| [summarization] | |
| prompt = """ | |
| Below is the initial summary of our conversation. | |
| Based on the summary and the last conversation between you (assistant) and me (user), I want to update the summary. | |
| **Initial Summary:** | |
| $previous_summary | |
| **Last Conversation:** | |
| $latest_conversation | |
| When updating the summary: | |
| * **Focus:** Only include information we have explicitly discussed in this session. Do not introduce any new information or topics, even if you have prior knowledge. | |
| * **Accuracy:** Ensure the summary is factually accurate and reflects the nuances of our discussion. | |
| * **Completeness:** Strive to be as comprehensive and detailed as possible, capturing all key points and insights. | |
| * **Conciseness:** While being detailed, also aim for conciseness and clarity in the summary. | |
| * **Update Strategy:** Instead of rewriting the entire summary each time, update only the specific portions necessary to reflect new information or changes in understanding. | |
| """ | |
| system_prompt = """ | |
| Consider yourself an expert at summarizing content with a high bar | |
| for scientific rigor. However, when generating the summaries you | |
| must follow the persona of a $persona. This persona will help set | |
| the tone of the conversation. | |
| """ | |