Add the documentation to some functions

functions.py

@@ -30,6 +30,16 @@ text_splitter = CharacterTextSplitter()
 
 
 def get_nearest_examples(question: str, k: int):
+    """
+    Returns the k nearest examples to a given question.
+
+    Args:
+        question (str): The input question to find nearest examples for.
+        k (int): The number of nearest examples to retrieve.
+
+    Returns:
+        The k nearest examples to the given question.
+    """
     print(['get_nearest_examples', 'start'])
     question_embedding = get_embeddings([question]).cpu().detach().numpy()
     embeddings_dataset = shared['embeddings_dataset']
@@ -56,6 +66,15 @@ def get_embeddings(text):
 
 
 def build_faiss_index(text):
+    """
+    Builds a FAISS index for the given text.
+
+    Args:
+        text (str): The input text to build a FAISS index for.
+
+    Returns:
+        None.
+    """
     print(['build_faiss_index', 'start'])
     text_list = split_text(text)
     emb_list = []
@@ -71,6 +90,15 @@ def build_faiss_index(text):
 
 
 def extract_text(url: str):
+    """
+    Extracts the text content from a given URL and returns it as a string.
+
+    Args:
+        url (str): The URL to extract text content from.
+
+    Returns:
+        str: The text content extracted from the URL, or an empty string if the URL is invalid.
+    """
     print(['extract_text', 'start'])
     if url is None or url.strip() == '':
         return ''
@@ -83,20 +111,50 @@ def extract_text(url: str):
 
 
 def split_text(text: str):
+    """
+    Splits a given text into a list of individual lines.
+
+    Args:
+        text (str): The input text to split into lines.
+
+    Returns:
+        List[str]: A list of individual lines in the input text.
+    """
     lines = text.split('\n')
     lines = [line.strip() for line in lines if line.strip()]
     return lines
 
 
 def remove_prompt(text: str) -> str:
+    """
+    Removes the prompt from a given text and returns the resulting text.
+
+    Args:
+        text (str): The input text to remove the prompt from.
+
+    Returns:
+        str: The input text with the prompt removed, or the original text if the prompt is not found.
+    """
     output_prompt = 'Output: '
-    idx = text.index(output_prompt)
-    res = text[idx + len(output_prompt):].strip()
-    res = res.replace('Input: ', '')
+    try:
+        idx = text.index(output_prompt)
+        res = text[idx + len(output_prompt):].strip()
+        res = res.replace('Input: ', '')
+    except ValueError:
+        res = text
     return res
 
 
 def summarize_text(text: str) -> str:
+    """
+    Generates a summary of the given text using a pre-trained language model.
+
+    Args:
+        text (str): The input text to generate a summary for.
+
+    Returns:
+        str: The generated summary for the input text.
+    """
     print(['summarize_text', 'start'])
 
     print(['summarize_text', 'splitting text'])
@@ -132,6 +190,15 @@ def summarize_text_v1(text: str):
 
 
 def generate_question(text: str):
+    """
+    Generates a question based on a random section of the input text using a pre-trained language model.
+
+    Args:
+        text (str): The input text to generate a question for.
+
+    Returns:
+        str: The generated question for the input text.
+    """
     print(['generate_question', 'start'])
     # Get a random section of the whole text to generate a question
     fragments = split_text(text)
@@ -156,6 +223,15 @@ def get_answer_context():
 
 
 def answer_question(question: str):
+    """
+    Generates an answer to the given question based on a pre-trained language model and a pre-built Faiss index.
+
+    Args:
+        question (str): The question to generate an answer for.
+
+    Returns:
+        str: The generated answer for the question.
+    """
     print(['answer_question', 'start'])
     full_text = shared['full_text']