Upload 6 files

Dockerfile

@@ -8,9 +8,20 @@ RUN apt-get update && apt-get install -y \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
-# Install Python dependencies
+# Install Python dependencies in layers to optimize caching and avoid timeouts
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+
+# 1. Install core dependencies
+RUN pip install --no-cache-dir fastapi uvicorn pydantic-settings python-multipart pypdf python-docx
+
+# 2. Install ML/RAG dependencies (Large)
+RUN pip install --no-cache-dir langchain langchain-community langchain-huggingface chromadb huggingface-hub
+
+# 3. Install Torch and Transformers (Very Large)
+RUN pip install --no-cache-dir torch transformers accelerate bitsandbytes
+
+# 4. Install llama-cpp-python using pre-built CPU wheels to avoid compilation timeout
+RUN pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/wheels/cpu
 
 # Copy application code
 COPY . .

requirements.txt

@@ -12,5 +12,4 @@ transformers
 bitsandbytes
 accelerate
 torch
-llama-cpp-python
 huggingface-hub