Sourcery refactored main branch #2
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
| PATH_SEPARATOR = WIN32 and "\\" or "/" | ||
| PATH_SEPARATOR = "\\" if WIN32 else "/" |
There was a problem hiding this comment.
Lines 27-27 refactored with the following changes:
- Replace boolean ternary with inline if expression (
ternary-to-if-expression)
Comment on lines
-264
to
-266
| # Warn if use_docker was unspecified (or None), and cannot be provided (the default). | ||
| # In this case the current behavior is to fall back to run natively, but this behavior | ||
| # is subject to change. |
There was a problem hiding this comment.
Function execute_code refactored with the following changes:
- Swap positions of nested conditionals (
swap-nested-ifs) - Hoist nested repeated code outside conditional statements (
hoist-similar-statement-from-if) - Remove unnecessary casts to int, str, float or bool (
remove-unnecessary-cast)
This removes the following comments ( why? ):
# In this case the current behavior is to fall back to run natively, but this behavior
# Warn if use_docker was unspecified (or None), and cannot be provided (the default).
# is subject to change.
Comment on lines
-448
to
+445
| if pos == -1: | ||
| return response | ||
| return response[:pos] | ||
| return response if pos == -1 else response[:pos] |
There was a problem hiding this comment.
Function _remove_check refactored with the following changes:
- Lift code into else after jump in control flow (
reintroduce-else) - Replace if statement with if expression (
assign-if-exp)
Comment on lines
-491
to
+486
| "success": any(s for s in success_list), | ||
| "success": any(success_list), |
There was a problem hiding this comment.
Function eval_function_completions refactored with the following changes:
- Simplify generator expression (
simplify-generator)
Comment on lines
-53
to
+54
| if idx < 0: | ||
| return None | ||
| if idx < 0: | ||
| return None |
There was a problem hiding this comment.
Function last_boxed_only_string refactored with the following changes:
- Hoist conditional out of nested conditional (
hoist-if-from-if) - Replace if statement with if expression (
assign-if-exp) - Inline variable that is immediately returned (
inline-immediately-returned-variable)
| if isinstance(message, str): | ||
| return {"content": message} | ||
| else: | ||
| return message | ||
| return {"content": message} if isinstance(message, str) else message |
There was a problem hiding this comment.
Function ConversableAgent._message_to_dict refactored with the following changes:
- Replace if statement with if expression (
assign-if-exp)
Comment on lines
-331
to
+328
| # When the agent composes and sends the message, the role of the message is "assistant" | ||
| # unless it's "function". | ||
| valid = self._append_oai_message(message, "assistant", recipient) | ||
| if valid: | ||
| if valid := self._append_oai_message(message, "assistant", recipient): |
There was a problem hiding this comment.
Function ConversableAgent.send refactored with the following changes:
- Use named expression to simplify assignment and conditional (
use-named-expression)
This removes the following comments ( why? ):
# unless it's "function".
# When the agent composes and sends the message, the role of the message is "assistant"
Comment on lines
-380
to
+374
| # When the agent composes and sends the message, the role of the message is "assistant" | ||
| # unless it's "function". | ||
| valid = self._append_oai_message(message, "assistant", recipient) | ||
| if valid: | ||
| if valid := self._append_oai_message(message, "assistant", recipient): |
There was a problem hiding this comment.
Function ConversableAgent.a_send refactored with the following changes:
- Use named expression to simplify assignment and conditional (
use-named-expression)
This removes the following comments ( why? ):
