fishy/Dynavera
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
No description
177 commits 1 branch 0 tags 4.6 MiB
Python 38.2%
Vue 28.4%
Jupyter Notebook 20.3%
TeX 7%
TypeScript 5.1%
Other 0.9%
Find a file
Viswamedha Nalabotu b604c243c8 Added prod start script, tweaked swarm values for inference containers
2026-02-26 12:08:16 +00:00
.vscode Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
apps Added download script and updated management command 2026-02-26 11:38:04 +00:00
compose Added prod start script, tweaked swarm values for inference containers 2026-02-26 12:08:16 +00:00
config Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
data Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
notebooks Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
requirements Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
site Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
.dockerignore Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
.editorconfig Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
.env.example Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
.env.template Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
.gitignore Removed vite deps folder 2026-02-26 01:39:10 +00:00
.gitlab-ci.yml Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
download_model.py Added download script and updated management command 2026-02-26 11:38:04 +00:00
gpu_server.py Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
manage.py Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
package-lock.json Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
package.json Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00
README.md Revised all files to reduce bloat + optimized workflow 2026-02-26 01:32:04 +00:00

README.md

Dynavera: Distributed Agentic Onboarding System

Dynavera is a multi-agent AI platform designed to automate role-specific onboarding. The system utilizes a distributed architecture to separate application logic from high-latency LLM inference, employing the Model Context Protocol (MCP) for internal data retrieval and Retrieval-Augmented Generation (RAG).

Project Goals

  • Distributed Orchestration: Implementation of a dual-node system (VPS/GPU) to manage real-time user interaction and heavy computational inference independently.

  • Context-Aware Training: Development of a RAG pipeline that utilizes semantic chunking and vector similarity search to provide role-specific guidance.

  • Agentic Workflow: Utilizing an orchestrator to manage stateful conversations, tool calls, and user progress tracking via WebSockets.

  • Automated Ingestion: Creating a pipeline for converting raw organizational documents (PDF/TXT) into searchable vector embeddings.

System Architecture

The application is split into two primary layers:

Management Layer (VPS)

  • Framework: Django 5.x with Django Channels for WebSocket management.
  • Database: PostgreSQL with the pgvector extension for semantic storage.
  • Task Queue: Celery and Redis for asynchronous document processing and ingestion.
  • Internal Routing: apps/onboarding/mcp.py serves as the Model Context Protocol router, bridging the agent to the PostgreSQL vector store.

Intelligence Layer (GPU Node)

  • Inference Server: gpu_server.py (FastAPI) located in the root, exposing endpoints for LLM chat completions and embeddings.
  • Semantic Processor: Custom logic within the inference server for smart chunking that detects topic shifts in text to optimize retrieval accuracy.

Tech Stack

  • Backend: Django, Django REST Framework, Django Channels.
  • Frontend: Vue 3, Vite, Pinia.
  • Database: PostgreSQL (pgvector).
  • AI/ML: FastAPI, OpenAI-compatible API structures, Sentence-Transformers.
  • Infrastructure: Docker, Redis, Celery.

Application Structure

  • apps.accounts: Manages User, Organization, and Role models, including invite-based onboarding logic.
  • apps.knowledge: Handles the RAG pipeline, including TrainingFile management and RoleRagDocument vector storage.
  • apps.onboarding: Contains the core logic for the onboarding experience:
    • consumers.py: The Agent Orchestrator managing WebSocket handshakes and session loops.
    • mcp.py: The internal router for Model Context Protocol tool execution.
    • models.py: Stores AgentConfig (prompts/tools) and OnboardingSession state.
  • gpu_server.py: The entry point for the Intelligence Layer, handling embedding generation and LLM inference.

Instructions for Evaluation

The system is currently pre-loaded with demonstration data from internal configuration files.

Access Credentials

Role Email Password
Admin admin@example.com admin
Manager haleisaac@example.com password
User j.thompson@example.com password

Recommended Technical Walkthrough

To verify the integration of the Knowledge Pipeline and the Agentic Orchestrator, follow these steps:

  1. Environment Setup: Navigate to https://fyp.viswamedha.com. *
  2. Document Ingestion: Log in as the Manager (haleisaac@example.com). Navigate to the University of Birmingham organization. Upload a PDF relevant to a specific role.
  3. Vectorization: Observe the ingestion status. The system will extract text, send it to the GPU node for semantic chunking, and store the resulting 1536-dimension vectors in PostgreSQL.
  4. Agent Interaction: Access the Role Onboarding interface. Initiate a session.
  5. Retrieval Verification: This will query the agent regarding specific details within the uploaded PDF. The agent in consumers.py will trigger a tool call via mcp.py, retrieve the relevant document chunks, and provide a contextualized response via onboarding pages.

*Note: If the website that I hosted is not accessible, please set up the project locally by following the instructions in the Usage section below.

Usage

  1. Clone the repository.
  2. Copy the .env.example file to .env or create a new .env file based on .env.template, and change the necessary environment variables. *
  3. Deploy via Docker Compose: docker compose -f compose/dev/docker-compose.yml --env-file .env up -d in the root directory.
  4. Access the frontend at the configured port (usually localhost:8000).
  • Note: If you use a different secret key, when the fyp-django-dev container starts, you will need to execute the following command to reset all accounts to default passwords of "admin" for admin users and "password" for manager and user accounts:
docker exec -it fyp-django-dev python manage.py reset_passwords

Warnings

  • The development compose is used here to allow HMR and easier debugging. Please only use this file.
  • Ensure that a GPU is available and CUDA drivers are properly installed for the inference server to function.
  • I have tested this on an RTX 3060 with 12GB VRAM, so I am not sure if it will work on other GPUs.
  • There is no guarantee that it will load on a CPU-only machine as the batch size and model parameters are configured for GPU inference.