Document-QandA / README.md
raseel-zymr's picture
Initial commit with streamlit
eaf0e00
---
title: Document QandA
emoji: πŸ†
colorFrom: red
colorTo: pink
sdk: streamlit
sdk_version: 1.21.0
app_file: app.py
pinned: false
license: mit
---
# Document Question & Answer
A Langchain-based application to upload any text or PDF document, ask relevant Questions to it and expect summarised answers.
### Pre-requisites
$ pip install langchain huggingface_hub sentence_transformers faiss-cpu unstructured chromadb Cython tiktoken unstructured[local-inference]
Or
$ pip install -r requirements.txt
* Install the above Python packages
### Reference:
* Vectorstore: https://python.langchain.com/en/latest/modules/indexes/vectorstores.html