llm-suite

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

(★ 9)

An advanced LLM-powered application offering features like Resume Parsing, OCR, and interactive LLM chat. Built using open-source Llama 3, Ollama, LM Studio, Flask, and more, it hosts LLMs locally for high-performance and secure processing.

llm-suite 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1><b>LLM Suite</b> - LLM-Powered Application</h1>
    
<h2>Overview / Usecases</h2>
    <p>This application leverages the power of advanced LLMs to offer a variety of features including:</p>
    <ul>
        <li><strong>Resume Percentage Match:</strong> Quickly match resumes against job descriptions with precision.</li>
        <li><strong>Resume Parser:</strong> Extract and structure information from resumes effortlessly.</li>
        <li><strong>Document OCR:</strong> Extract bill details e.g. Total Amount, Date and expense type.</li>
        <li><strong>Chat LLM:</strong> Engage in interactive conversations powered by a state-of-the-art language model.</li>
        <li><strong>Multiple Document RAG:</strong> Retrieve and aggregate information from multiple documents using advanced LLM techniques.</li>
        <li><strong>Single Document RAG:</strong> Retrieve and aggregate information from a single document for focused analysis.</li>
    </ul>
    <p>Built using <strong>open-source Llama 3.1</strong>, Ollama, LM Studio, Flask, and other technologies, this app is hosted in a local environment to ensure high performance and secure processing.</p>

<h2>Features</h2>
    <ol>
        <li><strong>Resume Percentage Match:</strong> Automatically compare resumes with job descriptions and return a match percentage.</li>
        <li><strong>Resume Parser:</strong> Parse resumes into structured data for easy storage and retrieval.</li>
        <li><strong>Document OCR:</strong> Extract bill details e.g. Total Amount, Date and expense type.</li>
        <li><strong>Chat LLM:</strong> Engage in meaningful conversations using the integrated language model.</li>
        <li><strong>Multiple Document RAG:</strong> Aggregate and analyze data across multiple documents.</li>
        <li><strong>Single Document RAG:</strong> Perform retrieval and aggregation on a single document for detailed insights.</li>
    </ol>

<h2>Technologies Used</h2>
    <ul>
        <li><strong>Llama 3.1:</strong> Open-source large language model for natural language processing tasks.</li>
        <li><strong>Ollama:</strong> Tool for fine-tuning and hosting models.</li>
        <li><strong>LM Studio:</strong> IDE for working with language models.</li>
        <li><strong>Flask:</strong> Lightweight web framework for hosting the application locally.</li>
        <li><strong>Python:</strong> Core programming language used across the application.</li>
    </ul>

<h2>Getting Started</h2>
    
<h3>Prerequisites</h3>
    <ul>
        <li>Python 3.8+</li>
        <li>Flask</li>
        <li>Dependencies listed in <code>requirements.txt</code></li>
    </ul>

<h3>Installation</h3>
    <ol>
        <li>Clone the repository:
            <pre><code>git clone https://github.com/neelshrimali/llm-suite.git</code></pre>
        </li>
        <li>Navigate to the project directory:
            <pre><code>cd llm-suite</code></pre>
        </li>
        <li>Install the required dependencies:
            <pre><code>pip install -r requirements.txt</code></pre>
        </li>
    </ol>

<h3>Running the Application</h3>
    <ol>
        <li>Start the Flask server:
            <pre><code>flask run</code></pre>
        </li>
        <li>Access the application in your browser at <code>http://localhost:5000</code>.</li>
    </ol>

<h2>Contributing</h2>
    <p>Contributions are welcome! Please feel free to submit a Pull Request.</p>

llm-suite

llm-suite 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

llm-suite

llm-suite 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README