Delete app.py

app.py

@@ -1,65 +0,0 @@
-
-pip install -r requirements.txt -q
-import box
-import yaml
-from langchain.vectorstores import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.document_loaders import PyPDFLoader, DirectoryLoader
-from langchain.embeddings import HuggingFaceEmbeddings
-
-
-# Import config vars
-with open('config.yml', 'r', encoding='utf8') as ymlfile:
-    cfg = box.Box(yaml.safe_load(ymlfile))
-
-
-# def run_ingest():
-loader = DirectoryLoader(cfg.DATA_PATH,
-                 glob='*.pdf',
-                 loader_cls=PyPDFLoader)
-
-documents = loader.load()
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=cfg.CHUNK_SIZE,
-                                       chunk_overlap=cfg.CHUNK_OVERLAP)
-texts = text_splitter.split_documents(documents)
-
-embeddings = HuggingFaceEmbeddings(model_name=cfg.EMBEDDINGS,
-                           model_kwargs={'device': 'cpu'})
-
-vectorstore = FAISS.from_documents(texts, embeddings)
-vectorstore.save_local(cfg.DB_FAISS_PATH)
-
-# if __name__ == "__main__":
-#     run_ingest()
-
-import timeit
-import argparse
-from llm.wrapper import setup_qa_chain
-from llm.wrapper import query_embeddings
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('input',
-                        type=str,
-                        default='What is the invoice number value?',
-                        help='Enter the query to pass into the LLM')
-    parser.add_argument('--semantic_search',
-                        type=bool,
-                        default=False,
-                        help='Enter True if you want to run semantic search, else False')
-    args = parser.parse_args()
-
-    start = timeit.default_timer()
-    if args.semantic_search:
-        semantic_search = query_embeddings(args.input)
-        print(f'Semantic search: {semantic_search}')
-        print('='*50)
-    else:
-        qa_chain = setup_qa_chain()
-        response = qa_chain({'query': args.input})
-        print(f'\nAnswer: {response["result"]}')
-        print('=' * 50)
-    end = timeit.default_timer()
-
-    # print(f"Time to retrieve answer: {end - start}")