Added pyproject.toml file, updated some dependencies

Dockerfile

@@ -1,5 +1,5 @@
 # Stage 1: Build dependencies and download models
-FROM public.ecr.aws/docker/library/python:3.11.11-slim-bookworm AS builder
+FROM public.ecr.aws/docker/library/python:3.11.13-slim-bookworm AS builder
 
 # Install system dependencies.
 RUN apt-get update && apt-get install -y \
@@ -22,15 +22,13 @@ ENV CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS"
 
 COPY requirements_aws.txt .
 
-RUN pip uninstall -y typing_extensions \
-&& pip install --no-cache-dir --target=/install typing_extensions==4.12.2 \
-&& pip install --no-cache-dir --target=/install torch==2.7.1+cpu --extra-index-url https://download.pytorch.org/whl/cpu \
+RUN pip install --no-cache-dir --target=/install torch==2.7.1+cpu --extra-index-url https://download.pytorch.org/whl/cpu \
 && pip install --no-cache-dir --target=/install -r requirements_aws.txt
 
 RUN rm requirements_aws.txt
 
 # Stage 2: Final runtime image
-FROM public.ecr.aws/docker/library/python:3.11.11-slim-bookworm
+FROM public.ecr.aws/docker/library/python:3.11.13-slim-bookworm
 
 # Install system dependencies.
 RUN apt-get update \
@@ -62,7 +60,6 @@ ENV HOME=/home/user \
 	GRADIO_SERVER_NAME=0.0.0.0 \
 	GRADIO_SERVER_PORT=7860 \
 	GRADIO_THEME=huggingface \
-	TLDEXTRACT_CACHE=$HOME/app/tld/.tld_set_snapshot \
 	SYSTEM=spaces
  
 # Set the working directory to the user's home directory

README.md

@@ -3,7 +3,7 @@ title: Large language model topic modelling
 emoji: 📝
 colorFrom: purple
 colorTo: yellow
-sdk: gradio
+sdk: docker
 app_file: app.py
 pinned: true
 license: agpl-3.0

pyproject.toml

@@ -0,0 +1,5 @@
+[project]
+name = "Large language model topic modelling"
+version = "0.1.0"
+description = "Topic model open text data files with a large language model."
+requires-python = ">=3.10"

requirements.txt

@@ -1,5 +1,5 @@
 pandas==2.3.1
-gradio==5.42.0
+gradio==5.44.1
 transformers==4.55.2
 spaces==0.40.0
 boto3==1.40.11
@@ -8,19 +8,19 @@ openpyxl==3.1.5
 markdown==3.7
 tabulate==0.9.0
 lxml==5.3.0
-google-genai==1.30.0
+google-genai==1.32.0
 html5lib==1.1
 beautifulsoup4==4.12.3
 rapidfuzz==3.13.0
 python-dotenv==1.1.0
 # Torch and Llama CPP Python
 # GPU
-torch==2.6.0 --extra-index-url https://download.pytorch.org/whl/cu124 # Latest compatible with CUDA 12.4
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.3.16-cu124/llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl # Specify exact llama_cpp for cuda compatibility on Hugging Face
+#torch==2.6.0 --extra-index-url https://download.pytorch.org/whl/cu124 # Latest compatible with CUDA 12.4
+#https://github.com/abetlen/llama-cpp-python/releases/download/v0.3.16-cu124/llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl # Specify exact llama_cpp for cuda compatibility on Hugging Face
 #
 # CPU only (for e.g. Hugging Face CPU instances): 
-# torch==2.6.0 --extra-index-url https://download.pytorch.org/whl/cpu
-# llama-cpp-python==0.3.16 # should work on local Linux systems, but will be extremely slow on Hugging Face and will most likely time out
+torch==2.7.1 --extra-index-url https://download.pytorch.org/whl/cpu
+llama-cpp-python==0.3.16 # should work on local Linux systems, but will be extremely slow on Hugging Face and will most likely time out
 # For Hugging Face can only specify the latest non-CUDA wheel for Python 3.10, currently only llama-cpp-python v0.3.2 that can only be used with Gemma 2 2b for local inference
 #https://github.com/abetlen/llama-cpp-#python/releases/download/v0.3.2/llama_cpp_python-0.3.2-cp310-cp310-linux_x86_64.whl
 

requirements_aws.txt

@@ -1,5 +1,5 @@
 pandas==2.3.1
-gradio==5.42.0
+gradio==5.44.1
 transformers==4.55.2
 spaces==0.40.0
 boto3==1.40.11
@@ -8,10 +8,10 @@ openpyxl==3.1.5
 markdown==3.7
 tabulate==0.9.0
 lxml==5.3.0
-google-genai==1.30.0
+google-genai==1.32.0
 html5lib==1.1
 beautifulsoup4==4.12.3
 rapidfuzz==3.13.0
 python-dotenv==1.1.0
-torch==2.6.0 --extra-index-url https://download.pytorch.org/whl/cu124 # Latest compatible with CUDA 12.4
+torch==2.7.1 --extra-index-url https://download.pytorch.org/whl/cpu
 llama-cpp-python==0.3.16

requirements_cpu_win.txt

@@ -1,5 +1,5 @@
 pandas==2.3.1
-gradio==5.42.0
+gradio==5.44.1
 transformers==4.55.2
 spaces==0.40.0
 boto3==1.40.11
@@ -8,11 +8,11 @@ openpyxl==3.1.5
 markdown==3.7
 tabulate==0.9.0
 lxml==5.3.0
-google-genai==1.30.0
+google-genai==1.32.0
 html5lib==1.1
 beautifulsoup4==4.12.3
 rapidfuzz==3.13.0
 python-dotenv==1.1.0
 # Following llama-cpp-python installation is that latest that has a wheel for Windows. will only work with Gemma 2
-torch==2.6.0 --extra-index-url https://download.pytorch.org/whl/cpu # Latest compatible with CUDA 12.4
+torch==2.7.1 --extra-index-url https://download.pytorch.org/whl/cpu # Latest compatible with CUDA 12.4
 https://github.com/abetlen/llama-cpp-python/releases/download/v0.3.2/llama_cpp_python-0.3.2-cp311-cp311-win_amd64.whl

requirements_gpu.txt

@@ -1,5 +1,5 @@
 pandas==2.3.1
-gradio==5.44.0
+gradio==5.44.1
 transformers==4.55.2
 spaces==0.40.0
 boto3==1.40.11
@@ -8,7 +8,7 @@ openpyxl==3.1.5
 markdown==3.7
 tabulate==0.9.0
 lxml==5.3.0
-google-genai==1.30.0
+google-genai==1.32.0
 html5lib==1.1
 beautifulsoup4==4.12.3
 rapidfuzz==3.13.0