Correcting tests and adjusting code for toml-based shared DTO object

config.toml

@@ -0,0 +1,15 @@
+
+[settings]
+db_engine = "neo4j"
+
+[OCR]
+TESSERACT_PATH = "/usr/bin/tesseract"
+POPPLER_PATH = "/usr/bin/pdftotext"
+
+[neo4j]
+NEO4J_URI = "neo4j://database:7687"
+NEO4J_USER = "neo4j"
+NEO4J_PASSWORD = "StrongPsPsP5"
+
+[qdrant]
+in_memory = true

docker/build_dev/dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:22.04
+FROM ubuntu:24.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 ENV POETRY_HOME="/root/.poetry"
@@ -7,9 +7,9 @@ ENV PATH="$POETRY_HOME/bin:$PATH"
 CMD ["bash"]
 
 RUN apt-get update
-RUN apt-get install -y python3 python3-pip curl
+RUN apt-get install -y python3 pipx curl
 RUN curl -sSL https://install.python-poetry.org | python3 -
 
 WORKDIR /ragger
 COPY . /ragger
-RUN make install
+RUN poetry install

docker/integration_tests/dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:22.04
+FROM ubuntu:24.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 ENV POETRY_HOME="/root/.poetry"
@@ -7,7 +7,7 @@ ENV PATH="$POETRY_HOME/bin:$PATH"
 CMD ["bash"]
 
 RUN apt-get update --fix-missing
-RUN apt-get install -y python3 python3-pip git ca-certificates lsb-release ubuntu-keyring software-properties-common curl
+RUN apt-get install -y python3 pipx git ca-certificates lsb-release ubuntu-keyring software-properties-common curl
 RUN curl -sSL https://install.python-poetry.org | python3 -
 
 RUN update-ca-certificates --fresh
@@ -17,9 +17,8 @@ RUN apt install -y libtesseract-dev
 RUN apt install -y poppler-utils
 
 WORKDIR /ragger
-RUN pip install --upgrade pip
 COPY . /ragger
 RUN touch logs.log
-RUN make install
+RUN poetry install
 
 RUN export GIT_PYTHON_GIT_EXECUTABLE=$(which git)

docker/unit_tests/dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:22.04
+FROM ubuntu:24.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 ENV POETRY_HOME="/root/.poetry"
@@ -7,17 +7,16 @@ ENV PATH="$POETRY_HOME/bin:$PATH"
 CMD ["bash"]
 
 RUN apt-get update
-RUN apt-get install -y python3 python3-pip git curl
+RUN apt-get install -y python3 pipx git curl
 RUN curl -sSL https://install.python-poetry.org | python3 -
 
 RUN apt install -y tesseract-ocr
 RUN apt install -y libtesseract-dev
 RUN apt install -y poppler-utils
 
 WORKDIR /ragger
-RUN pip install --upgrade pip
 COPY . /ragger
 RUN touch logs.log
-RUN make install
+RUN poetry install
 
 RUN export GIT_PYTHON_GIT_EXECUTABLE=$(which git)

src/context_search/__init__.py

@@ -2,15 +2,15 @@
 from .data_manager import DataManager
 from .reader import ReadManager
 from .preprocessor import Preprocessor
-from .communicator import Communicator
-from .utils import setup_logger, config_variables
+from .communicator import CommAdapterNeo
+from .utils import setup_logger, EnvInterface
 
 __all__ = [
     'ContextSearch',
     'DataManager',
     'ReadManager',
     'Preprocessor',
-    'Communicator',
+    'CommAdapterNeo',
     'setup_logger',
-    'config_variables'
-]
+    'EnvInterface'
+]

src/context_search/communicator/__init__.py

@@ -1,4 +1,4 @@
 
-from .communicator import Communicator
+from .communicator import CommAdapterNeo
 
-__all__ = ["Communicator"]
+__all__ = ["CommAdapterNeo"]

src/context_search/communicator/communicator.py

@@ -1,5 +1,5 @@
 from neo4j import GraphDatabase
-from qdrant_client import QdrantClient
+from abc import ABC, abstractmethod
 
 from ..utils import setup_logger
 from ..data_classes import LiteratureGraph
@@ -9,13 +9,6 @@
 logger = setup_logger("Communicator Logger", "logs.log")
 
 
-class DatabaseNotSupportedError(BaseException):
-    def __init__(self, db) -> None:
-        super().__init__(
-            ""
-        )
-
-
 class AbstractCommAdapter(ABC):
 
     @abstractmethod
@@ -28,6 +21,15 @@ def connection():
         pass
 
 
+class DatabaseNotSupported(BaseException, AbstractCommAdapter):
+    def __init__(self, *args, **kwargs) -> None:
+        super(BaseException).__init__(
+            "The requested database is not supported.\n"
+            "Supported:\n"
+            "   {Neo4j, Qdrant}"
+        )
+
+
 class CommAdapterNeo(AbstractCommAdapter):
     """Communicator class for interacting with the Neo4j database.
 
