Update app.py

app.py

@@ -68,29 +68,7 @@ index = pinecone.Index(index_name)
 
 FILE_UPLOAD_PATH= "./data/uploads/"
 os.makedirs(FILE_UPLOAD_PATH, exist_ok=True)
-# @st.cache
-def create_doc_store():
-    document_store = PineconeDocumentStore(
-        api_key= st.secrets["pinecone_apikey"],
-        index=index_name,
-        similarity="cosine",
-        embedding_dim=768,
-        metadata_config={
-            'indexed': ['filename']
-        }
-    )
-    return document_store
-
-# @st.cache
-# def create_pipe(document_store):
-    # retriever = EmbeddingRetriever(
-    # document_store=document_store,
-    # embedding_model="sentence-transformers/multi-qa-mpnet-base-dot-v1",
-    # model_format="sentence_transformers",
-    # )
-    # reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
-    # pipe = ExtractiveQAPipeline(reader, retriever)
-    # return pipe
+
 limit = 3750
 
 def retrieve(query):
@@ -154,20 +132,6 @@ def query(pipe, question, top_k_reader, top_k_retriever):
     query_with_contexts, contexts = retrieve(question)
     return complete(query_with_contexts), contexts
 
-document_store = create_doc_store()
-# pipe = create_pipe(document_store)
-retriever_model = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
-retriever = EmbeddingRetriever(
-document_store=document_store,
-embedding_model=retriever_model,
-model_format="sentence_transformers",
-)
-# load the retriever model from huggingface model hub
-# sentence_encoder = SentenceTransformer(retriever_model)
-
-# reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
-# pipe = ExtractiveQAPipeline(reader, retriever)
-# now query text-davinci-003 WITHOUT context
 
 indexing_pipeline_with_classification = Pipeline()
 indexing_pipeline_with_classification.add_node(