Merge pull request #264 from gukoff/comments-to-docstrings

Turn class comments into class docstrings

Author: tonybaloney

app/backend/approaches/chatreadretrieveread.py

@@ -6,10 +6,13 @@
 from approaches.approach import Approach
 from text import nonewlines
 
-# Simple retrieve-then-read implementation, using the Cognitive Search and OpenAI APIs directly. It first retrieves
-# top documents from search, then constructs a prompt with them, and then uses OpenAI to generate an completion 
-# (answer) with that prompt.
 class ChatReadRetrieveReadApproach(Approach):
+    """
+    Simple retrieve-then-read implementation, using the Cognitive Search and OpenAI APIs directly. It first retrieves
+    top documents from search, then constructs a prompt with them, and then uses OpenAI to generate an completion
+    (answer) with that prompt.
+    """
+
     prompt_prefix = """<|im_start|>system
 Assistant helps the company employees with their healthcare plan questions, and questions about the employee handbook. Be brief in your answers.
 Answer ONLY with the facts listed in the list of sources below. If there isn't enough information below, say you don't know. Do not generate answers that don't use the sources below. If asking a clarifying question to the user would help, ask the question.

app/backend/approaches/readretrieveread.py

@@ -11,12 +11,17 @@
 from lookuptool import CsvLookupTool
 from typing import Any
 
-# Attempt to answer questions by iteratively evaluating the question to see what information is missing, and once all information
-# is present then formulate an answer. Each iteration consists of two parts: first use GPT to see if we need more information, 
-# second if more data is needed use the requested "tool" to retrieve it. The last call to GPT answers the actual question.
-# This is inspired by the MKRL paper[1] and applied here using the implementation in Langchain.
-# [1] E. Karpas, et al. arXiv:2205.00445
 class ReadRetrieveReadApproach(Approach):
+    """
+    Attempt to answer questions by iteratively evaluating the question to see what information is missing, and once all information
+    is present then formulate an answer. Each iteration consists of two parts:
+     1. use GPT to see if we need more information
+     2. if more data is needed, use the requested "tool" to retrieve it.
+    The last call to GPT answers the actual question.
+    This is inspired by the MKRL paper[1] and applied here using the implementation in Langchain.
+
+    [1] E. Karpas, et al. arXiv:2205.00445
+    """
 
     template_prefix = \
 "You are an intelligent assistant helping Contoso Inc employees with their healthcare plan questions and employee handbook questions. " \

app/backend/approaches/retrievethenread.py

@@ -5,10 +5,13 @@
 from text import nonewlines
 from typing import Any
 
-# Simple retrieve-then-read implementation, using the Cognitive Search and OpenAI APIs directly. It first retrieves
-# top documents from search, then constructs a prompt with them, and then uses OpenAI to generate an completion 
-# (answer) with that prompt.
+
 class RetrieveThenReadApproach(Approach):
+    """
+    Simple retrieve-then-read implementation, using the Cognitive Search and OpenAI APIs directly. It first retrieves
+    top documents from search, then constructs a prompt with them, and then uses OpenAI to generate an completion
+    (answer) with that prompt.
+    """
 
     template = \
 "You are an intelligent assistant helping Contoso Inc employees with their healthcare plan questions and employee handbook questions. " + \