Upload 3 files

README.md

@@ -117,7 +117,7 @@ streamlit run app.py
 
 1. Create a new Hugging Face Space.
 2. Choose Streamlit as the Space SDK.
-3. Upload `app.py`, `README.md`, `requirements.txt`, `Dockerfile`, `.gitattributes`, and the `assets/` folder.
+3. Upload `app.py`, `README.md`, `requirements.txt`, `runtime.txt`, `.gitattributes`, and the `assets/` folder. `Dockerfile` is included for GitHub/Docker users, but a normal Streamlit Space does not require it.
 4. Add `GROQ_API_KEY` under Space Settings -> Secrets.
 5. Confirm `app.py` is the entry point.
 6. Restart the Space if dependencies are updated.
@@ -149,6 +149,7 @@ The app is designed to run on Hugging Face Spaces CPU. It uses CPU-compatible em
 ├── app.py
 ├── README.md
 ├── requirements.txt
+├── runtime.txt
 ├── Dockerfile
 ├── .gitattributes
 └── assets/

requirements.txt

@@ -6,10 +6,8 @@ langchain-community==0.2.16
 langchain-groq==0.1.10
 langchain-huggingface==0.0.3
 langchain-text-splitters==0.2.4
-faiss-cpu>=1.9.0.post1,<1.15.0
+faiss-cpu==1.8.0.post1
 sentence-transformers==3.1.1
-transformers==4.44.2
-torch==2.4.1
 pypdf==4.3.1
 docx2txt==0.8
 tiktoken==0.7.0

runtime.txt

@@ -0,0 +1 @@
+python-3.10