Update app.py

app.py

@@ -13,7 +13,7 @@ from langchain.document_loaders.parsers import OpenAIWhisperParser
 from langchain.schema import AIMessage, HumanMessage
 from langchain.llms import HuggingFaceHub
 from langchain.llms import HuggingFaceTextGenInference
-from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain.embeddings import HuggingFaceInstructEmbeddings, HuggingFaceEmbeddings, HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.prompts import PromptTemplate
@@ -182,8 +182,11 @@ def document_storage_mongodb(splits):
 #dokumente in chroma db vektorisiert ablegen können - die Db vorbereiten daüfur
 def document_retrieval_chroma(llm, prompt):      
     #embeddings = OpenAIEmbeddings()
-    #Alternative Embedding - für Vektorstore, um Ähnlichkeitsvektoren zu erzeugen
+    #Alternative Embedding - für Vektorstore, um Ähnlichkeitsvektoren zu erzeugen - die ...InstructEmbedding ist sehr rechenaufwendig
     embeddings = HuggingFaceInstructEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={"device": "cpu"})
+    #etwas weniger rechenaufwendig:
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2", model_kwargs={"device": "cpu"}, encode_kwargs={'normalize_embeddings': False})
+    
     db = Chroma(embedding_function = embeddings,
                 persist_directory = PATH_WORK + CHROMA_DIR)