polish-and-docker

Signed-off-by: Adrian Cole <[email protected]>

supporting-blog-content/building-multimodal-rag-with-elasticsearch-gotham/.dockerignore

@@ -0,0 +1,8 @@
+# Ignore everything
+**
+
+# Allow specific files and directories
+!requirements.txt
+!data/
+!src/
+!stages/

supporting-blog-content/building-multimodal-rag-with-elasticsearch-gotham/.env.template

@@ -1,13 +1,17 @@
-# Elasticsearch Configuration
-ELASTIC_API_KEY=your_api_key_here
-ELASTICSEARCH_ENDPOINT=your_elastic_endpoint
+# Make a copy of this file with the name .env and assign values to variables
+
+# How you connect to Elasticsearch: change details to your instance
+ELASTICSEARCH_URL=
+ELASTICSEARCH_API_KEY=
+# If not using API key, uncomment these and fill them in:
+# ELASTICSEARCH_USER=elastic
+# ELASTICSEARCH_PASSWORD=elastic
 
 # OpenAI Configuration
-OPENAI_API_KEY=your_openai_api_key_here
+OPENAI_API_KEY=
 
 # Model Configuration
-MODEL_PATH=~/.cache/torch/checkpoints/imagebind_huge.pth
 
 # Optional Configuration
-#LOG_LEVEL=INFO
-#DEBUG=False
+# LOG_LEVEL=INFO
+# DEBUG=False

supporting-blog-content/building-multimodal-rag-with-elasticsearch-gotham/Dockerfile

@@ -1,20 +1,36 @@
-FROM ubuntu:24.04
+# Use non-slim image due to OS dependencies of python packages. This gives us
+# git, build-essential, libglib2 (opencv) and gomp (torchaudio).
+FROM python:3.12
 
-# Install necessary packages
-RUN apt update && apt install -y --no-install-recommends \
-    python3 \
-    python3-pip \
-    python3-venv \
-    g++ \
-    gcc \
-    python3.12-dev
+COPY /requirements.txt .
 
-# Create and activate a virtual environment
-RUN python3 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
+# Our python requirements have some OS dependencies beyond the base layer:
+#
+# * imagebind pulls in cartopy which has OS dependencies on geos and proj
+# * opencv has a runtime OS dependency on libgl1-mesa-glx
+#
+# The dev dependencies are installed temporarily to compile the wheels.
+# We leave the only the runtime dependencies, to keep the image smaller.
+RUN apt-get update && \
+    # install build and runtime dependencies
+    apt-get install -y --no-install-recommends \
+        libgeos-dev \
+        libproj-dev \
+        libgeos-c1v5 \
+        libproj25 \
+        libgl1-mesa-glx && \
+    # Install everything except xformers first
+    grep -v "\bxformers\b" requirements.txt > /tmp/r.txt && pip install -r /tmp/r.txt && \
+    # Now, install xformers, as it should be able to see torch now
+    grep "\bxformers\b" requirements.txt > /tmp/r.txt && pip install -r /tmp/r.txt && \
+    # remove build dependencies
+    apt-get purge -y libgeos-dev libproj-dev && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+RUN mkdir -p ./data ./src ./stages
+COPY ./data ./data
+COPY ./src ./src
+COPY ./stages ./stages
 
-# Install Python packages in the virtual environment
-RUN pip install --upgrade pip
-RUN pip install torch
-RUN pip install wheel setuptools
-RUN pip install transformers xformers

supporting-blog-content/building-multimodal-rag-with-elasticsearch-gotham/README.md

@@ -11,67 +11,34 @@ The pipeline demonstrates how to:
 
 ## Prerequisites
 
-- Python 3.10+
+- A Docker runtime with 8GB+ free ram
+  - GPU is optional, but recommended
 - Elasticsearch cluster (cloud or local)
 - OpenAI API key - Setup an OpenAI account and create a [secret key](https://platform.openai.com/docs/quickstart)
-- 8GB+ RAM
-- GPU (optional but recommended)
 
 ## Quick Start
 
-1. **Setup Environment**
-```bash
-rm -rf .venv requirements.txt
-python3 -m venv .venv
-source .venv/bin/activate
-pip install pip-tools
-# Recreate requirements.txt
-pip-compile
-# Install main dependencies
-pip install -r requirements.txt
-
-
-
-python3 -m venv .venv
-source .venv/bin/activate
-pip install "python-dotenv[cli]"
-pip install -r requirements-torch.txt
-pip install -r requirements.txt
-
-# Make sure you have pytorch installed and Python 3.10+
-pip install torch torchvision torchaudio
-
-# Create and activate virtual environment
-python -m venv env_mmrag
-source env_mmrag/bin/activate  # Unix/MacOS
-# or
-.\env_mmrag\Scripts\activate   # Windows
-
-# Install dependencies
-pip install -r requirements.txt
-```
+This example runs four stages as docker compose services:
 
-2. **Configure Credentials**
-Create a `.env` file:
-```env
-ELASTICSEARCH_ENDPOINT="your-elasticsearch-endpoint"
-ELASTIC_API_KEY="your-elastic-api-key"
-OPENAI_API_KEY="your-openai-api-key"
+```mermaid
+graph TD
+    verify-file-structure --> generate-embeddings
+    generate-embeddings --> index-content
+    index-content --> search-and-analyze
 ```
 
-3. **Run the Demo**
-```bash
-# Verify file structure
-python stages/01-stage/files_check.py
+First, copy [env.example](env.example) to `.env` and fill in values noted inside.
 
-# Generate embeddings
-python stages/02-stage/test_embedding_generation.py
+Now, enter below to run the pipeline:
+```bash
+docker compose run --build --rm search-and-analyze
+```
 
-# Index content
-python stages/03-stage/index_all_modalities.py
+The first time takes a while to build the image and download ImageBind weights.
 
-# Search and analyze
-python stages/04-stage/rag_crime_analyze.py
+If you want to re-run just one stage, add `--no-deps` like this:
+```bash
+docker compose run --no-deps --build --rm search-and-analyze
 ```
 
 ## Project Structure

supporting-blog-content/building-multimodal-rag-with-elasticsearch-gotham/docker-compose.yml

@@ -0,0 +1,61 @@
+name: gotham-city-crime-analysis
+
+services:
+  verify-file-structure:
+    build:
+      context: .
+    container_name: verify-file-structure
+    restart: 'no'  # no need to re-verify file structure
+    env_file:
+      - .env
+    command: python stages/01-stage/files_check.py
+    extra_hosts:  # send localhost traffic to the docker host, e.g. your laptop
+        - "localhost:host-gateway"
+
+  generate-embeddings:
+    depends_on:
+      verify-file-structure:
+        condition: service_completed_successfully
+    build:
+      context: .
+    container_name: generate-embeddings
+    restart: 'no'  # no need to re-generate embeddings
+    env_file:
+      - .env
+    command: python stages/02-stage/test_embedding_generation.py
+    extra_hosts:  # send localhost traffic to the docker host, e.g. your laptop
+        - "localhost:host-gateway"
+    volumes:
+      - torch-checkpoints:/root/cache/torch/checkpoints/
+
+  index-content:
+    depends_on:
+      generate-embeddings:
+        condition: service_completed_successfully
+    build:
+      context: .
+    container_name: index-content
+    restart: 'no'  # no need to re-verify file structure
+    env_file:
+      - .env
+    command: python stages/03-stage/index_all_modalities.py
+    extra_hosts:  # send localhost traffic to the docker host, e.g. your laptop
+        - "localhost:host-gateway"
+
+  search-and-analyze:
+    depends_on:
+      index-content:
+        condition: service_completed_successfully
+    build:
+      context: .
+    container_name: search-and-analyze
+    restart: 'no'  # no need to re-verify file structure
+    env_file:
+      - .env
+    command: python stages/04-stage/rag_crime_analyze.py
+    extra_hosts:  # send localhost traffic to the docker host, e.g. your laptop
+        - "localhost:host-gateway"
+
+volumes:
+  # Avoid re-downloading a >4GB model checkpoint
+  torch-checkpoints: