https://github.com/goodguyady/querybaseai
AI-powered hybrid search engine combining keyword, vector, and LLM-based contextual search using RAG with support for AI21, OpenAI or any other LLMs.
https://github.com/goodguyady/querybaseai
ai django django-rest-framework document-search elasticsearch llm milvus nlp rag vector-search
Last synced: 6 months ago
JSON representation
AI-powered hybrid search engine combining keyword, vector, and LLM-based contextual search using RAG with support for AI21, OpenAI or any other LLMs.
- Host: GitHub
- URL: https://github.com/goodguyady/querybaseai
- Owner: GoodGuyAdy
- Created: 2025-04-13T13:30:10.000Z (6 months ago)
- Default Branch: master
- Last Pushed: 2025-04-13T15:55:31.000Z (6 months ago)
- Last Synced: 2025-04-13T16:23:25.789Z (6 months ago)
- Topics: ai, django, django-rest-framework, document-search, elasticsearch, llm, milvus, nlp, rag, vector-search
- Language: Python
- Homepage:
- Size: 23.4 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## 🚀 QueryBaseAI
An AI-powered hybrid search engine combining **Keyword Search**, **Vector Similarity Search**, and **LLM-based contextual answers** using **Retrieval Augmented Generation (RAG)** via **AI21**, **OpenAI** or any other LLM.
---
## 🧠 Overview
**QueryBaseAI** lets users create organisations, upload documents, automatically chunk & index them using Elasticsearch and Milvus, and ask natural language queries. The system generates smart, contextual answers using **RAG** powered by **AI21 or OpenAI** (configurable).
---
## 🔧 Tech Stack
| Layer | Stack |
|---------------|----------------------------------------|
| Backend | Django, Django REST Framework (DRF) |
| LLMs | AI21 & OpenAI (via user config) |
| Vector Store | Milvus |
| Text Search | Elasticsearch |
| Logging | Logstash, Kibana (ELK Stack) |
| Orchestration | Docker, Docker Compose |
---
## 💡 Key Features
- 📄 Upload multi-format docs (PDF, DOCX, TXT, MD)
- 🔗 Chunking, indexing & hybrid retrieval (keyword + vector)
- 🧠 Answer generation using **RAG** with OpenAI or AI21
- 📦 Dockerized microservices (Milvus, Elastic, Kibana)
- 📊 Real-time centralized logging (ELK stack)
---
## 📁 Project Structure
```
QueryBaseAI/
├── Backend/ # Django logic (views, serializers, APIs)
├── Core/ # Core database logics
├── LLM/ # LLM providers (OpenAI & AI21 logic)
├── ExternalTools/ # Elastic, Milvus connectors
├── .env # Environment variables
└── README.md # Project documentation
```
---
## 💻 Getting Started
1. Clone the repository from GitHub to your local machine
```bash
git clone https://github.com/GoodGuyAdy/QueryBaseAI.git
```
2. Change the current directory to the cloned project folder
```bash
cd QueryBaseAI
```
3. Install the Python dependencies listed in the requirements.txt file
```bash
pip install -r requirements.txt
```
4. Build and starts the Docker containers defined in the docker-compose.yml file
```bash
docker-compose up --build
```
5. Run the Django development server for the project
```bash
python manage.py runserver
```
---
## 🧑🏻🔧 Troubleshooting :-
- Ensure that your .env file contains a valid OPENAI_API_KEY or AI21_API_KEY.
- Make sure you have an active internet connection.
---