diff --git a/main.py b/main.py index 3e03098..602c58c 100644 --- a/main.py +++ b/main.py @@ -11,6 +11,7 @@ import pymongo import mongo_conn import pgvec_conn import redis_conn +from tqdm import tqdm count = 0 @@ -27,7 +28,8 @@ def retrieve_file_contents(path): contents = [] - for file in files: + print("Parsing files...") + for file in tqdm(files): content = file_extraction_functions[file[0]](file[1]) contents.append({ "type": file[0], @@ -64,7 +66,8 @@ def create_embeddings(pContent): conn.commit() - for content in pContent: + print("generating embeddings...") + for content in tqdm(pContent): for chunk in chunker.generate_chunks(content["content"]): merged_info = "Dateiname: " + content["filename"] + " Dateiinhalt: " + chunk # print(merged_info)