https://github.com/ribin-baby/rag_llamaindex_nvidianim

https://github.com/ribin-baby/rag_llamaindex_nvidianim

docker fastapi llama-index python

Last synced: 6 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/ribin-baby/rag_llamaindex_nvidianim
• Owner: Ribin-Baby
• Created: 2024-09-11T15:35:12.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-09-11T16:06:33.000Z (about 2 months ago)
• Last Synced: 2024-10-17T03:27:18.926Z (21 days ago)
• Topics: docker, fastapi, llama-index, python
• Language: Python
• Homepage:
• Size: 49.8 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

        
# RAG application using LLamaIndex and NVIDIA NIM microservice

* Here we are usingLlamaIndex to interact with NVIDIA hosted NIM microservices like chat, embedding, and reranking models to build a simple retrieval-augmented generation (RAG) application. 

# How to use ?

```sh

 curl -X 'GET' 'http://127.0.0.1:8000/query' -H 'accept: application/json' -H 'Content-Type: application/json' -d '{"query": "where is sweden located?"}'

 ```

# How to containarize ?

* build the docker image 

> docker build -t chatapp .

* `chatapp` is the image name

* run the container from the above created image

> docker run -p 8000:8000 chatapp

* this will expose the REST API to the application, which can be accessed from the host machine at the following endpoint

> http://localhost:8000/query