Create app.py

app.py

@@ -0,0 +1,92 @@
+# https://huggingface.co/spaces/micknikolic/enron
+
+# here are the imports
+
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain import OpenAI, VectorDBQA
+from langchain.document_loaders import DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+import os
+import nltk
+import pytesseract
+
+import pandas as pd
+pd.set_option('display.max_columns',None,
+              'display.max_rows',None,
+              'display.max_colwidth',None
+             )
+import numpy as np
+
+import os
+import re
+import io
+
+import gradio
+
+import warnings
+warnings.filterwarnings('ignore')
+
+# here is the code
+
+# data loading.
+# i am using a subset of the enron dataset, as it would be computationally very expensive to work with over 500k observations locally.
+
+data = pd.read_csv('subset_enron.csv',encoding='utf-8')
+data = data.sample(frac=0.01,random_state=12) #(5174, 2)
+
+# Text pre-processing.
+
+cleaned_message = data["message"].apply(lambda x: re.sub(r'\\{1,2}n', '', x))
+content = cleaned_message.tolist()
+class Document:
+    def __init__(self, page_content, metadata=None):
+        self.page_content = page_content
+        self.metadata = metadata if metadata is not None else {}
+
+documents = [Document(page_content) for page_content in content]
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+texts = text_splitter.split_documents(documents)
+
+openAI_embeddings = OpenAIEmbeddings(openai_api_key=os.getenv("openai_api_key"))
+vStore = Chroma.from_documents(documents=texts, embedding=openAI_embeddings)
+
+# Retrieval QA
+
+model_retrieval = RetrievalQA.from_chain_type(llm=OpenAI(openai_api_key=os.getenv("openai_api_key"),
+                                                         temperature=0.2,
+                                                         top_p=0.2,
+                                                         max_tokens=2000), 
+                                              chain_type="stuff", retriever=vStore.as_retriever())
+
+# Building Gradio based app. The Retrieval model.
+
+def get_answer(question):
+    """
+    Returns the answer on a given question.
+
+    Args:
+        question (string): end-user's input.
+
+    Returns:
+        the model's answer based on the enron emails dataset.
+    """
+    response = model_retrieval.run(question)
+    return response
+
+iface = gradio.Interface(
+    fn=get_answer,
+    inputs=gradio.Textbox(label="Enter your question here"),
+    outputs=[
+        gradio.Textbox(label="Answer")],
+    title="Retrieval QA for the subset of the Enron dataset",
+    examples=[
+        "Who are the senders of these emails?",
+        "What's at the center of these emails?"
+    ]
+)
+
+iface.launch()