itsmariamaraki commited on
Commit
3e819ab
·
verified ·
1 Parent(s): 3104f9a

Update assessment3_maria_maraki.py

Browse files
Files changed (1) hide show
  1. assessment3_maria_maraki.py +6 -11
assessment3_maria_maraki.py CHANGED
@@ -7,7 +7,9 @@ Original file is located at
7
  https://colab.research.google.com/drive/1jm_hI8O4Y0HgNNdWLnkLBIjlzSaGwwBS
8
  """
9
 
10
-
 
 
11
 
12
  """Since the dataset **emails.csv** in the [Enron Email Dataset](https://www.kaggle.com/datasets/wcukierski/enron-email-dataset/code) was too big, I split the original dataset into smaller .csv files and then chose one of the split files: ***emails_subset.csv***
13
 
@@ -51,10 +53,7 @@ pd.set_option('display.max_columns',None,
51
  'display.max_colwidth',None
52
  )
53
 
54
- from google.colab import drive
55
- drive.mount('/content/drive')
56
-
57
- email_data = pd.read_csv('/content/drive/MyDrive/data/emails_subset.csv')
58
  email_data.head()
59
 
60
 
@@ -83,7 +82,7 @@ from langchain.document_loaders import DirectoryLoader
83
  import warnings
84
  warnings.filterwarnings('ignore')
85
 
86
- openAI_embeddings = OpenAIEmbeddings(openai_api_key="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")
87
 
88
  content = []
89
  for item in email_data.message:
@@ -116,7 +115,7 @@ The fine-tuning task kept crushing my notebook and I had to restart so I stored
116
 
117
  """# Gradio Interface that answers questions related to the case"""
118
 
119
- email_data_retrieval = RetrievalQA.from_chain_type(llm=OpenAI(openai_api_key="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",
120
  temperature=0.6,
121
  top_p=0.5,
122
  max_tokens=500),
@@ -135,7 +134,3 @@ iface = gradio.Interface(
135
 
136
  iface.launch()
137
 
138
-
139
-
140
-
141
-
 
7
  https://colab.research.google.com/drive/1jm_hI8O4Y0HgNNdWLnkLBIjlzSaGwwBS
8
  """
9
 
10
+ ###########################################################################################################################################################
11
+ #The provided code has undergone minor adjustments from its original source (colab enviroment) to ensure its compatibility with the Hugging Face ecosystem.
12
+ ###########################################################################################################################################################
13
 
14
  """Since the dataset **emails.csv** in the [Enron Email Dataset](https://www.kaggle.com/datasets/wcukierski/enron-email-dataset/code) was too big, I split the original dataset into smaller .csv files and then chose one of the split files: ***emails_subset.csv***
15
 
 
53
  'display.max_colwidth',None
54
  )
55
 
56
+ email_data = pd.read_csv('emails_subset.csv')
 
 
 
57
  email_data.head()
58
 
59
 
 
82
  import warnings
83
  warnings.filterwarnings('ignore')
84
 
85
+ openAI_embeddings = OpenAIEmbeddings(openai_api_key=os.environ.get('OPENAI_API_KEY'))
86
 
87
  content = []
88
  for item in email_data.message:
 
115
 
116
  """# Gradio Interface that answers questions related to the case"""
117
 
118
+ email_data_retrieval = RetrievalQA.from_chain_type(llm=OpenAI(openai_api_key=os.environ.get('OPENAI_API_KEY'),
119
  temperature=0.6,
120
  top_p=0.5,
121
  max_tokens=500),
 
134
 
135
  iface.launch()
136