try to change embedding model

app.py

@@ -1,6 +1,9 @@
+from time import time
 import gradio as gr
 from langchain.chains import RetrievalQA
-from langchain.embeddings import OpenAIEmbeddings
+# from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.embeddings import GPT4AllEmbeddings
 from langchain.llms import OpenAI
 from langchain.chat_models import ChatOpenAI
 from langchain.vectorstores import Qdrant
@@ -16,7 +19,16 @@ PERSIST_DIR_NAME = "nvdajp-book"
 
 
 def get_retrieval_qa(model_name: str | None, temperature: int, option: str | None) -> RetrievalQA:
-    embeddings = OpenAIEmbeddings()
+    # embeddings = OpenAIEmbeddings()
+    model_name = "sentence-transformers/all-mpnet-base-v2"
+    model_kwargs = {'device': 'cpu'}
+    encode_kwargs = {'normalize_embeddings': False}
+    embeddings = HuggingFaceEmbeddings(
+        model_name=model_name,
+        model_kwargs=model_kwargs,
+        encode_kwargs=encode_kwargs,
+    )
+    # embeddings = GPT4AllEmbeddings()
     db_url, db_api_key, db_collection_name = DB_CONFIG
     client = QdrantClient(url=db_url, api_key=db_api_key)
     db = Qdrant(client=client, collection_name=db_collection_name, embeddings=embeddings)
@@ -36,7 +48,7 @@ def get_retrieval_qa(model_name: str | None, temperature: int, option: str | Non
                 "filter": {"category": option},
             }
         )
-    return RetrievalQA.from_chain_type(
+    result = RetrievalQA.from_chain_type(
         llm=ChatOpenAI(
             model=model,
             temperature=temperature
@@ -45,6 +57,7 @@ def get_retrieval_qa(model_name: str | None, temperature: int, option: str | Non
         retriever=retriever,
         return_source_documents=True,
     )
+    return result
 
 
 def get_related_url(metadata):

config.py

@@ -1,7 +1,7 @@
 import os
 
 
-SAAS = True
+SAAS = False
 
 
 def get_db_config():

store.py

@@ -1,6 +1,8 @@
 from langchain.document_loaders import ReadTheDocsLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings
+# from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.embeddings import GPT4AllEmbeddings
 from langchain.vectorstores import Qdrant
 # from qdrant_client import QdrantClient
 from nvda_ug_loader import NVDAUserGuideLoader
@@ -35,7 +37,16 @@ def get_text_chunk(docs):
 
 
 def store(texts):
-    embeddings = OpenAIEmbeddings()
+    # embeddings = OpenAIEmbeddings()
+    model_name = "sentence-transformers/all-mpnet-base-v2"
+    model_kwargs = {'device': 'cuda'}
+    encode_kwargs = {'normalize_embeddings': False}
+    embeddings = HuggingFaceEmbeddings(
+        model_name=model_name,
+        model_kwargs=model_kwargs,
+        encode_kwargs=encode_kwargs,
+    )
+    # embeddings = GPT4AllEmbeddings()
     db_url, db_api_key, db_collection_name = DB_CONFIG
     # client = QdrantClient(url=db_url, api_key=db_api_key, prefer_grpc=True)
     _ = Qdrant.from_documents(