Yasu777 commited on
Commit
b7cf0a0
·
1 Parent(s): e632315

Update third.py

Browse files
Files changed (1) hide show
  1. third.py +5 -25
third.py CHANGED
@@ -2,7 +2,6 @@
2
 
3
  import os
4
  import openai
5
- import json
6
  from langchain.chat_models import ChatOpenAI
7
  from langchain.experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner
8
  from langchain.llms import OpenAI
@@ -58,13 +57,10 @@ async def main(editable_output2, keyword_id):
58
 
59
  # Specify the type of information you want to research.
60
  if "人物" in h1_text or any("人物" in h2_text for h2_text in h2_texts) or any("人物" in h3_text for h3_text in h3_texts):
61
- # If the topic is about a person, specify that you want to research their name and career.
62
  purpose += " including the person's name and career"
63
  elif "商品" in h1_text or any("商品" in h2_text for h2_text in h2_texts) or any("商品" in h3_text for h3_text in h3_texts):
64
- # If the topic is about a product, specify that you want to research the brand name, product name, and price.
65
  purpose += " including the brand name, product name, and price"
66
  elif "イベント" in h1_text or any("イベント" in h2_text for h2_text in h2_texts) or any("イベント" in h3_text for h3_text in h3_texts):
67
- # If the topic is about an event, specify that you want to research the event's content, schedule, and venue.
68
  purpose += " including the event's content, schedule, and venue"
69
 
70
  # Convert the purpose into an instruction in the form of a question.
@@ -74,23 +70,7 @@ async def main(editable_output2, keyword_id):
74
  if instruction not in executed_instructions:
75
  raw_output = agent.run(instruction)
76
  executed_instructions.append(instruction)
77
-
78
- # raw_outputの内容を確認
79
- print(f"Raw Output: {raw_output}")
80
-
81
- try:
82
- # エージェントの出力をJSONとして解析
83
- agent_output = json.loads(raw_output)
84
-
85
- # 'action_input'を取得
86
- response_content = agent_output['action']['action_input']
87
- except json.JSONDecodeError:
88
- # JSON形式でない場合は、raw_outputを直接使用する
89
- response_content = raw_output
90
- except Exception as e:
91
- print(f"Error: {e}")
92
- return
93
-
94
  research_results.append(response_content)
95
  else:
96
  response_content = "This instruction has already been executed."
@@ -102,10 +82,10 @@ async def main(editable_output2, keyword_id):
102
  }
103
 
104
  # Prepare the user message
105
- research_summary = "\n".join(research_results) # 調査結果をまとめる
106
  user_message = {
107
  "role": "user",
108
- "content": f'"{h1_text}"という記事タイトルに沿った導入文を日本語で作成し、各見出し"{", ".join(h2_texts)}"についての導入文を作成してください。導入文はそれぞれの見出しの直下にある"{", ".join(h3_texts)}"の内容を考慮に入れて作成してください。その後、"{", ".join(h3_texts)}"についての本文を作成してください。各セクションは、読者の興味を引き、記事の主題を明確に示すものであるべきです。最後に、記事全体のまとめ、<h2>まとめ</h2>としてクローズしてください。以下に取得した情報を示します:{research_summary}'
109
  }
110
 
111
  # Generate a new text using the ChatCompletion API
@@ -115,10 +95,10 @@ async def main(editable_output2, keyword_id):
115
  temperature=0.7,
116
  )
117
  result = response.choices[0]["message"]["content"]
118
-
119
  # Save the generated message to output3.txt
120
  with open('output3.txt', 'w', encoding='utf-8') as f:
121
  f.write(result)
122
-
123
  # Print the generated message
124
  print(result)
 
2
 
3
  import os
4
  import openai
 
5
  from langchain.chat_models import ChatOpenAI
6
  from langchain.experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner
7
  from langchain.llms import OpenAI
 
57
 
58
  # Specify the type of information you want to research.
59
  if "人物" in h1_text or any("人物" in h2_text for h2_text in h2_texts) or any("人物" in h3_text for h3_text in h3_texts):
 
60
  purpose += " including the person's name and career"
61
  elif "商品" in h1_text or any("商品" in h2_text for h2_text in h2_texts) or any("商品" in h3_text for h3_text in h3_texts):
 
62
  purpose += " including the brand name, product name, and price"
63
  elif "イベント" in h1_text or any("イベント" in h2_text for h2_text in h2_texts) or any("イベント" in h3_text for h3_text in h3_texts):
 
64
  purpose += " including the event's content, schedule, and venue"
65
 
66
  # Convert the purpose into an instruction in the form of a question.
 
70
  if instruction not in executed_instructions:
71
  raw_output = agent.run(instruction)
72
  executed_instructions.append(instruction)
73
+ response_content = raw_output
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
  research_results.append(response_content)
75
  else:
76
  response_content = "This instruction has already been executed."
 
82
  }
83
 
84
  # Prepare the user message
85
+ research_summary = "\n".join(research_results)
86
  user_message = {
87
  "role": "user",
88
+ "content": f'"{h1_text}"という記事タイトルに沿った導入文を日本語で作成し、各見出し"{", ".join(h2_texts)}"についての導入文を作成してください。導入文はそれぞれの見出しの直下にある"{", ".join(h3_texts)}"の内容を考慮に入れて作成してください。その後、"{", ".join(h3_texts)}"のセクションで本文を作成してください。各セクションは、読者の興味を引き、記事の主題を明確に示すものであるべきです。最後に、記事全体のまとめ、<h2>まとめ</h2>としてクローズしてください。以下に取得した情報を示します:{research_summary}'
89
  }
90
 
91
  # Generate a new text using the ChatCompletion API
 
95
  temperature=0.7,
96
  )
97
  result = response.choices[0]["message"]["content"]
98
+
99
  # Save the generated message to output3.txt
100
  with open('output3.txt', 'w', encoding='utf-8') as f:
101
  f.write(result)
102
+
103
  # Print the generated message
104
  print(result)