Update app.py

app.py

@@ -7,38 +7,30 @@ from langchain.vectorstores import Chroma
 #from langchain.embeddings import OpenAIEmbeddings
 #from langchain.llms import OpenAI
 from langchain.chains import VectorDBQA
-
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
 
 
 
 
 tokenizer_nlp = AutoTokenizer.from_pretrained("FlavioBF/multi-qa-mpnet-base-dot-v1_fine_tuned_model")
 model_nlp = AutoModelForQuestionAnswering.from_pretrained("FlavioBF/multi-qa-mpnet-base-dot-v1_fine_tuned_model")
-
-
-
 #url='https://huggingface.co/FlavioBF/multi-qa-mpnet-base-dot-v1_fine_tuned_model/commit/1a9570af077d83fc8a728b0addf8a8bd276e2492'
 # Load model directly
 #model_name2 = "FlavioBF/multi-qa-mpnet-base-dot-v1_fine_tuned_model"
 #nlp = pipeline("question-answering", model=model_nlp, tokenizer=tokenizer2)
 #nlp = pipeline("fill-mask", model="FlavioBF/multi-qa-mpnet-base-dot-v1_fine_tuned_model")
 
-#persist_directory = 'https://drive.google.com/drive/folders/1jRoIBEzgT3-5Pk9eu9oWkbaUq7GxBAiV?usp=sharing'
-persist_directory = 'https://drive.google.com/file/d/1U-isHky75OdYwt0UFjYsDAh4idVyixxM/view?usp=sharing'
+persist_directory = 'https://drive.google.com/drive/folders/1jRoIBEzgT3-5Pk9eu9oWkbaUq7GxBAiV?usp=sharing'
+#persist_directory = 'https://drive.google.com/file/d/1U-isHky75OdYwt0UFjYsDAh4idVyixxM/view?usp=sharing'
 
 embedding = HuggingFaceEmbeddings()
 vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)
-
 # Now we can load the persisted database from disk, and use it as normal. 
 #vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)
-qa = VectorDBQA.from_chain_type(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_base=base_path), chain_type="stuff", vectorstore=vectordb)
+#qa = VectorDBQA.from_chain_type(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_base=base_path), chain_type="stuff", vectorstore=vectordb)
 
 context=qa.run(query)
-
-context = ""
-question = ""
-
-
 #vectordb = Chroma.from_documents(documents=all_splits, embedding=embeddings, persist_directory="chroma_db")
 
 retriever = vectordb.as_retriever()