https://github.com/darian16/rag_demo
Demo for Bounce Insights. RAG-powered survey analysis tool.
https://github.com/darian16/rag_demo
chroma docker fastapi firebase langgraph llmops pylint pytest python rag reactjs
Last synced: 8 months ago
JSON representation
Demo for Bounce Insights. RAG-powered survey analysis tool.
- Host: GitHub
- URL: https://github.com/darian16/rag_demo
- Owner: darian16
- License: mit
- Created: 2025-02-07T20:06:29.000Z (8 months ago)
- Default Branch: develop
- Last Pushed: 2025-02-12T12:35:45.000Z (8 months ago)
- Last Synced: 2025-02-12T13:51:05.286Z (8 months ago)
- Topics: chroma, docker, fastapi, firebase, langgraph, llmops, pylint, pytest, python, rag, reactjs
- Language: JavaScript
- Homepage: https://rag-demo-33b16.web.app
- Size: 657 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
RAG-powered survey analysis tool
Demo for Bounce Insights
## Table of Contents
- [Tech Stack](#tech-stack)
- [RAG agent workflow](#rag-agent-workflow)
- [Preview](#preview)
- [Sample of queries](#sample-of-queries)
- [Services topology diagram](#services-topology-diagram)
- [Frontend](#frontend)
- [Frontend dependencies](#frontend-dependencies)
- [Frontend Severless settings recommendations](#frontend-severless-settings-recommendations)
- [Backend](#backend)
- [Services](#services)
- [Backend dependencies](#backend-dependencies)
- [Backend Severless settings recommendations](#backend-severless-settings-recommendations)
## Tech Stack
- **LLMops**: LanghGraph.
- **Frontend**: ReacJS, Material.
- **Backend**: FastAPI.
- **Database**: Chroma.
- **Infrastructure**: Google Cloud Platform (GCP), Terraform, Makefile, Docker, Docker Compose, CloudRun for serverless architecture, Firebase.
## RAG agent workflow
## Preview
## Sample of queries
## Services topology diagram
## Frontend
### Frontend dependencies
### Frontend severless settings recommendations
- Memory (Memory to allocate to each container instance): 128Mb
- CPU (Number of vCPUs allocated to each container instance): 0.1
- Request timeout (Time within which a response must be returned): 300 seconds
- Maximum requests per container (The maximum number of concurrent requests that can reach each container instance): 1
- Minimum number of instances (Autoscaling): 1
- Maximum number of instances (Autoscaling): 5
## Backend
### Services
### Backend dependencies
-
### Backend severless settings recommendations
- Memory (Memory to allocate to each container instance): 512Mb
- CPU (Number of vCPUs allocated to each container instance): 1
- Request timeout (Time within which a response must be returned): 300 seconds
- Maximum requests per container (The maximum number of concurrent requests that can reach each container instance): 1
- Minimum number of instances (Autoscaling): 1
- Maximum number of instances (Autoscaling): 5
[🔼 Back to top](#-rag-powered-survey-analysis-tool)