# unless it's "function".
# When the agent composes and sends the message, the role of the message is "assistant"
Comment on lines
-708
to
+723
| else: | ||
| if self._consecutive_auto_reply_counter[sender] >= self._max_consecutive_auto_reply_dict[sender]: | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| terminate = self._is_termination_msg(message) | ||
| reply = self.get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| if terminate | ||
| else f"Please give feedback to {sender.name}. Press enter to skip and use auto-reply, or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply if reply or not terminate else "exit" | ||
| elif self._is_termination_msg(message): | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| reply = self.get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply or "exit" | ||
| elif self._consecutive_auto_reply_counter[sender] >= self._max_consecutive_auto_reply_dict[sender]: | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| terminate = self._is_termination_msg(message) | ||
| reply = self.get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| if terminate | ||
| else f"Please give feedback to {sender.name}. Press enter to skip and use auto-reply, or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply if reply or not terminate else "exit" | ||
| elif self._is_termination_msg(message): | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| reply = self.get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply or "exit" |
There was a problem hiding this comment.
Function ConversableAgent.check_termination_and_human_reply refactored with the following changes:
- Merge else clause's nested if statement into elif (
merge-else-if-into-elif) - Split conditional into multiple branches (
split-or-ifs) - Merge duplicate blocks in conditional (
merge-duplicate-blocks) - Remove redundant conditional (
remove-redundant-if)
Comment on lines
-779
to
+793
| else: | ||
| if self._consecutive_auto_reply_counter[sender] >= self._max_consecutive_auto_reply_dict[sender]: | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| terminate = self._is_termination_msg(message) | ||
| reply = await self.a_get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| if terminate | ||
| else f"Please give feedback to {sender.name}. Press enter to skip and use auto-reply, or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply if reply or not terminate else "exit" | ||
| elif self._is_termination_msg(message): | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| reply = await self.a_get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply or "exit" | ||
| elif self._consecutive_auto_reply_counter[sender] >= self._max_consecutive_auto_reply_dict[sender]: | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| terminate = self._is_termination_msg(message) | ||
| reply = await self.a_get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| if terminate | ||
| else f"Please give feedback to {sender.name}. Press enter to skip and use auto-reply, or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply if reply or not terminate else "exit" | ||
| elif self._is_termination_msg(message): | ||
| if self.human_input_mode == "NEVER": | ||
| reply = "exit" | ||
| else: | ||
| # self.human_input_mode == "TERMINATE": | ||
| reply = await self.a_get_human_input( | ||
| f"Please give feedback to {sender.name}. Press enter or type 'exit' to stop the conversation: " | ||
| ) | ||
| no_human_input_msg = "NO HUMAN INPUT RECEIVED." if not reply else "" | ||
| # if the human input is empty, and the message is a termination message, then we will terminate the conversation | ||
| reply = reply or "exit" |
There was a problem hiding this comment.
Function ConversableAgent.a_check_termination_and_human_reply refactored with the following changes:
- Merge else clause's nested if statement into elif (
merge-else-if-into-elif) - Split conditional into multiple branches (
split-or-ifs) - Merge duplicate blocks in conditional (
merge-duplicate-blocks) - Remove redundant conditional (
remove-redundant-if)
Comment on lines
-962
to
+951
| reply = input(prompt) | ||
| return reply | ||
| return input(prompt) |
There was a problem hiding this comment.
Function ConversableAgent.get_human_input refactored with the following changes:
- Inline variable that is immediately returned (
inline-immediately-returned-variable)
Comment on lines
-976
to
+964
| reply = input(prompt) | ||
| return reply | ||
| return input(prompt) |
There was a problem hiding this comment.
Function ConversableAgent.a_get_human_input refactored with the following changes:
- Inline variable that is immediately returned (
inline-immediately-returned-variable)
Comment on lines
-48
to
+51
| else: | ||
| offset = self.agent_names.index(agent.name) + 1 | ||
| for i in range(len(self.agents)): | ||
| if self.agents[(offset + i) % len(self.agents)] in agents: | ||
| return self.agents[(offset + i) % len(self.agents)] | ||
| offset = self.agent_names.index(agent.name) + 1 | ||
| for i in range(len(self.agents)): | ||
| if self.agents[(offset + i) % len(self.agents)] in agents: | ||
| return self.agents[(offset + i) % len(self.agents)] |
There was a problem hiding this comment.
