diff --git a/.env.example b/.env.example
new file mode 100644
index 00000000..a0f0c9bc
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,2 @@
+WEAVIATE_HOST=
+WEAVIATE_PORT=
diff --git a/app/domain/data/lecture_unit_dto.py b/app/domain/data/lecture_unit_dto.py
index 3e7b4d74..8b123c1c 100644
--- a/app/domain/data/lecture_unit_dto.py
+++ b/app/domain/data/lecture_unit_dto.py
@@ -1,12 +1,13 @@
-from datetime import datetime
-from typing import Optional
-
 from pydantic import BaseModel, Field
 
 
 class LectureUnitDTO(BaseModel):
-    id: int
+    to_update: bool = Field(alias="toUpdate")
+    pdf_file_base64: str = Field(alias="pdfFile")
+    lecture_unit_id: int = Field(alias="lectureUnitId")
+    lecture_unit_name: str = Field(alias="lectureUnitName")
     lecture_id: int = Field(alias="lectureId")
-    release_date: Optional[datetime] = Field(alias="releaseDate", default=None)
-    name: Optional[str] = None
-    attachment_version: int = Field(alias="attachmentVersion")
+    lecture_name: str = Field(alias="lectureName")
+    course_id: int = Field(alias="courseId")
+    course_name: str = Field(alias="courseName")
+    course_description: str = Field(alias="courseDescription")
diff --git a/app/ingestion/__init__.py b/app/ingestion/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/app/ingestion/abstract_ingestion.py b/app/ingestion/abstract_ingestion.py
new file mode 100644
index 00000000..d78244f0
--- /dev/null
+++ b/app/ingestion/abstract_ingestion.py
@@ -0,0 +1,29 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict
+
+
+class AbstractIngestion(ABC):
+    """
+    Abstract class for ingesting repositories into a database.
+    """
+
+    @abstractmethod
+    def chunk_data(self, path: str) -> List[Dict[str, str]]:
+        """
+        Abstract method to chunk code files in the root directory.
+        """
+        pass
+
+    @abstractmethod
+    def ingest(self, path: str) -> bool:
+        """
+        Abstract method to ingest repositories into the database.
+        """
+        pass
+
+    @abstractmethod
+    def update(self, path: str):
+        """
+        Abstract method to update a repository in the database.
+        """
+        pass
diff --git a/app/pipeline/chat/tutor_chat_pipeline.py b/app/pipeline/chat/tutor_chat_pipeline.py
index 5f36b1b8..1117fb38 100644
--- a/app/pipeline/chat/tutor_chat_pipeline.py
+++ b/app/pipeline/chat/tutor_chat_pipeline.py
@@ -182,7 +182,7 @@ def _add_student_repository_to_prompt(
         for file in selected_files:
             if file in student_repository:
                 self.prompt += SystemMessagePromptTemplate.from_template(
-                    f"For reference, we have access to the student's '{file}' file:"
+                    f"For reference, we have access to the student's '{file}' file: "
                 )
                 self.prompt += HumanMessagePromptTemplate.from_template(
                     student_repository[file].replace("{", "{{").replace("}", "}}")
diff --git a/app/retrieval/__init__.py b/app/retrieval/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/app/retrieval/abstract_retrieval.py b/app/retrieval/abstract_retrieval.py
new file mode 100644
index 00000000..8682d963
--- /dev/null
+++ b/app/retrieval/abstract_retrieval.py
@@ -0,0 +1,15 @@
+from abc import ABC, abstractmethod
+from typing import List
+
+
+class AbstractRetrieval(ABC):
+    """
+    Abstract class for retrieving data from a database.
+    """
+
+    @abstractmethod
+    def retrieve(self, path: str, hybrid_factor: float, result_limit: int) -> List[str]:
+        """
+        Abstract method to retrieve data from the database.
+        """
+        pass
diff --git a/app/retrieval/lecture_retrieval.py b/app/retrieval/lecture_retrieval.py
new file mode 100644
index 00000000..11797930
--- /dev/null
+++ b/app/retrieval/lecture_retrieval.py
@@ -0,0 +1,43 @@
+from abc import ABC
+from typing import List
+
+from weaviate import WeaviateClient
+from weaviate.classes.query import Filter
+
+from app.retrieval.abstract_retrieval import AbstractRetrieval
+from app.vector_database.lecture_schema import init_lecture_schema, LectureSchema
+
+
+class LectureRetrieval(AbstractRetrieval, ABC):
+    """
+    Class for retrieving lecture data from the database.
