Update app.py

app.py

@@ -26,10 +26,24 @@ class VectorStore:
         self.chroma_client = chromadb.Client()
         self.collection = self.chroma_client.create_collection(name=collection_name)
 
-    def populate_vectors(self, texts, ids):
-        embeddings = self.embedding_model.encode(texts, batch_size=32).tolist()
-        for text, embedding, doc_id in zip(texts, embeddings, ids):
-            self.collection.add(embeddings=[embedding], documents=[text], ids=[doc_id])
+    # def populate_vectors(self, texts, ids):
+    #     embeddings = self.embedding_model.encode(texts, batch_size=32).tolist()
+    #     for text, embedding, doc_id in zip(texts, embeddings, ids):
+    #         self.collection.add(embeddings=[embedding], documents=[text], ids=[doc_id])
+
+        # Method to populate the vector store with embeddings from a dataset
+    def populate_vectors(self, dataset):
+        # Select the text columns to concatenate
+        # title = dataset['train']['title_cleaned'][:1000]  # Limiting to 100 examples for the demo
+        recipe = dataset['train']['recipe_new'][:1000]
+        allergy = dataset['train']['allergy_type'][:1000]
+        ingredients = dataset['train']['ingredients_alternatives'][:1000]
+
+        # Concatenate the text from both columns
+        texts = [f"{rep} {ingr} {alle}" for rep, ingr,alle in zip(recipe, ingredients,allergy)]
+        for i, item in enumerate(texts):
+            embeddings = self.embedding_model.encode(item).tolist()
+            self.collection.add(embeddings=[embeddings], documents=[item], ids=[str(i)])
 
     def search_context(self, query, n_results=1):
         query_embedding = self.embedding_model.encode([query]).tolist()