Function GroupChat.next_agent refactored with the following changes:
- Remove unnecessary else after guard condition (
remove-unnecessary-else)
| contain_code = False | ||
| for c in cb: | ||
| if c[0] == "python" or c[0] == "wolfram": | ||
| contain_code = True | ||
| break | ||
| contain_code = any(c[0] in ["python", "wolfram"] for c in cb) |
There was a problem hiding this comment.
Function _is_termination_msg_mathchat refactored with the following changes:
- Use any() instead of for loop (
use-any) - Replace multiple comparisons of same variable with
inoperator (merge-comparisons)
Comment on lines
-110
to
+106
| if "=" in last_line: | ||
| last_line = "print(" + last_line.split(" = ")[0] + ")" | ||
| lines.append(last_line) | ||
| else: | ||
| lines[-1] = "print(" + last_line + ")" | ||
| lines[-1] = f"print({last_line})" |
There was a problem hiding this comment.
Function _add_print_to_last_line refactored with the following changes:
- Remove redundant conditional (
remove-redundant-if) - Use f-string instead of string concatenation [×2] (
use-fstring-for-concatenation)
Comment on lines
-259
to
+268
| if self.verbosity >= 2: | ||
| # Use the messaging mechanism so that the analyzer's messages are included in the printed chat. | ||
| self.analyzer.reset() # Clear the analyzer's list of messages. | ||
| self.send( | ||
| recipient=self.analyzer, message=text_to_analyze, request_reply=False | ||
| ) # Put the message in the analyzer's list. | ||
| self.send(recipient=self.analyzer, message=analysis_instructions, request_reply=True) # Request the reply. | ||
| return self.last_message(self.analyzer)["content"] | ||
| else: | ||
| if self.verbosity < 2: | ||
| # Use the analyzer's method directly, to leave analyzer message out of the printed chat. | ||
| return self.analyzer.analyze_text(text_to_analyze, analysis_instructions) | ||
| # Use the messaging mechanism so that the analyzer's messages are included in the printed chat. | ||
| self.analyzer.reset() # Clear the analyzer's list of messages. | ||
| self.send( | ||
| recipient=self.analyzer, message=text_to_analyze, request_reply=False | ||
| ) # Put the message in the analyzer's list. | ||
| self.send(recipient=self.analyzer, message=analysis_instructions, request_reply=True) # Request the reply. | ||
| return self.last_message(self.analyzer)["content"] |
There was a problem hiding this comment.
Function TeachableAgent.analyze refactored with the following changes:
- Swap if/else branches (
swap-if-else-branches) - Remove unnecessary else after guard condition (
remove-unnecessary-else)
Comment on lines
-306
to
+305
| print(colored(" Location = {}".format(self.path_to_dict), "light_green")) | ||
| print(colored(f" Location = {self.path_to_dict}", "light_green")) |
There was a problem hiding this comment.
Function MemoStore.__init__ refactored with the following changes:
- Replace call to format with f-string (
use-fstring-for-formatting)
Comment on lines
-320
to
+319
| " ID: {}\n INPUT TEXT: {}\n OUTPUT TEXT: {}".format(uid, input_text, output_text), | ||
| f" ID: {uid}\n INPUT TEXT: {input_text}\n OUTPUT TEXT: {output_text}", |
There was a problem hiding this comment.
Function MemoStore.list_memos refactored with the following changes:
- Replace call to format with f-string (
use-fstring-for-formatting)
Comment on lines
-328
to
+327
| print(colored(" Location = {}".format(self.path_to_dict), "light_green")) | ||
| print(colored(f" Location = {self.path_to_dict}", "light_green")) |
There was a problem hiding this comment.
