Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,51 +9,4 @@ app_file: app.py
|
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
### 🚀 **Features**
|
| 13 |
|
| 14 |
-
- **PDF & PPT Extraction**: Upload PDF and PowerPoint files to extract text! 📄➡️📝
|
| 15 |
-
- **Vector Store**: Automatically stores extracted text in a **Cassandra** vector store. 🔍📚
|
| 16 |
-
- **Ask Anything**: Ask questions about the document, and get answers powered by **OpenAI**! 🤖❓
|
| 17 |
-
|
| 18 |
-
---
|
| 19 |
-
|
| 20 |
-
### 🛠️ **Tech Stack**
|
| 21 |
-
- **Streamlit**: Frontend framework to interact with the app.
|
| 22 |
-
- **LangChain**: For seamless document processing and querying.
|
| 23 |
-
- **OpenAI**: For LLM integration to provide intelligent responses.
|
| 24 |
-
- **Astra DB**: Database for storing and managing vectorized text data.
|
| 25 |
-
- **Python Libraries**: PyPDF2, python-pptx, cassio, and more.
|
| 26 |
-
|
| 27 |
-
---
|
| 28 |
-
|
| 29 |
-
### 🌍 **Deployment**
|
| 30 |
-
|
| 31 |
-
This project is designed to be deployed on **Hugging Face Spaces**. Just upload your code, and it will run in the cloud! 🌩️
|
| 32 |
-
|
| 33 |
-
Make sure to configure the **Secrets** in Hugging Face Spaces for storing your sensitive API keys securely! 🔒
|
| 34 |
-
|
| 35 |
-
---
|
| 36 |
-
|
| 37 |
-
### 💡 **How It Works**
|
| 38 |
-
|
| 39 |
-
- Upload a **PDF** or **PPT** file using the file uploader. 📤
|
| 40 |
-
- The app will extract text from the file using **PyPDF2** (for PDFs) or **python-pptx** (for PPTs). 📄➡️📝
|
| 41 |
-
- The extracted text is split into manageable chunks using **LangChain's CharacterTextSplitter**. ✂️
|
| 42 |
-
- The chunks are then added to **Cassandra** as vectorized data using **OpenAI embeddings**. 🔄
|
| 43 |
-
- Ask any query about the content of your document, and the app will respond using the power of **OpenAI**! 🤖💬
|
| 44 |
-
|
| 45 |
-
---
|
| 46 |
-
|
| 47 |
-
### 🎯 **Why Use This?**
|
| 48 |
-
|
| 49 |
-
- **Make documents interactive**: Easily explore the content of your documents by asking questions.
|
| 50 |
-
- **Quick retrieval**: With the text stored in a vector store, you can query the content efficiently.
|
| 51 |
-
- **Secure API keys**: API keys are securely managed using environment variables and **Hugging Face Spaces Secrets**. 🔑💼
|
| 52 |
-
|
| 53 |
-
---
|
| 54 |
-
### ✨ **Enjoy the App!** ✨
|
| 55 |
-
Now, go ahead and chat with your documents! 😄
|
| 56 |
-
|
| 57 |
-
---
|
| 58 |
-
|
| 59 |
-
This version now only focuses on the app’s features and deployment, making it more suited for hosting and sharing on Hugging Face Spaces!
|
|
|
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
|
|
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|