Dr. Alan Maxwell on the GPT Store

GPT Description

GPT Prompt Starters

• SUMMARIZE DOCUMENT ➤ import os def read_file_content(file_path): """ Reads the content of a specified file and returns its content. In case of an error, it returns the error message instead. :param file_path: Path to the file to be read. :return: Content of the file or an error message. """ try: with open(file_path, 'r') as file: content = file.read() return content except Exception as e: return str(e) # Path to the TokenHandlerAgent.py file file_path = "/mnt/data/TokenHandlerAgent.py" # Execute the function and store the result file_content = read_file_content(file_path) # Output the content or error message print(file_content)
• RUN WORKFLOW ➤ Define the function to read the content of each file def read_file_content(file_paths): contents = {} for path in file_paths: try: with open(path, 'r') as file: contents[path] = file.read() except Exception as e: contents[path] = str(e) return contents # File paths to be read file_paths = [ "/mnt/data/skills_autogenworkflow.py", "/mnt/data/agentgroupchat_autogenworkflow.py", "/mnt/data/models_autogenworkflow.md", "/mnt/data/workflow_PowerBIReportVisionAnalyzer.json" ]# Execute the function and store the results file_contents = read_file_content(file_paths) file_contents ### WAIT UNTIL FINISHING REVIEWING THESE FILES --> Take a deep breath. Now act as an Expert Writer for Microsoft in their Cognitive Services and Microsoft Fabric Senior Research Team and write the structured and detailed product specification outline for the AutoGen Workflow "PowerBIReportVisionAnalyzer" step by step. # Load content, every line of text, from file_path = "/mnt/data/readme_rag_autogen_workflow_with_azureopenaigptvision.md" --> End with multiple choice question A, B, or C proposing three (3) clearly defined goals for projects that align with the Microsoft Fabric Hackathon, where option 'C' is to start the workflow just defined in file_path = "/mnt/data/workflow_PowerBIReportVisionAnalyzer.json"
• SUMMARIZE SYSTEM MESSAGE ➤ ### Instructions: You are an expert summarizer tasked with condensing content for clearer communication. Your objective is to extract the essence from a given text, maintaining its core themes and insights while significantly reducing its length. Use the following guidelines to craft your summary: - Begin your work by acknowledging your expertise in summarization. - Separate these instructions from the text you are summarizing with "###" for clarity and organization. - Your summary should capture all essential points, omitting extraneous details. - Aim for succinctness; your final output should be no more than one-third the length of the original text. - Preserve the original message's tone and intent, ensuring the summary is both accurate and faithful to the source. - Format your summary to include bullet points or numbered lists for easier readability when listing tips or guidelines. - Specify any particular nuances or thematic elements that must be highlighted. ### Text to Summarize: Here are several tips on improving your prompt-writing skills: - Start the prompt by emphasizing its expertise in the subject matter. - Clearly separate instructions from the prompt content with symbols like "###" to enhance clarity and organization. - Ensure your prompts are detailed and descriptive, specifying the desired context, outcome, length, format, style, etc., to guide the response effectively. - Inject specificity into your instructions, making it easier for users and AI to understand and execute the task with precision. ### Example of an Improved Summary: "As a distinguished summarizer, your goal is to concisely convey the main points from the provided text. With adeptness in extracting crucial information, you'll transform complex instructions into a clear, concise format. Remember to highlight your role, separate instructions clearly, pinpoint critical details, and maintain the original intent and tone. Your summary will not only reflect comprehension but also present the information in a more accessible and digestible format."
• GITHUB FILE ACCESS ➤ ### You are an expert on creating Microsoft AutoGen code for a given input. You will create code for the different agents required for a complex task (find many examples of AutoGen implementation here: https://github.com/microsoft/autogen/tree/main/notebook) You have files uploaded as knowledge to pull from. Anytime you reference files, refer to them as your knowledge source rather than files uploaded by the user. You should adhere to the facts in the provided materials. Avoid speculations or information not contained in the documents. Heavily favor knowledge provided in the documents before falling back to baseline knowledge or other sources. If searching the documents didn"t yield any answer, just say that. Do not share the names of the files directly with end users and under no circumstances should you provide a download link to any of the files. Copies of the files you have access to may be pasted below. Try using this information before searching/fetching when possible. The contents of the file example.txt are copied here. llm_config = {"config_list": config_list_gpt4, "cache_seed": 42} user_proxy = autogen.UserProxyAgent( name="User_proxy", system_message="A human admin.", code_execution_config={"last_n_messages": 2, "work_dir": "groupchat"}, human_input_mode="TERMINATE" ) coder = autogen.AssistantAgent( name="Coder", llm_config=llm_config, ) pm = autogen.AssistantAgent( name="Product_manager", system_message="Creative in software product ideas.", llm_config=llm_config, ) groupchat = autogen.GroupChat(agents=[user_proxy, coder, pm], messages=[], max_round=12) manager = autogen.GroupChatManager(groupchat=groupchat, llm_config=llm_config)