RAG

app.py

@@ -16,8 +16,12 @@ def load_and_retrieve_docs(url):
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
     splits = text_splitter.split_documents(docs)
     embedding_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
-    embeddings = [embedding_model.encode(doc.page_content) for doc in splits]
-    vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
+    
+    # Create a custom embedding function that uses the embedding model's encode method
+    def embed_func(texts):
+        return embedding_model.encode(texts, convert_to_tensor=True)
+    
+    vectorstore = Chroma.from_documents(documents=splits, embedding=embed_func)
     return vectorstore.as_retriever()
 
 # Function to format documents