Function MemoStore.close refactored with the following changes:
- Replace call to format with f-string (
use-fstring-for-formatting)
Comment on lines
-347
to
+346
| "\nINPUT-OUTPUT PAIR ADDED TO VECTOR DATABASE:\n ID\n {}\n INPUT\n {}\n OUTPUT\n {}".format( | ||
| self.last_memo_id, input_text, output_text | ||
| ), | ||
| f"\nINPUT-OUTPUT PAIR ADDED TO VECTOR DATABASE:\n ID\n {self.last_memo_id}\n INPUT\n {input_text}\n OUTPUT\n {output_text}", |
There was a problem hiding this comment.
Function MemoStore.add_input_output_pair refactored with the following changes:
- Replace call to format with f-string (
use-fstring-for-formatting)
Comment on lines
-365
to
+362
| "\nINPUT-OUTPUT PAIR RETRIEVED FROM VECTOR DATABASE:\n INPUT1\n {}\n OUTPUT\n {}\n DISTANCE\n {}".format( | ||
| input_text, output_text, distance | ||
| ), | ||
| f"\nINPUT-OUTPUT PAIR RETRIEVED FROM VECTOR DATABASE:\n INPUT1\n {input_text}\n OUTPUT\n {output_text}\n DISTANCE\n {distance}", |
There was a problem hiding this comment.
Function MemoStore.get_nearest_memo refactored with the following changes:
- Replace call to format with f-string (
use-fstring-for-formatting)
Comment on lines
-375
to
+370
| if n_results > len(self.uid_text_dict): | ||
| n_results = len(self.uid_text_dict) | ||
| n_results = min(n_results, len(self.uid_text_dict)) |
There was a problem hiding this comment.
Function MemoStore.get_related_memos refactored with the following changes:
- Replace comparison with min/max call (
min-max-identity) - Replace call to format with f-string (
use-fstring-for-formatting)
Comment on lines
-401
to
+434
| examples = [] | ||
| examples.append({"text": "When I say papers I mean research papers, which are typically pdfs.", "label": "yes"}) | ||
| examples.append({"text": "Please verify that each paper you listed actually uses langchain.", "label": "no"}) | ||
| examples.append({"text": "Tell gpt the output should still be latex code.", "label": "no"}) | ||
| examples.append({"text": "Hint: convert pdfs to text and then answer questions based on them.", "label": "yes"}) | ||
| examples.append( | ||
| {"text": "To create a good PPT, include enough content to make it interesting.", "label": "yes"} | ||
| ) | ||
| examples.append( | ||
| examples = [ | ||
| { | ||
| "text": "When I say papers I mean research papers, which are typically pdfs.", | ||
| "label": "yes", | ||
| }, | ||
| { | ||
| "text": "Please verify that each paper you listed actually uses langchain.", | ||
| "label": "no", | ||
| }, | ||
| { | ||
| "text": "Tell gpt the output should still be latex code.", | ||
| "label": "no", | ||
| }, | ||
| { | ||
| "text": "Hint: convert pdfs to text and then answer questions based on them.", | ||
| "label": "yes", | ||
| }, | ||
| { | ||
| "text": "To create a good PPT, include enough content to make it interesting.", | ||
| "label": "yes", | ||
| }, | ||
| { | ||
| "text": "No, for this case the columns should be aspects and the rows should be frameworks.", | ||
| "label": "no", | ||
| } | ||
| ) | ||
| examples.append({"text": "When writing code, remember to include any libraries that are used.", "label": "yes"}) | ||
| examples.append({"text": "Please summarize the papers by Eric Horvitz on bounded rationality.", "label": "no"}) | ||
| examples.append({"text": "Compare the h-index of Daniel Weld and Oren Etzioni.", "label": "no"}) | ||
| examples.append( | ||
| }, | ||
| { | ||
| "text": "When writing code, remember to include any libraries that are used.", | ||
| "label": "yes", | ||
| }, | ||
| { | ||
| "text": "Please summarize the papers by Eric Horvitz on bounded rationality.", | ||
| "label": "no", | ||
| }, | ||
| { | ||
| "text": "Compare the h-index of Daniel Weld and Oren Etzioni.", | ||
| "label": "no", | ||
| }, | ||
| { | ||
| "text": "Double check to be sure that the columns in a table correspond to what was asked for.", | ||
| "label": "yes", | ||
| } | ||
| ) | ||
| }, | ||
| ] |
There was a problem hiding this comment.
Function MemoStore.prepopulate refactored with the following changes:
- Merge append into list declaration [×10] (
merge-list-append)
| output_text = oai.ChatCompletion.extract_text_or_function_call(response)[0] | ||
| return output_text | ||
| return oai.ChatCompletion.extract_text_or_function_call(response)[0] |
There was a problem hiding this comment.
Function TextAnalyzerAgent.analyze_text refactored with the following changes:
- Inline variable that is immediately returned (
inline-immediately-returned-variable)
| temperature_or_top_p = params.pop("temperature_or_top_p", None) | ||
| if temperature_or_top_p: | ||
| if temperature_or_top_p := params.pop("temperature_or_top_p", None): |
There was a problem hiding this comment.
Function Completion._get_params_for_create refactored with the following changes:
- Use named expression to simplify assignment and conditional (
use-named-expression)
Comment on lines
-27
to
+33
| teachable_agent = TeachableAgent( | ||
| return TeachableAgent( | ||
| name="teachableagent", | ||
| llm_config={"config_list": config_list, "request_timeout": 120, "use_cache": use_cache}, | ||
| llm_config={ | ||
| "config_list": config_list, | ||
| "request_timeout": 120, | ||
| "use_cache": use_cache, | ||
| }, |
There was a problem hiding this comment.
Function create_teachable_agent refactored with the following changes:
- Inline variable that is immediately returned (
inline-immediately-returned-variable)
Comment on lines
-38
to
-44
| feeds_summary = "\n".join( | ||
| return "\n".join( | ||
| [ | ||
| f"News summary: {f['title']}. {f['summary']} overall_sentiment_score: {f['overall_sentiment_score']}" | ||
| for f in feeds | ||
| ] | ||
| ) | ||
| return feeds_summary |
There was a problem hiding this comment.
Function get_market_news refactored with the following changes:
- Inline variable that is immediately returned (
inline-immediately-returned-variable)
Comment on lines
-42
to
+48
| teachable_agent = TeachableAgent( | ||
| return TeachableAgent( | ||
| name="teachableagent", | ||
| llm_config={"config_list": config_list, "request_timeout": 120, "use_cache": use_cache}, | ||
| llm_config={ | ||
| "config_list": config_list, | ||
| "request_timeout": 120, | ||
| "use_cache": use_cache, | ||
| }, |
There was a problem hiding this comment.
Function create_teachable_agent refactored with the following changes:
- Inline variable that is immediately returned (
inline-immediately-returned-variable)
| for pair in dists.keys(): | ||
| for pair in dists: |
There was a problem hiding this comment.
Function solve_tsp refactored with the following changes:
- Remove unnecessary call to keys() (
remove-dict-keys) - Convert for loop into call to sum() (
sum-comprehension) - Inline variable that is only used once [×2] (
inline-variable)
This removes the following comments ( why? ):
# Calculate the cost of the current route
| max([len(x["solution"].split()) for x in tune_data]), | ||
| max(len(x["solution"].split()) for x in tune_data), |
There was a problem hiding this comment.
Function test_math refactored with the following changes:
- Replace unneeded comprehension with generator (
comprehension-to-generator) - Replace a[0:x] with a[:x] and a[x:len(a)] with a[x:] (
remove-redundant-slice-index)
Apply Sweep Rules to your PR?
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Branch
mainrefactored by Sourcery.If you're happy with these changes, merge this Pull Request using the Squash and merge strategy.
See our documentation here.
Run Sourcery locally
Reduce the feedback loop during development by using the Sourcery editor plugin:
Review changes via command line
To manually merge these changes, make sure you're on the
mainbranch, then run:Help us improve this pull request!