edited app.py and Dockerfile

Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.13.5-slim
 
-# Install system dependencies for ctransformers
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
     build-essential \
     libssl-dev \
@@ -9,19 +9,8 @@ RUN apt-get update && apt-get install -y \
     git \
     && rm -rf /var/lib/apt/lists/*
 
-# Create a directory for the model files
+# Set the work directory and copy your application files
 WORKDIR /app
-RUN mkdir -p /app/models
-
-# Download the tinyllama model during the build
-RUN curl -L https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.4-GGUF/resolve/main/tinyllama-1.1b-chat-v0.4.Q4_0.gguf \
-    -o /app/models/tinyllama.gguf
-
-# Download the Deepseek model during the build
-RUN curl -L https://huggingface.co/TheBloke/deepseek-coder-1.3B-base-GGUF/resolve/main/deepseek-coder-1.3b-base-q4_K_M.gguf \
-    -o /app/models/deepseek-coder-1.3b.gguf
-
-# Copy your application files
 COPY requirements.txt ./
 COPY app.py ./
 

app.py

@@ -4,41 +4,55 @@ from langchain.memory import ConversationBufferMemory
 from langchain.memory.chat_message_histories import ChatMessageHistory
 from langchain.prompts import PromptTemplate
 from langchain_core.runnables import RunnableSequence
+from huggingface_hub import hf_hub_download
 import os
 
 # --- Model Definitions ---
-# A dictionary mapping display names to model file paths and types
+# A dictionary mapping display names to model info
 MODEL_MAP = {
     "TinyLlama (1.1B)": {
-        "path": "/app/models/tinyllama.gguf",
+        "repo_id": "TheBloke/TinyLlama-1.1B-Chat-v0.4-GGUF",
+        "filename": "tinyllama-1.1b-chat-v0.4.Q4_0.gguf",
         "type": "llama"
     },
     "Deepseek-Coder (1.3B)": {
-        "path": "/app/models/deepseek-coder-1.3b.gguf",
+        "repo_id": "TheBloke/deepseek-coder-1.3B-base-GGUF",
+        "filename": "deepseek-coder-1.3b-base-q4_K_M.gguf",
         "type": "deepseek"
     }
 }
 
-# ----------------- Streamlit UI and Logic -----------------
-st.set_page_config(layout="wide")
-st.title("My Local Chatbot")
-
-# Sidebar Inputs
-st.sidebar.header("Settings")
-selected_model_name = st.sidebar.selectbox("Choose a Model", list(MODEL_MAP.keys()))
+# --- Model Loading ---
+@st.cache_resource
+def download_model_from_hub(repo_id, filename):
+    st.write(f"Downloading model '{filename}' from Hugging Face Hub...")
+    model_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    return model_path
 
-# Use st.cache_resource to load the LLM once
 @st.cache_resource
 def load_llm(model_name):
-    st.write(f"Loading the '{model_name}' model... this may take a moment.")
+    """Loads the model once and caches it."""
     model_info = MODEL_MAP[model_name]
+    
+    # Download the model file first
+    model_path = download_model_from_hub(model_info["repo_id"], model_info["filename"])
+
+    # Now load the model using the local file path
     llm = CTransformers(
-        model=model_info["path"],
+        model=model_path,
         model_type=model_info["type"],
         config={'max_new_tokens': 2048, 'temperature': 0.7}
     )
     return llm
 
+# ----------------- Streamlit UI and Logic -----------------
+st.set_page_config(layout="wide")
+st.title("My Local Chatbot")
+
+# Sidebar Inputs
+st.sidebar.header("Settings")
+selected_model_name = st.sidebar.selectbox("Choose a Model", list(MODEL_MAP.keys()))
+
 # Load the selected model
 llm = load_llm(selected_model_name)
 st.success(f"Model '{selected_model_name}' loaded successfully!")