https://github.com/creative-link-for-digital-health/conversation_manager

Research focused conversation manger for LLMs

https://github.com/creative-link-for-digital-health/conversation_manager

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Research focused conversation manger for LLMs

Basic Info
  • Host: GitHub
  • Owner: Creative-Link-for-Digital-Health
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 118 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License

README.md

Conversation Research System - Setup Guide

📦 Conda Environment Setup

Prerequisites

Quick Start

```bash

Create the conda environment

conda env create -f environment.yml

Activate the environment

conda activate conversation-manager

🚀 System Setup

1. Configuration Files

Create your configuration files:

```bash

Copy and customize scenario configuration

cp scenario.toml.template scenario.toml

Copy and add your API secrets (DO NOT COMMIT THIS FILE!)

Make sure that this is not world readable on the server --> chmod 600 .secrets.toml

TODO more robust way of dealing with this in the future

cp .secrets.toml.template .secrets.toml ```

2. Configure Your Research Scenario

Edit scenario.toml: - Set your scenario name and description - Configure LLM provider settings - Set system prompt UUID (after creating prompts) - Enable/configure RAG if needed - Enable/configure local logging if needed - Enable/configure REDCap logging if needed

3. Add API Keys

Edit .secrets.toml with your actual API keys: - LLM Provider API key - REDCap API token (if using REDCap) - Any other provider API keys

4. Create Prompts and Document Collections

TODO Create better documentation here

5. Start the Backend

```bash

Start the Flask backend

python app.py ```

The backend will: - ✅ Validate configuration - ✅ Initialize prompt management - FUTURE FEATURE: Set up RAG system (if enabled) - ✅ Connect to REDCap (if enabled) - 🚀 Start API server on http://localhost:5500

6. Test the System

```bash

Test API health

curl http://localhost:5500/health

```

📚 Additional Resources

Owner

  • Name: Creative Link for Digital Health
  • Login: Creative-Link-for-Digital-Health
  • Kind: organization

GitHub Events

Total
  • Push event: 15
  • Pull request event: 2
  • Create event: 4
Last Year
  • Push event: 15
  • Pull request event: 2
  • Create event: 4

Dependencies

environment.yml pypi
  • docling >=1.0.0
  • pycap >=2.5.0
  • python-multipart >=0.0.6
  • redis >=5.0.0
  • uuid *