Pipeline | Installation | User Interface | Model | Database | Search | Contact
- FastAPI & Gradio backend
- Dockerize packages
- Add UI ingest upload file
- Add login page
- Add docs
- Nginx for http and https
- K8s
- CI/CD cloud (AWS/Azure)
- Minimum CPU 8GiB RAM
- Uncomment line 8 packages = [{include = "**"}] to use all internal packages (Passing Flake8)
- Install packages and download GPT4All model by
- Run locally
chmod u+x ./setup.sh
bash ./setup.sh
- Build MongoDB, Mongo Express, Logstash, Elasticsearch and Kibana
docker compose -f docker-compose-service.yml up
poetry run python app.py --host 0.0.0.0 --port 8071
- Run docker
docker compose up
poetry run python app.py --host 0.0.0.0 --port 8071
Run on: http://localhost:8071
- Chatbot:
- Ingest PDF:
- GPT4ALL: Current best commercially licensable model based on GPT-J and trained by Nomic AI on the latest curated GPT4All dataset.
- MongoDB Run on: http://localhost:27017
poetry run python src/ingest_database.py --mongodb-host "mongodb://localhost:27017/" --data-path "static/pdf/"
Run on: http://localhost:8081
Run on: http://localhost:9600
- Elasticsearch & Kibana
poetry run python src/ingest_search.py --mongodb-host "mongodb://localhost:27017/" --es-host "http://localhost:9200/" --index_name "document"
Elasticsearch run on: http://localhost:9200
Kibana run on: http://localhost:5601
- KhoiVN - @linkedin-khoivn8071 - nguyenkhoi8071@gmail.com
- Project Link: Github-E2E-AI-Chatbot
- Website: khoivn.space
- From Langchain Framework: https://github.com/hwchase17/langchain
- From GPT4All: https://github.com/nomic-ai/gpt4all