Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,3 +10,55 @@ pinned: false
|
|
| 10 |
---
|
| 11 |
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
|
| 13 |
+
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Chat With Documents 🤖📄
|
| 17 |
+
|
| 18 |
+
Welcome to the **Chat with Documents** app! 🚀 This Streamlit app allows you to upload PDF and PPT files, extract their content, store the extracted text in a vector store, and interact with it using natural language queries! 🤖💬
|
| 19 |
+
|
| 20 |
+
Built with **LangChain**, **OpenAI**, **Streamlit**, and **Astra DB**, this project leverages the power of LLMs (Large Language Models) to allow users to chat with their documents like never before. 🧠
|
| 21 |
+
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
### 🚀 **Features**
|
| 25 |
+
|
| 26 |
+
- **PDF & PPT Extraction**: Upload PDF and PowerPoint files to extract text! 📄➡️📝
|
| 27 |
+
- **Vector Store**: Automatically stores extracted text in a **Cassandra** vector store. 🔍📚
|
| 28 |
+
- **Ask Anything**: Ask questions about the document and get answers powered by **OpenAI**! 🤖❓
|
| 29 |
+
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
+
### 🛠️ **Tech Stack**
|
| 33 |
+
- **Streamlit**: Frontend framework to interact with the app.
|
| 34 |
+
- **LangChain**: For seamless document processing and querying.
|
| 35 |
+
- **OpenAI**: For LLM integration to provide intelligent responses.
|
| 36 |
+
- **Astra DB**: Database for storing and managing vectorized text data.
|
| 37 |
+
- **Python Libraries**: PyPDF2, python-pptx, cassio, and more.
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
### 💡 **How It Works**
|
| 44 |
+
|
| 45 |
+
- Upload a **PDF** or **PPT** file using the file uploader. 📤
|
| 46 |
+
- The app will extract text from the file using **PyPDF2** (for PDFs) or **python-pptx** (for PPTs). 📄➡️📝
|
| 47 |
+
- The extracted text is split into manageable chunks using **LangChain's CharacterTextSplitter**. ✂️
|
| 48 |
+
- The chunks are then added to **Cassandra** as vectorized data using **OpenAI embeddings**. 🔄
|
| 49 |
+
- Ask any query about the content of your document, and the app will respond using the power of **OpenAI**! 🤖💬
|
| 50 |
+
|
| 51 |
+
---
|
| 52 |
+
|
| 53 |
+
### 🎯 **Why Use This?**
|
| 54 |
+
|
| 55 |
+
- **Make documents interactive**: Easily explore the content of your documents by asking questions.
|
| 56 |
+
- **Quick retrieval**: With the text stored in a vector store, you can query the content efficiently.
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
### ✨ **Enjoy the App!** ✨
|
| 62 |
+
Now, go ahead and chat with your documents! 😄
|
| 63 |
+
|
| 64 |
+
---
|