diff --git a/README.md b/README.md
index bcc4793..9584d3f 100644
--- a/README.md
+++ b/README.md
@@ -3,6 +3,57 @@
 This repository implements computer vision based approaches for detecting and parsing visual features such as tables or
 previous redactions in documents.
 
+## API
+
+Input message:
+
+```json
+{
+  "targetFilePath": {
+    "pdf": "absolute file path",
+    "vlp_output": "absolute file path"
+  },
+  "responseFilePath": "absolute file path",
+  "operation": "table_image_inference"
+}
+```
+
+Response is uploaded to the storage as specified in the `responseFilePath` field. The structure is as follows:
+
+```json
+{
+  ...,
+  "data": [
+    {
+      'pageNum': 0,
+      'bbox': {
+        'x1': 55.3407,
+        'y1': 247.0246,
+        'x2': 558.5602,
+        'y2': 598.0585
+      },
+      'uuid': '2b10c1a2-393c-4fca-b9e3-0ad5b774ac84',
+      'label': 'table',
+      'tableLines': [
+        {
+          'x1': 0,
+          'y1': 16,
+          'x2': 1399,
+          'y2': 16
+        },
+        ...
+      ],
+      'imageInfo': {
+        'height': 693,
+        'width': 1414
+      }
+    },
+    ...
+  ]
+}
+
+```
+
 ## Installation
 
 ```bash
@@ -31,10 +82,9 @@ The below snippet shows hot to find the outlines of previous redactions.
 
 ```python
 from cv_analysis.redaction_detection import find_redactions
-import pdf2image 
+import pdf2image
 import numpy as np
 
-
 pdf_path = ...
 page_index = ...
 
diff --git a/test/unit_tests/table_inference_test.py b/test/unit_tests/table_inference_test.py
index 5ee337e..6c2c4be 100644
--- a/test/unit_tests/table_inference_test.py
+++ b/test/unit_tests/table_inference_test.py
@@ -1,12 +1,23 @@
 from cv_analysis.server.pipeline import make_image_analysis_pipeline
 from cv_analysis.table_inference import infer_lines
 
-def test_table_inference():
+
+def test_table_inference_smoke():
     pl = make_image_analysis_pipeline(infer_lines)
     with open("test/test_data/article.pdf", "rb") as f:
         pdf_bytes = f.read()
-    vlp_mock = {"data": [{"page_idx": 1, "image_boxes": [{"label": "table", "x1": 0.1, "y1": 0.3, "x2": 0.4, "y2": 0.6}]}]}
-    output = list(pl(pdf_bytes, vlp_mock))
+    vlp_mock = {
+        "data": [
+            {
+                "page_idx": 1,
+                "boxes": [
+                    {"uuid": "marius-marius-gib-mir-meine-legionen-wieder", "label": "table", "box": {"x1": 100, "y1": 100, "x2": 200, "y2": 200}}
+                ],
+            }
+        ]
+    }
+    data = {"pdf": pdf_bytes, "vlp_output": vlp_mock}
+    output = list(pl(data))
     lines = output[0]["tableLines"]
     assert len(lines) > 1
-    assert all(map(lambda item: sorted(item.keys())==['x1', 'x2', 'y1', 'y2'], lines))
\ No newline at end of file
+    assert all(map(lambda item: sorted(item.keys()) == ["x1", "x2", "y1", "y2"], lines))