This is an ongoing project being built alongside the LC Pill Checker project to expand its capabilities to allow for image analysis
To run this project, you will need to add the following environment variables to your .env file
REACT_APP_IMG_ENDPOINT
- API endpoint to upload images to
REACT_APP_KEY_ENDPOINT
- API endpoint to store the user's OpenAI API key
SECRET_KEY
- for flask sessions configuration
REDIS_HOST
- Redis cloud endpoint
REDIS_PWD
- Redis cloud endpoint password
REDIS_PORT
- Redis cloud port
POST /key
Parameter | Type | Description |
---|---|---|
input |
string |
(Required) Your OpenAI API key |
POST /upload
Parameter | Type | Description |
---|---|---|
images |
object (form-data) |
(Required) Image to analyse |
Client: React, Redux, TailwindCSS
Server: Flask, Render, Redis
RAG: Pinecone, OpenAI models (gpt-4o, text-embedding-3-large), LangChain
todo:
- link frontend to be processed by lc backend on flask ✔️
- fix image processing errors - fix upload and api key endpoints ✔️
- Convert image recognition results to embeddings to query pinecone vector store ✔️
- prepare images for testing
- firebase authentication
- set up feedback database for RLHF