Remove deleted endpoints, explain evaluation

Removed the description of the summarisation endpoint which now lives in its own repository. Also added a little disclaimer to the evaluation section.

README.md

@@ -17,25 +17,6 @@ You can now view the Swagger documentation of the API in your browser under `loc
 
 ## Endpoints
 
-### Summarisation
-The endpoint `completion` returns a shortened version of the input text you provide as source.
-
-You can access it with the following curl statement or via the Swagger docs.
-
-```shell
-curl -X 'POST' \
-  'http://localhost:3000/completion?model=gpt-3.5-turbo&honest=true' \
-  -H 'accept: application/json' \
-  -H 'Content-Type: application/json' \
-  -d '{
-  "source": "string"
-}'
-```
-
-Since this API is also designed for demonstration purposes it is possible to enforce hallucinations by setting the 
-honest parameter to `false`. As models you can choose either `gpt-3.5-turbo` or `gpt-4-turbo`. 
-
-
 ## Fact check
 
 The endpoint `check` performs a check if a `sentence` is contained in the `source`. 
@@ -65,7 +46,10 @@ This repository contains two scripts designed to evaluate and enhance the accura
 The script `evaluation.py` aims to validate the effectiveness of the system by comparing its predictions with the
 gold standard dataset, ultimately providing a measure of accuracy.
 
-The script `predictor.py` focuses on processing the test data set using the provided API to create set to validate against. 
+The script `predictor.py` focuses on processing the test data set using the provided API to create set to validate against.
+
+:warning: This test set is designed to detect wrong answers to questions if the source is given. We think the two tasks
+are similar enough to use this on our domain as well.
 
 ### Available Test- and Training Data
 
@@ -95,4 +79,4 @@ JSON object with the structure as follows:
 To run the evaluation simply run `python evaluate.py` after you've placed your results in the data folder.
 The evaluation script calculates the accuracy - e.g. the percentage of correctly predicted samples.
 
-The current 
+The current