fix packaging and imports and introduce tests with pytest.

still issues with celery worker.

.github/workflows/pytest.yml

@@ -24,5 +24,4 @@ jobs:
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
       - name: Test with pytest
         run: |
-          cd application
-          pytest
+          python -m pytest

application/Dockerfile

@@ -14,10 +14,10 @@ FROM python:3.10-slim-bullseye
 COPY --from=builder /usr/local/ /usr/local/
 
 WORKDIR /app
-COPY . /app
+COPY . /app/application
 ENV FLASK_APP=app.py
 ENV FLASK_DEBUG=true
 
 EXPOSE 7091
 
-CMD ["gunicorn", "-w", "2", "--timeout", "120", "--bind", "0.0.0.0:7091", "wsgi:app"]
+CMD ["gunicorn", "-w", "2", "--timeout", "120", "--bind", "0.0.0.0:7091", "application.wsgi:app"]

application/app.py

@@ -68,19 +68,20 @@ if platform.system() == "Windows":
 dotenv.load_dotenv()
 
 # load the prompts
-with open("prompts/combine_prompt.txt", "r") as f:
+current_dir = os.path.dirname(os.path.abspath(__file__))
+with open(os.path.join(current_dir, "prompts", "combine_prompt.txt"), "r") as f:
     template = f.read()
 
-with open("prompts/combine_prompt_hist.txt", "r") as f:
+with open(os.path.join(current_dir, "prompts", "combine_prompt_hist.txt"), "r") as f:
     template_hist = f.read()
 
-with open("prompts/question_prompt.txt", "r") as f:
+with open(os.path.join(current_dir, "prompts", "question_prompt.txt"), "r") as f:
     template_quest = f.read()
 
-with open("prompts/chat_combine_prompt.txt", "r") as f:
+with open(os.path.join(current_dir, "prompts", "chat_combine_prompt.txt"), "r") as f:
     chat_combine_template = f.read()
 
-with open("prompts/chat_reduce_prompt.txt", "r") as f:
+with open(os.path.join(current_dir, "prompts", "chat_reduce_prompt.txt"), "r") as f:
     chat_reduce_template = f.read()
 
 api_key_set = settings.API_KEY is not None
@@ -92,7 +93,7 @@ app.config["CELERY_BROKER_URL"] = settings.CELERY_BROKER_URL
 app.config["CELERY_RESULT_BACKEND"] = settings.CELERY_RESULT_BACKEND
 app.config["MONGO_URI"] = settings.MONGO_URI
 celery = Celery()
-celery.config_from_object("celeryconfig")
+celery.config_from_object("application.celeryconfig")
 mongo = MongoClient(app.config["MONGO_URI"])
 db = mongo["docsgpt"]
 vectors_collection = db["vectors"]
@@ -129,6 +130,7 @@ def get_vectorstore(data):
             vectorstore = ""
     else:
         vectorstore = ""
+    vectorstore = os.path.join("application", vectorstore)
     return vectorstore
 
 

application/tests/test_app.py

@@ -1,37 +0,0 @@
-from application.app import get_vectorstore
-
-
-# Test cases for get_vectorstore function
-def test_no_active_docs():
-    data = {}
-    assert get_vectorstore(data) == ""
-
-
-def test_default_active_docs():
-    data = {"active_docs": "default"}
-    assert get_vectorstore(data) == ""
-
-
-def test_local_default_active_docs():
-    data = {"active_docs": "local/default"}
-    assert get_vectorstore(data) == ""
-
-
-def test_local_custom_active_docs():
-    data = {"active_docs": "local/custom_index"}
-    assert get_vectorstore(data) == "indexes/local/custom_index"
-
-
-def test_remote_active_docs():
-    data = {"active_docs": "remote_index"}
-    assert get_vectorstore(data) == "vectors/remote_index"
-
-
-def test_active_docs_not_in_data():
-    data = {"other_key": "value"}
-    assert get_vectorstore(data) == ""
-
-
-def test_multiple_slashes_in_active_docs():
-    data = {"active_docs": "local/some/other/index"}
-    assert get_vectorstore(data) == "indexes/local/some/other/index"

docker-compose-azure.yaml

@@ -13,7 +13,6 @@ services:
 
   backend:
     build: ./application
-    working_dir: /application
     environment:
       - API_KEY=$OPENAI_API_KEY
       - EMBEDDINGS_KEY=$OPENAI_API_KEY
@@ -28,16 +27,15 @@ services:
     ports:
       - "7091:7091"
     volumes:
-      - ./application/indexes:/application/indexes
-      - ./application/inputs:/application/inputs
-      - ./application/vectors:/application/vectors
+      - ./application/indexes:/app/application/indexes
+      - ./application/inputs:/app/application/inputs
+      - ./application/vectors:/app/application/vectors
     depends_on:
         - redis
         - mongo
 
   worker:
     build: ./application
-    working_dir: /application
     command: celery -A application.app.celery worker -l INFO
     environment:
       - API_KEY=$OPENAI_API_KEY

docker-compose.yaml

@@ -13,7 +13,6 @@ services:
 
   backend:
     build: ./application
-    working_dir: /application
     environment:
       - API_KEY=$OPENAI_API_KEY
       - EMBEDDINGS_KEY=$OPENAI_API_KEY
@@ -23,16 +22,15 @@ services:
     ports:
       - "7091:7091"
     volumes:
-      - ./application/indexes:/application/indexes
-      - ./application/inputs:/application/inputs
-      - ./application/vectors:/application/vectors
+      - ./application/indexes:/app/application/indexes
+      - ./application/inputs:/app/application/inputs
+      - ./application/vectors:/app/application/vectors
     depends_on:
       - redis
       - mongo
 
   worker:
     build: ./application
-    working_dir: /application
     command: celery -A application.app.celery worker -l INFO
     environment:
       - API_KEY=$OPENAI_API_KEY

tests/test_app.py

@@ -0,0 +1,28 @@
+from application.app import get_vectorstore
+import os
+
+
+# Test cases for get_vectorstore function
+def test_no_active_docs():
+    data = {}
+    assert get_vectorstore(data) == os.path.join("application", "")
+
+
+def test_local_default_active_docs():
+    data = {"active_docs": "local/default"}
+    assert get_vectorstore(data) == os.path.join("application", "")
+
+
+def test_local_non_default_active_docs():
+    data = {"active_docs": "local/something"}
+    assert get_vectorstore(data) == os.path.join("application", "indexes/local/something")
+
+
+def test_default_active_docs():
+    data = {"active_docs": "default"}
+    assert get_vectorstore(data) == os.path.join("application", "")
+
+
+def test_complex_active_docs():
+    data = {"active_docs": "local/other/path"}
+    assert get_vectorstore(data) == os.path.join("application", "indexes/local/other/path")