Update app.py

app.py

@@ -52,7 +52,26 @@ model = model.eval()
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 print(f"Model device: {model.device}")
 
+# a custom embedding
+from sentence_transformers import SentenceTransformer
+from langchain_experimental.text_splitter import SemanticChunker
+from typing import List
+
+
+class MyEmbeddings:
+    def __init__(self):
+        self.model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+        #self.model=model
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        return [self.model.encode(t).tolist() for t in texts]
+    def embed_query(self, query: str) -> List[float]:
+            return [self.model.encode([query])][0][0].tolist()
+
+
+embeddings = MyEmbeddings()
 
+splitter = SemanticChunker(embeddings)