diff --git a/rag-with-dockling/README.md b/rag-with-dockling/README.md
index 4c37f99b7..f7b8da82b 100644
--- a/rag-with-dockling/README.md
+++ b/rag-with-dockling/README.md
@@ -19,6 +19,31 @@ This project leverages LlamaIndex and IBM's Docling for RAG over excel sheets. Y
 
 ---
 
+## 🐞 Issue You may face
+### 1. Pickle Error with `@st.cache_resource`
+The app might fail with: `An error occurred: cannot pickle 'classmethod' object`
+
+> ✅ **Solution**: Don’t cache non-picklable objects like the Ollama client or embeddings. Instead, store them in Streamlit's session state:
+> ```python
+> if "llm_client" not in st.session_state:
+>     st.session_state.llm_client = Ollama(model="llama3.2")
+> ```
+
+### 2. App Extremely Slow (incase Used another Large Model)
+This often happens due to high memory usage. `ollama` was observed using 10+ GB RAM on an 8 GB Mac, leading to heavy swapping. Large embedding models like `bge-large-en-v1.5` also consume significant memory.
+
+> ✅ **Solution**:
+> * **Use smaller Ollama models**:
+>     * `qwen2:1.5b`
+>     * `llama3.2:1b`
+>     * `mistral:7b-instruct-q4_K_M`
+> * **Use smaller embeddings**:
+>     ```python
+>     HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+>     ```
+
+---
+
 ## 📬 Stay Updated with Our Newsletter!
 **Get a FREE Data Science eBook** 📖 with 150+ essential lessons in Data Science when you subscribe to our newsletter! Stay in the loop with the latest tutorials, insights, and exclusive resources. [Subscribe now!](https://join.dailydoseofds.com)