Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/easonlai/chat_with_pdf_streamlit

In this repository, you will discover how Streamlit, can work seamlessly with Azure OpenAI Service's Embedding and GPT 3.5 models. These tools make it possible to create a user-friendly web application that enables users to ask questions in natural language about a PDF file they have uploaded.
https://github.com/easonlai/chat_with_pdf_streamlit

azure azure-openai azure-openai-api azure-openai-service openai openai-api python python3 semantic-search streamlit streamlit-webapp

Last synced: 2 months ago
JSON representation

Host: GitHub
URL: https://github.com/easonlai/chat_with_pdf_streamlit
Owner: easonlai
Created: 2023-08-24T14:38:57.000Z (over 1 year ago)
Default Branch: main
Last Pushed: 2023-08-29T15:06:09.000Z (over 1 year ago)
Last Synced: 2024-04-28T05:09:39.806Z (9 months ago)
Topics: azure, azure-openai, azure-openai-api, azure-openai-service, openai, openai-api, python, python3, semantic-search, streamlit, streamlit-webapp
Language: Python
Homepage:
Size: 4.07 MB
Stars: 5
Watchers: 2
Forks: 1
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# Semantic Search Web App (Chat with PDF) with Streamlit and Azure OpenAI Service

In this repository, you will discover how [Streamlit](https://streamlit.io/), a Python framework for developing interactive data applications, can work seamlessly with [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview)'s [Embedding](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#embeddings-models) and [GPT 3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/legacy-models#gpt-35-models) models. These tools make it possible to create a user-friendly web application that enables users to ask questions in natural language about a PDF file they have uploaded. It is a simple yet effective solution that allows users to retrieve valuable information from the document by semantic searching.

* [app.py](https://github.com/easonlai/chat_with_pdf_streamlit/blob/main/app.py) <-- Sample using FAISS (Facebook AI Similarity Search) as a Vector Database to store the embedding vectors and perform similar searches.

**Architecture**
![alt text](https://github.com/easonlai/chat_with_pdf_streamlit/blob/main/git-images/git-image-1.png)

**To run this Streamlit web app**
```
streamlit run app.py
```

Enjoy!