+    """
+
+    def __init__(self, client: WeaviateClient):
+        self.collection = init_lecture_schema(client)
+
+    def retrieve(
+        self,
+        user_message: str,
+        hybrid_factor: float,
+        result_limit: int,
+        lecture_id: int = None,
+        message_vector: [float] = None,
+    ) -> List[str]:
+        response = self.collection.query.hybrid(
+            query=user_message,
+            filters=(
+                Filter.by_property(LectureSchema.LECTURE_ID.value).equal(lecture_id)
+                if lecture_id
+                else None
+            ),
+            alpha=hybrid_factor,
+            vector=message_vector,
+            return_properties=[
+                LectureSchema.PAGE_TEXT_CONTENT.value,
+                LectureSchema.PAGE_IMAGE_DESCRIPTION.value,
+                LectureSchema.COURSE_NAME.value,
+            ],
+            limit=result_limit,
+        )
+        return response
diff --git a/app/retrieval/repositories_retrieval.py b/app/retrieval/repositories_retrieval.py
new file mode 100644
index 00000000..37920fac
--- /dev/null
+++ b/app/retrieval/repositories_retrieval.py
@@ -0,0 +1,45 @@
+from typing import List
+
+from weaviate import WeaviateClient
+from weaviate.classes.query import Filter
+
+from app.retrieval.abstract_retrieval import AbstractRetrieval
+from app.vector_database.repository_schema import (
+    init_repository_schema,
+    RepositorySchema,
+)
+
+
+class RepositoryRetrieval(AbstractRetrieval):
+    """
+    Class for Retrieving repository code for from the vector database.
+    """
+
+    def __init__(self, client: WeaviateClient):
+        self.collection = init_repository_schema(client)
+
+    def retrieve(
+        self,
+        user_message: str,
+        result_limit: int,
+        repository_id: int = None,
+    ) -> List[str]:
+        response = self.collection.query.near_text(
+            near_text=user_message,
+            filters=(
+                Filter.by_property(RepositorySchema.REPOSITORY_ID.value).equal(
+                    repository_id
+                )
+                if repository_id
+                else None
+            ),
+            return_properties=[
+                RepositorySchema.REPOSITORY_ID.value,
+                RepositorySchema.COURSE_ID.value,
+                RepositorySchema.CONTENT.value,
+                RepositorySchema.EXERCISE_ID.value,
+                RepositorySchema.FILEPATH.value,
+            ],
+            limit=result_limit,
+        )
+        return response
diff --git a/app/vector_database/__init__.py b/app/vector_database/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/app/vector_database/database.py b/app/vector_database/database.py
new file mode 100644
index 00000000..f670c372
--- /dev/null
+++ b/app/vector_database/database.py
@@ -0,0 +1,44 @@
+import logging
+import os
+import weaviate
+from .lecture_schema import init_lecture_schema
+from .repository_schema import init_repository_schema
+import weaviate.classes as wvc
+
+logger = logging.getLogger(__name__)
+
+
+class VectorDatabase:
+    """
+    Class to interact with the Weaviate vector database
+    """
+
+    def __init__(self):
+        self.client = weaviate.connect_to_wcs(
+            cluster_url=os.getenv("WEAVIATE_CLUSTER_URL"),
+            auth_credentials=weaviate.auth.AuthApiKey(os.getenv("WEAVIATE_AUTH_KEY")),
+        )
+        self.repositories = init_repository_schema(self.client)
+        self.lectures = init_lecture_schema(self.client)
+
+    def __del__(self):
+        self.client.close()
+
+    def delete_collection(self, collection_name):
+        """
+        Delete a collection from the database
+        """
+        if self.client.collections.exists(collection_name):
+            if self.client.collections.delete(collection_name):
+                logger.info(f"Collection {collection_name} deleted")
+            else:
+                logger.error(f"Collection {collection_name} failed to delete")
+
+    def delete_object(self, collection_name, property_name, object_property):
+        """
+        Delete an object from the collection inside the databse
+        """
+        collection = self.client.collections.get(collection_name)
+        collection.data.delete_many(
+            where=wvc.query.Filter.by_property(property_name).equal(object_property)
+        )
diff --git a/app/vector_database/lecture_schema.py b/app/vector_database/lecture_schema.py
new file mode 100644
index 00000000..22616f1c
--- /dev/null
+++ b/app/vector_database/lecture_schema.py
@@ -0,0 +1,97 @@
+from enum import Enum
+
+from weaviate.classes.config import Property
+from weaviate import WeaviateClient
+from weaviate.collections import Collection
+from weaviate.collections.classes.config import Configure, VectorDistances, DataType
+
+
+class LectureSchema(Enum):
+    """
+    Schema for the lecture slides
+    """
+
+    COLLECTION_NAME = "LectureSlides"
+    COURSE_NAME = "course_name"
+    COURSE_DESCRIPTION = "course_description"
+    COURSE_ID = "course_id"
+    LECTURE_ID = "lecture_id"
+    LECTURE_NAME = "lecture_name"
+    LECTURE_UNIT_ID = "lecture_unit_id"
+    LECTURE_UNIT_NAME = "lecture_unit_name"
+    PAGE_TEXT_CONTENT = "page_text_content"
+    PAGE_IMAGE_DESCRIPTION = "page_image_explanation"
+    PAGE_BASE64 = "page_base64"
+    PAGE_NUMBER = "page_number"
+
+
+def init_lecture_schema(client: WeaviateClient) -> Collection:
+    """
+    Initialize the schema for the lecture slides
+    """
+    if client.collections.exists(LectureSchema.COLLECTION_NAME.value):
+        return client.collections.get(LectureSchema.COLLECTION_NAME.value)
+    return client.collections.create(
+        name=LectureSchema.COLLECTION_NAME.value,
+        vectorizer_config=Configure.Vectorizer.none(),
+        vector_index_config=Configure.VectorIndex.hnsw(
+            distance_metric=VectorDistances.COSINE
+        ),
+        properties=[
+            Property(
+                name=LectureSchema.COURSE_ID.value,
+                description="The ID of the course",
+                data_type=DataType.INT,
+            ),
+            Property(
+                name=LectureSchema.COURSE_NAME.value,
+                description="The name of the course",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.COURSE_DESCRIPTION.value,
+                description="The description of the COURSE",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.LECTURE_ID.value,
+                description="The ID of the lecture",
+                data_type=DataType.INT,
+            ),
+            Property(
+                name=LectureSchema.LECTURE_NAME.value,
+                description="The name of the lecture",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.LECTURE_UNIT_ID.value,
+                description="The ID of the lecture unit",
+                data_type=DataType.INT,
+            ),
+            Property(
+                name=LectureSchema.LECTURE_UNIT_NAME.value,
+                description="The name of the lecture unit",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.PAGE_TEXT_CONTENT.value,
+                description="The original text content from the slide",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.PAGE_IMAGE_DESCRIPTION.value,
+                description="The description of the slide if the slide contains an image",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.PAGE_BASE64.value,
+                description="The base64 encoded image of the slide if the slide contains an image",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=LectureSchema.PAGE_NUMBER.value,
+                description="The page number of the slide",
+                data_type=DataType.INT,
+            ),
+        ],
+    )
diff --git a/app/vector_database/repository_schema.py b/app/vector_database/repository_schema.py
new file mode 100644
index 00000000..cb288713
--- /dev/null
+++ b/app/vector_database/repository_schema.py
@@ -0,0 +1,60 @@
+from enum import Enum
+from weaviate.classes.config import Property
+from weaviate import WeaviateClient
+from weaviate.collections import Collection
+from weaviate.collections.classes.config import Configure, VectorDistances, DataType
+
+
+class RepositorySchema(Enum):
+    """
+    Schema for the student repository
+    """
+
+    COLLECTION_NAME = "StudentRepository"
+    CONTENT = "content"
+    COURSE_ID = "course_id"
+    EXERCISE_ID = "exercise_id"
+    REPOSITORY_ID = "repository_id"
+    FILEPATH = "filepath"
+
+
+def init_repository_schema(client: WeaviateClient) -> Collection:
+    """
+    Initialize the schema for the student repository
+    """
+    if client.collections.exists(RepositorySchema.COLLECTION_NAME.value):
+        return client.collections.get(RepositorySchema.COLLECTION_NAME.value)
+    return client.collections.create(
+        name=RepositorySchema.COLLECTION_NAME.value,
+        vectorizer_config=Configure.Vectorizer.none(),
+        vector_index_config=Configure.VectorIndex.hnsw(
+            distance_metric=VectorDistances.COSINE
+        ),
+        properties=[
+            Property(
+                name=RepositorySchema.CONTENT.value,
+                description="The content of this chunk of code",
+                data_type=DataType.TEXT,
+            ),
+            Property(
+                name=RepositorySchema.COURSE_ID.value,
+                description="The ID of the course",
+                data_type=DataType.INT,
+            ),
+            Property(
+                name=RepositorySchema.EXERCISE_ID.value,
+                description="The ID of the exercise",
+                data_type=DataType.INT,
+            ),
+            Property(
+                name=RepositorySchema.REPOSITORY_ID.value,
+                description="The ID of the repository",
+                data_type=DataType.INT,
+            ),
+            Property(
+                name=RepositorySchema.FILEPATH.value,
+                description="The filepath of the code",
+                data_type=DataType.TEXT,
+            ),
+        ],
+    )
diff --git a/requirements.txt b/requirements.txt
index d86942af..78c7b582 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,6 +6,8 @@ ollama==0.1.9
 openai==1.25.2
 pre-commit==3.7.0
 pydantic==2.7.1
+PyMuPDF==1.23.22
 PyYAML==6.0.1
+requests~=2.31.0
 uvicorn==0.29.0
-requests~=2.31.0
\ No newline at end of file
+weaviate-client==4.5.4