gitea/infio-copilot
1
0
Fork 0
mirror of https://github.com/EthanMarti/infio-copilot.git synced 2026-05-09 16:38:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

update trans

Browse Source
This commit is contained in:
duanfuxiang
2025-07-03 09:03:00 +08:00
parent 98bc810b86
commit a269258353
11 changed files with 2679 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/core/prompts/transformations/dense-summary.ts
View File

@@ -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";