update source information with relevance score explanation

assets/source_information.md

@@ -11,4 +11,16 @@ Here is a quick introduction to the sources of data accessed by the different ag
     - Guides made available to the general public 
     - Reports on experiences with new technologies 
     - Studies and research on local impacts institutional documents (analyses requested by France & activity reports) 
-    - Sectoral transition plans for the industrial sectors with the highest emissions (glass, paper, cement, steel, aluminium, chemicals, sugar)
+    - Sectoral transition plans for the industrial sectors with the highest emissions (glass, paper, cement, steel, aluminium, chemicals, sugar)
+
+<br>
+
+Here you can find some information on what the relevance score is. The relevance score is a measure used to evaluate the relevance of documents retrieved in relation to a given query in a vectorstore. When a document is stored as a vector, the relevance score indicates how close this document is to the query in terms of vector similarity.
+
+Here is how it generally works:
+
+    - Vector Representation: Documents and the query are converted into vectors in a vector space.
+    - Similarity Calculation: A similarity measure (such as the dot product or cosine distance) is used to compare the vectors of the documents with that of the query.
+    - Relevance Score: The result of this comparison is the relevance score, which indicates how relevant each document is to the query.
+
+A higher score means that the document is more relevant to the query. This allows the retrieved documents to be ranked based on their relevance.