update gpt-3.5 version

cfg.py

@@ -26,7 +26,6 @@ mongo_db = (
 logger = logging.getLogger(__name__)
 logging.basicConfig(level=logging.INFO)
 
-# required
 ACTIVELOOP_TOKEN = os.getenv("ACTIVELOOP_TOKEN")
 if ACTIVELOOP_TOKEN is None:
     logger.warning("No activeloop token found, you will not be able to fetch data.")
@@ -45,7 +44,7 @@ deeplake.deepcopy(
     overwrite=True,
     num_workers=12,
 )
-DEEPLAKE_DATASET_PATH = "local_dataset"
+# DEEPLAKE_DATASET_PATH = "local_dataset"
 
 logger.info(f"{DEEPLAKE_DATASET_PATH=}")
 
@@ -89,7 +88,7 @@ true
 Q:
 """,
         "completion_kwargs": {
-            "model": "gpt-3.5-turbo-1106",
+            "model": "gpt-3.5-turbo-0125",
             "stream": False,
             "temperature": 0,
         },
@@ -110,13 +109,13 @@ Q:
     },
     completion_cfg={
         "completion_kwargs": {
-            "model": "gpt-3.5-turbo-1106",
+            "model": "gpt-3.5-turbo-0125",
             "stream": True,
             "temperature": 0,
         },
     },
     tokenizer_cfg={
-        "model_name": "gpt-3.5-turbo-1106",
+        "model_name": "gpt-3.5-turbo-0125",
     },
     documents_formatter_cfg={
         "max_tokens": 13500,

data/process_csvs_store.py

@@ -2,8 +2,9 @@ import pandas as pd
 import time
 import os
 from buster.documents_manager import DeepLakeDocumentsManager
-from deeplake.core.vectorstore import VectorStore
-from langchain.embeddings.openai import OpenAIEmbeddings
+
+# from deeplake.core.vectorstore import VectorStore
+# from langchain.embeddings.openai import OpenAIEmbeddings
 import numpy as np
 
 # from openai import OpenAI