-
DocQA
Document Question Answering with the added powers of OCR. Also has it's own "Vector Database", no Pinecone needed.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Made a simple Document Question Answering bot which can read document formats like pdf, jpeg, doc, txt and answer questions based on that. Have used open source OCR - tesseract. Have also implemented document chunking and vector storage using OpenAI and numpy. The question answering finally happens by making a call to the OpenAI ChatGPT 3.5 endpoint Check it out and do give it a star if you find it useful- https://github.com/wasabi9/DocQA