Spaces:
Sleeping
Sleeping
Create README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,18 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 📄 Chat with your PDF (HuggingFace RAG)
|
| 2 |
+
|
| 3 |
+
This Space lets you upload a PDF and ask questions about it.
|
| 4 |
+
|
| 5 |
+
- Embeddings: `sentence-transformers/all-MiniLM-L6-v2`
|
| 6 |
+
- LLM: `google/gemma-2b-it`
|
| 7 |
+
- Framework: Streamlit
|
| 8 |
+
- Architecture: Retrieval-Augmented Generation (RAG)
|
| 9 |
+
|
| 10 |
+
## How it works
|
| 11 |
+
|
| 12 |
+
1. Upload a PDF in the sidebar.
|
| 13 |
+
2. The app extracts text, splits into chunks, and embeds them.
|
| 14 |
+
3. When you ask a question, the app:
|
| 15 |
+
- embeds the question
|
| 16 |
+
- retrieves the most relevant chunks
|
| 17 |
+
- passes them with the question to the LLM
|
| 18 |
+
4. The model answers based **only** on the document context.
|