Fix dependency related build issues in Dockerfiles (#2135)

* Fix a path issue in Dockerfile-GPU

* Fix paths in Dockerfile-GPU

* Add workflow_dispatch to docker build task

* Remove reference to optional component from ui/, not needed anymore

* Move pytorch installation last to avoid replacing it later

* Remove optional import from rest_api too, no more needed

* Change path in ui/Dockerfile

* ui container works again

* Complete review of import paths

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

.github/workflows/docker_build.yml

@@ -1,6 +1,7 @@
 name: docker-build
 
 on:
+  workflow_dispatch:
   push:
     branches:
       - master

Dockerfile

@@ -22,7 +22,7 @@ COPY haystack /home/user/haystack/
 # Copy package files & models
 COPY setup.py setup.cfg pyproject.toml VERSION.txt LICENSE README.md models* /home/user/
 # Copy REST API code
-COPY rest_api /home/user/rest_api
+COPY rest_api /home/user/rest_api/
 
 # Install package
 RUN pip install --upgrade pip
@@ -33,8 +33,8 @@ RUN pip freeze
 RUN python3 -c "from haystack.utils.docker import cache_models;cache_models()"
 
 # create folder for /file-upload API endpoint with write permissions, this might be adjusted depending on FILE_UPLOAD_PATH
-RUN mkdir -p /home/user/file-upload
-RUN chmod 777 /home/user/file-upload
+RUN mkdir -p /home/user/rest_api/file-upload
+RUN chmod 777 /home/user/rest_api/file-upload
 
 # optional : copy sqlite db if needed for testing
 #COPY qa.db /home/user/

Dockerfile-GPU

@@ -5,9 +5,6 @@ WORKDIR /home/user
 ENV LC_ALL=C.UTF-8
 ENV LANG=C.UTF-8
 
-# create folder for /file-upload API endpoint with write permissions, this might be adjusted depending on FILE_UPLOAD_PATH
-RUN mkdir -p /home/user/file-upload && chmod 777 /home/user/file-upload
-
 # Install software dependencies
 RUN apt-get update && apt-get install -y software-properties-common && \
     add-apt-repository ppa:deadsnakes/ppa && \
@@ -36,24 +33,26 @@ RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.7 1
     update-alternatives --set python3 /usr/bin/python3.7
 
 # Copy Haystack code
-COPY haystack /home/user/haystack
+COPY haystack /home/user/haystack/
 # Copy package files & models
 COPY setup.py setup.cfg pyproject.toml VERSION.txt LICENSE README.md models* /home/user/
 # Copy REST API code
-COPY rest_api /home/user/
-
-RUN pip install --upgrade pip
-RUN echo "Install required packages" && \
-    # Install PyTorch for CUDA 11
-    pip3 install --no-cache-dir torch==1.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html
+COPY rest_api /home/user/rest_api/
 
 # Install package
-RUN pip install --no-cache .[docstores-gpu,crawler,preprocessing,ocr,ray]
-RUN pip install --no-cache rest_api/
+RUN pip install --upgrade pip
+RUN pip install --no-cache-dir .[docstores-gpu,crawler,preprocessing,ocr,ray]
+RUN pip install --no-cache-dir rest_api/
+# Install PyTorch for CUDA 11
+RUN pip3 install --no-cache-dir torch==1.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html
 
 # Cache Roberta and NLTK data
 RUN python3 -c "from haystack.utils.docker import cache_models;cache_models()"
 
+# create folder for /file-upload API endpoint with write permissions, this might be adjusted depending on FILE_UPLOAD_PATH
+RUN mkdir -p /home/user/rest_api/file-upload
+RUN chmod 777 /home/user/rest_api/file-upload
+
 # optional : copy sqlite db if needed for testing
 #COPY qa.db /home/user/
 

docker-compose-gpu.yml

@@ -14,7 +14,7 @@ services:
           - driver: nvidia
             count: 1
             capabilities: [gpu]
-    # Mount custom Pipeline YAML and custom Components.
+    # # Mount custom Pipeline YAML and custom Components.
     # volumes:
     #   - ./rest_api/pipeline:/home/user/rest_api/pipeline
     ports:
@@ -59,4 +59,4 @@ services:
       - DEFAULT_QUESTION_AT_STARTUP
       - DEFAULT_DOCS_FROM_RETRIEVER
       - DEFAULT_NUMBER_OF_ANSWERS
-    command: "/bin/bash -c 'sleep 15 && streamlit run webapp.py'"
+    command: "/bin/bash -c 'sleep 15 && python -m streamlit run ui/webapp.py'"

