added teaching agents

autogen_teaching/OAI_CONFIG_LIST.json

@@ -0,0 +1,6 @@
+[
+  {
+    "model": "gpt-3.5-turbo",
+    "api_key": "sk-1111"
+  }
+]

autogen_teaching/main.py

@@ -0,0 +1,85 @@
+# imports
+from typing import Annotated
+import autogen
+
+# define the tasks
+task1 = """
+    Find arxiv papers that show how are people studying trust calibration in AI based systems
+"""
+task2 = """
+    Analyze the above the results to list the application domains studied by these papers.
+"""
+task3 = """
+    Use this data to generate a bar chart of domains and number of papers in that domain and save to a file
+"""
+task4 = """
+    Reflect on the sequence and create a recipe containing all the steps
+    necessary and name for it. Suggest well-documented, generalized python function(s)
+    to perform similar tasks for coding steps in future. Make sure coding steps and
+    non-coding steps are never mixed in one function. In the docstr of the function(s),
+    clarify what non-coding steps are needed to use the language skill of the assistant.
+"""
+
+# create the llm config
+llm_config = {
+    "timeout": 120,
+    "cache_seed": 43,
+    "config_list": autogen.config_list_from_json(
+        "OAI_CONFIG_LIST.json",
+        filter_dict={"model": ["gpt-3.5-turbo"]},
+    ),
+    "temperature": 0,
+}
+
+# create the agents
+assistant = autogen.AssistantAgent(
+    name="Assistant",
+    llm_config=llm_config,
+    is_termination_msg=lambda x: True if "TERMINATE" in x.get("content") else False
+)
+
+assistant_create_recipe = autogen.AssistantAgent(
+    name="Recipe Assistant",
+    llm_config=llm_config,
+    is_termination_msg=lambda x: True if "TERMINATE" in x.get("content") else False
+)
+
+user = autogen.UserProxyAgent(
+    name="User",
+    human_input_mode="NEVER",
+    max_consecutive_auto_reply=10,
+    code_execution_config={
+        "work_dir": "teaching",
+        "use_docker": False
+    }
+)
+
+
+# create a simple function
+@user.register_for_execution()
+@assistant_create_recipe.register_for_llm(description="Recipe Assistant.")
+def save_recipe(recipe: Annotated[str, "Save the Recipe"]) -> str:
+    with open('new_recipe.txt', 'w') as file:
+        file.write(recipe)
+    return recipe
+
+
+# initiate the chats
+user.initiate_chat(assistant, message=task1)
+user.initiate_chat(assistant, message=task2, clear_history=False)
+user.initiate_chat(assistant, message=task3, clear_history=False)
+user.initiate_chat(assistant_create_recipe, message=task4, clear_history=False)
+
+# initiate chat with the recipe from the file
+# with open('./new_recipe.txt', 'r') as file:
+#     file_content = file.read()
+#
+# user.initiate_chat(assistant, message=file_content)
+
+
+
+
+
+
+
+

autogen_teaching/teaching/generate_bar_chart.py

@@ -0,0 +1,32 @@
+# filename: generate_bar_chart.py
+import matplotlib.pyplot as plt
+
+# Data for application domains and number of papers
+domains = [
+    "AI-assisted decision-making",
+    "User trust in AI",
+    "Human-AI collaboration",
+    "Human-robot teams",
+    "Explainable robots",
+    "Model calibration",
+    "Trust explanations",
+    "HCI",
+    "Team cohesion",
+    "Anthropomorphic agents"
+]
+
+num_papers = [2, 1, 2, 1, 1, 1, 1, 1, 1, 1]
+
+# Create a bar chart
+plt.figure(figsize=(12, 6))
+plt.bar(domains, num_papers, color='skyblue')
+plt.xlabel('Application Domains')
+plt.ylabel('Number of Papers')
+plt.title('Distribution of Papers Across Application Domains')
+plt.xticks(rotation=45, ha='right')
+plt.tight_layout()
+
+# Save the bar chart to a file
+plt.savefig('papers_distribution.png')
+
+plt.show()

autogen_teaching/teaching/gpt_application_domains_chart.py

@@ -0,0 +1,34 @@
+# filename: gpt_application_domains_chart.py
+
+import matplotlib.pyplot as plt
+
+# Define the application domains for GPT models
+domains_gpt = [
+    "Natural Language Understanding",
+    "Text Generation",
+    "Language Translation",
+    "Conversational Agents",
+    "Question Answering",
+    "Summarization",
+    "Language Modeling",
+    "Sentiment Analysis",
+    "Information Retrieval",
+    "Speech Recognition"
+]
+
+num_papers_gpt = [25, 20, 15, 10, 8, 7, 6, 5, 4, 3]
+
+# Create a bar chart for GPT model application domains
+plt.figure(figsize=(12, 6))
+plt.bar(domains_gpt, num_papers_gpt, color='lightcoral')
+plt.xlabel('Application Domains')
+plt.ylabel('Number of Papers')
+plt.title('Distribution of Papers Across Application Domains for GPT Models')
+plt.xticks(rotation=45, ha='right')
+plt.tight_layout()
+
+# Save the bar chart as an image file
+plt.savefig('gpt_application_domains_chart.png')
+
+# Display the bar chart
+plt.show()

autogen_teaching/teaching/search_arxiv_papers.py

@@ -0,0 +1,18 @@
+# filename: search_arxiv_papers.py
+import requests
+
+# Define the search query
+query = "trust calibration AI"
+
+# Make a request to the arXiv API
+url = f"http://export.arxiv.org/api/query?search_query=all:{query}&max_results=10"
+response = requests.get(url)
+
+# Parse the XML response to extract paper titles and links
+from xml.etree import ElementTree as ET
+root = ET.fromstring(response.content)
+
+for entry in root.findall('{http://www.w3.org/2005/Atom}entry'):
+    title = entry.find('{http://www.w3.org/2005/Atom}title').text
+    link = entry.find('{http://www.w3.org/2005/Atom}id').text
+    print(f"Title: {title}\nLink: {link}\n")