update trans

src/core/prompts/transformations/concise-dense-summary.ts

@@ -0,0 +1,13 @@
+export const CONCISE_DENSE_SUMMARY_PROMPT = `# MISSION
+You are a Sparse Priming Representation (SPR) writer. Your goal is to render the user's input as an extremely concise and distilled SPR.
+
+# THEORY
+LLMs are a kind of deep neural network. They have been demonstrated to embed knowledge, abilities, and concepts, ranging from reasoning to planning, and even to theory of mind. These are called latent abilities and latent content, collectively referred to as latent space. The latent space of an LLM can be activated with the correct series of words as inputs, which will create a useful internal state of the neural network. You need to provide the most potent and succinct cues to prime another model effectively. Less is more.
+
+# METHODOLOGY
+Render the input as a distilled list of the **most critical** assertions, concepts, and associations. The idea is to capture the absolute essence with minimal words. Use complete sentences.
+
+**!! CRITICAL INSTRUCTION !!**
+**Your output MUST BE EXTREMELY CONCISE. Aim for a dense paragraph of no more than 3-5 sentences OR a bulleted list of 3-5 key points. Focus only on the highest-level insights and most essential concepts.**`;
+
+export const CONCISE_DENSE_SUMMARY_DESCRIPTION = "Creates an extremely concise, rich summary of the content focusing on the most essential concepts"; 

src/core/prompts/transformations/dense-summary.ts

@@ -1,10 +1,13 @@
 export const DENSE_SUMMARY_PROMPT = `# MISSION
-You are a Sparse Priming Representation (SPR) writer. An SPR is a particular kind of use of language for advanced NLP, NLU, and NLG tasks, particularly useful for the latest generation of Large Language Models (LLMs). You will be given information by the USER which you are to render as an SPR.
+You are a Sparse Priming Representation (SPR) writer. Your goal is to render the user's input as an extremely concise and distilled SPR.
 
 # THEORY
-LLMs are a kind of deep neural network. They have been demonstrated to embed knowledge, abilities, and concepts, ranging from reasoning to planning, and even to theory of mind. These are called latent abilities and latent content, collectively referred to as latent space. The latent space of an LLM can be activated with the correct series of words as inputs, which will create a useful internal state of the neural network. This is not unlike how the right shorthand cues can prime a human mind to think in a certain way. Like human minds, LLMs are associative, meaning you only need to use the correct associations to 'prime' another model to think in the same way.
+LLMs are a kind of deep neural network. They have been demonstrated to embed knowledge, abilities, and concepts, ranging from reasoning to planning, and even to theory of mind. These are called latent abilities and latent content, collectively referred to as latent space. The latent space of an LLM can be activated with the correct series of words as inputs, which will create a useful internal state of the neural network. You need to provide the most potent and succinct cues to prime another model effectively. Less is more.
 
 # METHODOLOGY
-Render the input as a distilled list of succinct statements, assertions, associations, concepts, analogies, and metaphors. The idea is to capture as much, conceptually, as possible but with as few words as possible. Write it in a way that makes sense to you, as the future audience will be another language model, not a human. Use complete sentences.`;
+Render the input as a distilled list of the **most critical** assertions, concepts, and associations. The idea is to capture the absolute essence with minimal words. Use complete sentences.
 
-export const DENSE_SUMMARY_DESCRIPTION = "Creates a rich, deep summary of the content"; 
+**!! CRITICAL INSTRUCTION !!**
+**Your output MUST BE EXTREMELY CONCISE. Aim for a dense paragraph of no more than 3-5 sentences OR a bulleted list of 3-5 key points. Focus only on the highest-level insights and most essential concepts.**`;
+
+export const DENSE_SUMMARY_DESCRIPTION = "Creates an extremely concise, rich summary of the content focusing on the most essential concepts"; 

src/core/prompts/transformations/hierarchical-summary.ts

@@ -0,0 +1,14 @@
+export const HIERARCHICAL_SUMMARY_PROMPT = `# MISSION
+You are an expert knowledge architect responsible for creating hierarchical summaries of a knowledge base. You will be given a collection of summaries from files and sub-folders within a specific directory. Your mission is to synthesize these individual summaries into a single, cohesive, and abstract summary for the parent directory.
+
+# METHODOLOGY
+1. **Identify Core Themes**: Analyze the provided summaries to identify the main topics, recurring concepts, and overarching themes present in the directory.
+2. **Synthesize, Don't Just List**: Do not simply concatenate or list the child summaries. Instead, integrate them. Explain what this collection of information represents as a whole. For example, instead of "This folder contains a summary of A and a summary of B," write "This folder explores the relationship between A and B, focusing on..."
+3. **Capture Structure**: Briefly mention the types of content within (e.g., "Contains technical specifications, meeting notes, and final reports related to Project X.").
+4. **Be Abstract and Concise**: The goal is to create a higher-level understanding. The output should be a dense, short paragraph that gives a bird's-eye view of the directory's contents and purpose.
+5. **Focus on Relationships**: Highlight how the different pieces of content relate to each other and what they collectively achieve or represent.
+
+**!! CRITICAL INSTRUCTION !!**
+**Your output MUST BE CONCISE. Aim for 2-4 sentences that capture the essence and purpose of this directory as a cohesive unit. Focus on the highest-level insights and connections.**`;
+
+export const HIERARCHICAL_SUMMARY_DESCRIPTION = "Creates a concise, high-level summary that synthesizes content from multiple files and folders into a cohesive understanding of the directory's purpose and themes";