, dominance patterns, and ecological outcomes. ✅ Flexible LLM Integration – Works with LLM7 (default), OpenAI, Anthropic, Google Vertex AI, or any LangChain-compatible model. ✅ Regex-Pattern Validation – Ensures extracted data matches predefined formats. ✅ Environment-Friendly – Optimized for lightweight, high-accuracy analysis.

---

Installation

pip install ecodynalyze

---

Usage Examples

Basic Usage (Default LLM7)

from ecodynalyze import ecodynalyze

user_input = """
In a 2023 study, researchers observed that species A dominated interactions
with species B in 85% of recorded events, while species C showed minimal
competitive behavior due to habitat constraints.
"""

response = ecodynalyze(user_input)
print(response)

Custom LLM Integration

Using OpenAI

from langchain_openai import ChatOpenAI
from ecodynalyze import ecodynalyze

llm = ChatOpenAI(model="gpt-4")
response = ecodynalyze(user_input, llm=llm)

Using Anthropic (Claude)

from langchain_anthropic import ChatAnthropic
from ecodynalyze import ecodynalyze

llm = ChatAnthropic(model="claude-2")
response = ecodynalyze(user_input, llm=llm)

Using Google Vertex AI

from langchain_google_genai import ChatGoogleGenerativeAI
from ecodynalyze import ecodynalyze

llm = ChatGoogleGenerativeAI(model="gemini-pro")
response = ecodynalyze(user_input, llm=llm)

---

Parameters

Parameter	Type	Description
user_input	str	Text excerpt (e.g., research paper, field notes) to analyze.
api_key	Optional[str]	LLM7 API key (defaults to LLM7_API_KEY env var).
llm	Optional[BaseChatModel]	Custom LangChain LLM (e.g., ChatOpenAI, ChatAnthropic).

---

LLM7 API Key

• Default: Uses LLM7_API_KEY environment variable.
• Manual Override: Pass via api_key parameter.
• Free Tier: Sufficient for most use cases (rate limits apply).
• Upgrade: Get a custom API key at LLM7 Token.

---

Output Format

The function returns a list of structured dictionaries containing:

• Species names
• Interaction types (e.g., competition, predation)
• Dominance patterns
• Environmental context

Example output:

[
    {
        "species1": "A",
        "species2": "B",
        "interaction": "competition",
        "dominance": "A > B (85%)",
        "environment": "habitat-constrained"
    }
]

---

Contributing & Support

📢 Issues & Feedback: GitHub Issues 📧 Author: Eugene Evstafev (LinkedIn) 📧 Contact: [e-mail]

---

License

MIT