@@ -82,7 +84,7 @@ def add_literature_subgraph(
             session,
             literature_graph: LiteratureGraph
     ):
-        session.write_transaction(
+        session.execute_write(
             self._add_literature_subgraph,
             literature_graph
         )
@@ -92,7 +94,7 @@ def create_vector_indexes(self, session):
         """Creates vector indexes for chunks and tags.
         This function is separated from the add_literature_subgraph
         because the indexes cannot be created in the same transaction"""
-        session.write_transaction(self._index_ebeddables)
+        session.execute_write(self._index_ebeddables)
 
     def _add_literature_subgraph(self, tx, literature_graph: LiteratureGraph):
         """Builds the the nodes and relationships based on the given
@@ -117,37 +119,37 @@ def _index_ebeddables(self, tx):
 
     @connection
     def get_literature(self, session, filename):
-        return session.read_transaction(QueryBuilder._get_literature, filename)
+        return session.execute_read(QueryBuilder._get_literature, filename)
 
     @connection
     def get_literature_chunks(self, session, filename):
-        return session.read_transaction(
+        return session.execute_read(
             QueryBuilder._get_literature_chunks,
             filename
         )
 
     @connection
     def get_literature_tags(self, session, filename):
-        return session.read_transaction(
+        return session.execute_read(
             QueryBuilder._get_literature_tags,
             filename
         )
 
     @connection
     def search_n_records(self, session, query, n):
-        return session.read_transaction(
+        return session.execute_read(
             QueryBuilder._search_n_records,
             query,
             n
         )
 
     @connection
     def get_all_literatures(self, session):
-        return session.read_transaction(QueryBuilder._get_all_literatures)
+        return session.execute_read(QueryBuilder._get_all_literatures)
 
     @connection
     def delete_literature(self, session, filename):
-        session.write_transaction(QueryBuilder._delete_literature, filename)
+        session.execute_write(QueryBuilder._delete_literature, filename)
 
     def __del__(self):
         if self._driver is not None:
@@ -210,7 +212,5 @@ class DatabaseManager:
     def __init__(self, adapter: str):
         self.database_adapter = self.supported_db.get(
             adapter,
-            DatabaseNotSupportedError
+            DatabaseNotSupported
         )
-
-    def 

src/context_search/data_manager.py

@@ -2,9 +2,8 @@
 
 from .reader import ReadManager
 from .preprocessor import Preprocessor
-from .communicator import Communicator
-from .utils import setup_logger, config_variables
-
+from .communicator import CommAdapterNeo
+from .utils import setup_logger, EnvInterface
 
 logger = setup_logger('Data Manager Logger', 'logs.log')
 
@@ -15,23 +14,24 @@ class DataManager:
     _communicator = None
 
     def __init__(self):
+        EnvInterface().set_env_variables_from_config()
         self.read_manager = ReadManager()
         self.preprocessor = Preprocessor()
 
     @property
     def communicator(self):
         if self._communicator is None:
-            neo4j_variables = config_variables.get_neo4j_variables()
-            self._communicator = Communicator(
-                uri=neo4j_variables[0],
-                user=neo4j_variables[1],
-                password=neo4j_variables[2]
+            neo4j_variables = EnvInterface.get_neo4j_vars()
+            self._communicator = CommAdapterNeo(
+                uri=neo4j_variables["NEO4J_URI"],
+                user=neo4j_variables["NEO4J_USER"],
+                password=neo4j_variables["NEO4J_PASSWORD"]
             )
-            logger.info(f"""
+            logger.debug(f"""
             Communicator created with:
-            uri: {neo4j_variables[0]}
-            user: {neo4j_variables[1]}
-            password: {neo4j_variables[2]}
+            uri: {neo4j_variables["NEO4J_URI"]}
+            user: {neo4j_variables["NEO4J_USER"]}
+            password: {neo4j_variables["NEO4J_PASSWORD"]}
             """)
         return self._communicator
 

src/context_search/reader/reader.py

@@ -9,7 +9,7 @@
 from typing import List
 
 from ..data_classes import LiteratureDTO
-from ..utils import setup_logger, config_variables
+from ..utils import setup_logger, EnvInterface
 
 current_directory = os.path.dirname(__file__)
 
@@ -106,18 +106,13 @@ def _setup_paths_from_config(self):
         directory as the script that is being run with paths to tesseract
         and poppler bin folder (NOT TO EXECUTABLES, BUT FOLDERS).
         """
-        if not os.getenv("POPPLER_PATH") or not os.getenv("TESSERACT_PATH"):
-            self.tesseract_path, self.poppler_path = config_variables.get_OCR_variables()
+        self.tesseract_path = os.getenv("TESSERACT_PATH")
+        self.poppler_path = os.getenv("POPPLER_PATH")
 
-        if os.getenv("POPPLER_PATH"):
-            self.poppler_path = os.getenv("POPPLER_PATH")
-        else:
-            os.environ["POPPLER_PATH"] = self.poppler_path
-
-        if os.getenv("TESSERACT_PATH"):
-            self.tesseract_path = os.getenv("TESSERACT_PATH")
-        else:
-            os.environ["TESSERACT_PATH"] = self.tesseract_path
+        if not self.tesseract_path or not self.poppler_path:
+            ocr_vars = EnvInterface.get_OCR_vars()
+            self.tesseract_path = ocr_vars.get("TESSERACT_PATH")
+            self.poppler_path = ocr_vars.get("POPPLER_PATH")
 
         if os.name == "nt":
             pytesseract.pytesseract.tesseract_cmd = os.path.join(

src/context_search/utils/__init__.py

@@ -1,13 +1,9 @@
 from .config_variables import (
-    get_OCR_variables,
-    get_neo4j_variables,
-    set_env_variables_from_config
+    EnvInterface
 )
 from .logger_setup import setup_logger
 
 __all__ = [
-    "get_OCR_variables",
-    "get_neo4j_variables",
-    "set_env_variables_from_config",
+    "EnvInterface",
     "setup_logger"
 ]