docker-compose.yml

@@ -48,4 +48,4 @@ services:
       - DEFAULT_QUESTION_AT_STARTUP
       - DEFAULT_DOCS_FROM_RETRIEVER
       - DEFAULT_NUMBER_OF_ANSWERS
-    command: "/bin/bash -c 'sleep 15 && streamlit run webapp.py'"
+    command: "/bin/bash -c 'sleep 15 && python -m streamlit run ui/webapp.py'"

rest_api/application.py

@@ -5,21 +5,15 @@ logger = logging.getLogger(__name__)
 logging.getLogger("elasticsearch").setLevel(logging.WARNING)
 logging.getLogger("haystack").setLevel(logging.INFO)
 
-try:
-    import uvicorn
-    from fastapi import FastAPI, HTTPException
-    from fastapi.routing import APIRoute
-    from fastapi.openapi.utils import get_openapi
-    from starlette.middleware.cors import CORSMiddleware
+import uvicorn
+from fastapi import FastAPI, HTTPException
+from fastapi.routing import APIRoute
+from fastapi.openapi.utils import get_openapi
+from starlette.middleware.cors import CORSMiddleware
 
-    from rest_api.controller.errors.http_error import http_error_handler
-    from rest_api.config import ROOT_PATH
-    from rest_api.controller.router import router as api_router
-
-except (ImportError, ModuleNotFoundError) as ie:
-    from haystack.utils.import_utils import _optional_component_not_installed
-
-    _optional_component_not_installed("rest_api", "rest", ie)
+from rest_api.controller.errors.http_error import http_error_handler
+from rest_api.config import ROOT_PATH
+from rest_api.controller.router import router as api_router
 
 
 def get_application() -> FastAPI:

ui/Dockerfile

@@ -5,15 +5,17 @@ WORKDIR /home/user
 RUN apt-get update && apt-get install -y curl git pkg-config cmake
 
 # copy code
-COPY setup.py /home/user/
-COPY utils.py /home/user/
-COPY webapp.py /home/user/
+RUN mkdir ui/
+COPY setup.py /home/user/ui
+COPY utils.py /home/user/ui
+COPY webapp.py /home/user/ui
 COPY eval_labels_example.csv /home/user/
 
 # install as a package
-RUN pip install .
+RUN pip install --upgrade pip
+RUN pip install ui/
 
 EXPOSE 8501
 
 # cmd for running the API
-CMD ["streamlit", "run", "webapp.py"]
+CMD ["python", "-m", "streamlit", "run", "ui/webapp.py"]

ui/utils.py

@@ -5,13 +5,7 @@ import logging
 import requests
 from time import sleep
 from uuid import uuid4
-
-try:
-    import streamlit as st
-except (ImportError, ModuleNotFoundError) as ie:
-    from haystack.utils.import_utils import _optional_component_not_installed
-
-    _optional_component_not_installed(__name__, "ui", ie)
+import streamlit as st
 
 
 API_ENDPOINT = os.getenv("API_ENDPOINT", "http://localhost:8000")

ui/webapp.py

@@ -1,21 +1,14 @@
 import os
 import sys
-
 import logging
 import pandas as pd
 from json import JSONDecodeError
 from pathlib import Path
+import streamlit as st
+from annotated_text import annotation
+from markdown import markdown
 
-try:
-    import streamlit as st
-    from annotated_text import annotation
-    from markdown import markdown
-
-    from ui.utils import haystack_is_ready, query, send_feedback, upload_doc, haystack_version, get_backlink
-except (ImportError, ModuleNotFoundError) as ie:
-    from haystack.utils.import_utils import _optional_component_not_installed
-
-    _optional_component_not_installed(__name__, "ui", ie)
+from ui.utils import haystack_is_ready, query, send_feedback, upload_doc, haystack_version, get_backlink
 
 
 # Adjust to a question that you would like users to see in the search bar when they load the UI: