add docker test

Signed-off-by: Adrian Cole <[email protected]>
elastic · Feb 20, 2025 · 19e6280 · 19e6280
1 parent 3873ccd
commit 19e6280
Show file tree

Hide file tree

Showing 5 changed files with 32 additions and 10 deletions.
diff --git a/.github/workflows/docker-chatbot-rag-app.yml b/.github/workflows/docker-chatbot-rag-app.yml
@@ -12,7 +12,9 @@ on:
     branches:
       - main
     paths:
-      # Verify changes to the Dockerfile on PRs
+      # Verify changes to the Dockerfile on PRs, tainted when we update ES.
+      - docker/docker-compose-elastic.yml
+      - example-apps/chatbot-rag-app/docker-compose.yml
       - example-apps/chatbot-rag-app/Dockerfile
       - .github/workflows/docker-chatbot-rag-app.yml
       - '!**/*.md'
@@ -42,13 +44,26 @@ jobs:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
+      # This builds the image and pushes its digest if a multi-architecture
+      # image will be made later (event_name == 'push'). As a side-effect the
+      # layers built are in the cache and usable for testing PRs later.
       - uses: docker/build-push-action@v6
         id: build
         with:
           context: example-apps/chatbot-rag-app
           outputs: type=image,name=${{ env.IMAGE }},push-by-digest=true,name-canonical=true,push=${{ github.event_name == 'push' && 'true' || 'false' }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
+      - name: start elasticsearch
+        if: github.event_name == 'pull_request'
+        run: docker compose -f docker/docker-compose-elastic.yml up --quiet-pull -d --wait --wait-timeout 120 elasticsearch
+      - name: test image
+        if: github.event_name == 'pull_request'
+        working-directory: example-apps/chatbot-rag-app
+        run: |  # This tests ELSER is working, which doesn't require an LLM.
+          cp env.example .env
+          docker compose build create-index
+          time docker compose run --build --rm -T create-index
       - name: export digest
         if: github.event_name == 'push'
         run: |

diff --git a/docker/README.md b/docker/README.md
@@ -12,7 +12,7 @@ wget https://raw.githubusercontent.com/elastic/elasticsearch-labs/refs/heads/mai
 Use docker compose to run Elastic stack in the background:
 
 ```bash
-docker compose -f docker-compose-elastic.yml up --force-recreate -d
+docker compose -f docker-compose-elastic.yml up --force-recreate --wait -d
 ```
 
 Then, you can view Kibana at http://localhost:5601/app/home#/

diff --git a/docker/docker-compose-elastic.yml b/docker/docker-compose-elastic.yml
@@ -2,7 +2,7 @@ name: elastic-stack
 
 services:
   elasticsearch:
-    image: docker.elastic.co/elasticsearch/elasticsearch:8.17.0
+    image: docker.elastic.co/elasticsearch/elasticsearch:8.17.2
     container_name: elasticsearch
     ports:
       - 9200:9200
@@ -16,7 +16,8 @@ services:
       - xpack.security.http.ssl.enabled=false
       - xpack.security.transport.ssl.enabled=false
       - xpack.license.self_generated.type=trial
-      # Use minimum heap required by ELSER
+      # Note that ELSER is recommended to have 2GB, but it is JNI (PyTorch).
+      # So, ELSER's memory is in addition to the heap and other overhead.
       - ES_JAVA_OPTS=-Xms2g -Xmx2g
     ulimits:
       memlock:
@@ -37,7 +38,7 @@ services:
     depends_on:
       elasticsearch:
         condition: service_healthy
-    image: docker.elastic.co/elasticsearch/elasticsearch:8.17.0
+    image: docker.elastic.co/elasticsearch/elasticsearch:8.17.2
     container_name: elasticsearch_settings
     restart: 'no'
     command: >
@@ -49,7 +50,7 @@ services:
       '
 
   kibana:
-    image: docker.elastic.co/kibana/kibana:8.17.0
+    image: docker.elastic.co/kibana/kibana:8.17.2
     container_name: kibana
     depends_on:
       elasticsearch_settings:
@@ -73,7 +74,7 @@ services:
       interval: 1s
 
   apm-server:
-    image: docker.elastic.co/apm/apm-server:8.17.0
+    image: docker.elastic.co/apm/apm-server:8.17.2
     container_name: apm-server
     depends_on:
       elasticsearch:

diff --git a/example-apps/chatbot-rag-app/api/chat.py b/example-apps/chatbot-rag-app/api/chat.py
@@ -6,6 +6,7 @@
     get_elasticsearch_chat_message_history,
 )
 from flask import current_app, render_template, stream_with_context
+from functools import cache
 from langchain_elasticsearch import (
     ElasticsearchStore,
     SparseVectorStrategy,
@@ -27,11 +28,16 @@
     strategy=SparseVectorStrategy(model_id=ELSER_MODEL),
 )
 
-llm = get_llm()
+
+@cache
+def get_lazy_llm():
+    return get_llm()
 
 
 @stream_with_context
 def ask_question(question, session_id):
+    llm = get_lazy_llm()
+
     yield f"data: {SESSION_ID_TAG} {session_id}\n\n"
     current_app.logger.debug("Chat session ID: %s", session_id)
 

diff --git a/example-apps/chatbot-rag-app/docker-compose.yml b/example-apps/chatbot-rag-app/docker-compose.yml
@@ -2,7 +2,7 @@ name: chatbot-rag-app
 
 services:
   create-index:
-    image: ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app
+    image: ${IMAGE:-ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app}
     build:
       context: .
     container_name: create-index
@@ -21,7 +21,7 @@ services:
       create-index:
         condition: service_completed_successfully
     container_name: api-frontend
-    image: ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app
+    image: ${IMAGE:-ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app}
     build:
       context: .
     env_file: