diff --git a/components/minhash_generator/Dockerfile b/components/minhash_generator/Dockerfile
new file mode 100644
index 000000000..abfa9a414
--- /dev/null
+++ b/components/minhash_generator/Dockerfile
@@ -0,0 +1,23 @@
+FROM --platform=linux/amd64 python:3.8-slim
+
+# System dependencies
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install git -y
+
+# Install requirements
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+# Install Fondant
+# This is split from other requirements to leverage caching
+ARG FONDANT_VERSION=main
+RUN pip3 install fondant[aws,azure,gcp]@git+https://github.com/ml6team/fondant@${FONDANT_VERSION}
+
+# Set the working directory to the component folder
+WORKDIR /component/src
+
+# Copy over src-files
+COPY src/ .
+
+ENTRYPOINT ["python", "main.py"]
\ No newline at end of file
diff --git a/components/minhash_generator/fondant_component.yaml b/components/minhash_generator/fondant_component.yaml
new file mode 100644
index 000000000..f1a83ae38
--- /dev/null
+++ b/components/minhash_generator/fondant_component.yaml
@@ -0,0 +1,22 @@
+name: MinHash generator
+description: A component that generates minhashes of text.
+image: ghcr.io/ml6team/minhash_generator:latest
+
+consumes:
+  text:
+    fields:
+      data:
+        type: string
+
+produces:
+  text:
+    fields:
+      minhash:
+        type: array
+        items:
+            type: uint64
+args:
+  shingle_ngram_size:
+    description: Define size of ngram used for the shingle generation
+    type: int
+    default: 3
\ No newline at end of file
diff --git a/components/minhash_generator/requirements.txt b/components/minhash_generator/requirements.txt
new file mode 100644
index 000000000..396953e56
--- /dev/null
+++ b/components/minhash_generator/requirements.txt
@@ -0,0 +1,2 @@
+datasketch==1.5.9
+nltk==3.8.1
\ No newline at end of file
diff --git a/components/minhash_generator/src/main.py b/components/minhash_generator/src/main.py
new file mode 100644
index 000000000..2135ec3a2
--- /dev/null
+++ b/components/minhash_generator/src/main.py
@@ -0,0 +1,64 @@
+"""A component that generates minhashes of text."""
+import logging
+
+import numpy as np
+import pandas as pd
+from datasketch import MinHash
+from fondant.component import PandasTransformComponent
+from nltk.util import ngrams
+
+logger = logging.getLogger(__name__)
+
+
+def create_shingles(text: str) -> list:
+    """Creates text shingles that will be used for the hash generation."""
+    # Split text into words
+    words = text.split()
+
+    # Generate shingles of size 3 using nltk's ngrams function
+    return list(ngrams(words, 3))
+
+def compute_minhash(shingles: list) -> np.ndarray:
+        """Calculate minhash based on the shingles."""
+        minhash = MinHash()
+
+        # Update the MinHash object with the shingles
+        for shingle in shingles:
+            minhash.update(" ".join(shingle).encode("utf-8"))
+
+        return minhash.hashvalues
+
+class MinHashGeneratorComponent(PandasTransformComponent):
+    """Component generates minhashes of text."""
+
+    def setup(self, *, shingle_ngram_size: int):
+        """Setup component.
+
+        Args:
+            shingle_ngram_size: Defines size of ngram used for the shingle generation.
+        """
+        self.shingle_ngram_size = shingle_ngram_size
+
+    def transform(self, dataframe: pd.DataFrame) -> pd.DataFrame:
+        """
+        Generates minhash values of text.
+
+        Args:
+            dataframe: Pandas dataframe.
+
+        Returns:
+            Pandas dataframe
+        """
+        dataframe[("text", "shingles")] = dataframe[("text", "data")].apply(
+            create_shingles,
+        )
+        dataframe[("text", "minhash")] = dataframe[("text", "shingles")].apply(
+            compute_minhash,
+        )
+
+        return dataframe
+
+
+if __name__ == "__main__":
+    component = MinHashGeneratorComponent.from_args()
+    component.run()
diff --git a/components/minhash_generator/tests/component_test.py b/components/minhash_generator/tests/component_test.py
new file mode 100644
index 000000000..b446a704c
--- /dev/null
+++ b/components/minhash_generator/tests/component_test.py
@@ -0,0 +1,38 @@
+"""Unit test for minhash generation component."""
+import pandas as pd
+from fondant.component_spec import ComponentSpec
+
+from components.minhash_generator.src.main import MinHashGeneratorComponent
+
+
+def test_run_component_test():
+    """Test MinHash generation."""
+    # Given: Dataframe with text, one duplicate in
+    data = [
+        {"data": "This is my first sentence"},
+        {"data": "This is my first sentence"},
+        {"data": "This is a different sentence"},
+    ]
+
+    dataframe = pd.concat({"text": pd.DataFrame(data)}, axis=1, names=["text", "data"])
+
+    # When: The text filter component proceed the dataframe
+    spec = ComponentSpec.from_file("../fondant_component.yaml")
+
+    component = MinHashGeneratorComponent(
+        spec,
+        input_manifest_path="./dummy_input_manifest.json",
+        output_manifest_path="./dummy_input_manifest.json",
+        metadata={},
+        user_arguments={},
+    )
+
+    dataframe = component.transform(dataframe=dataframe)
+
+    # Then: dataframe contain minhashes for each entry
+    assert any(
+        dataframe.loc[0]["text"]["minhash"] == dataframe.loc[1]["text"]["minhash"],
+    )
+    assert not any(
+        dataframe.loc[0]["text"]["minhash"] == dataframe.loc[2]["text"]["minhash"],
+    )