150 lines
2.4 KiB
YAML
150 lines
2.4 KiB
YAML
# Deep Dive Relevance Keywords
|
|
# Define keywords and their weights for scoring entries
|
|
|
|
# Weight tiers: High (3.0x), Medium (1.5x), Low (0.5x)
|
|
weights:
|
|
high: 3.0
|
|
medium: 1.5
|
|
low: 0.5
|
|
|
|
# High-priority keywords (critical to Hermes/Timmy work)
|
|
high:
|
|
# Framework specific
|
|
- hermes
|
|
- timmy
|
|
- timmy foundation
|
|
- langchain
|
|
- langgraph
|
|
- crewai
|
|
- autogen
|
|
- autogpt
|
|
- babyagi
|
|
|
|
# Agent concepts
|
|
- llm agent
|
|
- llm agents
|
|
- agent framework
|
|
- agent frameworks
|
|
- multi-agent
|
|
- multi agent
|
|
- agent orchestration
|
|
- agentic
|
|
- agentic workflow
|
|
- agent system
|
|
|
|
# Tool use
|
|
- tool use
|
|
- tool calling
|
|
- function calling
|
|
- mcp
|
|
- model context protocol
|
|
- toolformer
|
|
- gorilla
|
|
|
|
# Reasoning
|
|
- chain-of-thought
|
|
- chain of thought
|
|
- reasoning
|
|
- planning
|
|
- reflection
|
|
- self-reflection
|
|
|
|
# RL and training
|
|
- reinforcement learning
|
|
- RLHF
|
|
- DPO
|
|
- GRPO
|
|
- PPO
|
|
- preference optimization
|
|
- alignment
|
|
|
|
# Fine tuning
|
|
- fine-tuning
|
|
- finetuning
|
|
- instruction tuning
|
|
- supervised fine-tuning
|
|
- sft
|
|
- peft
|
|
- lora
|
|
|
|
# Safety
|
|
- ai safety
|
|
- constitutional ai
|
|
- red teaming
|
|
- adversarial
|
|
|
|
# Medium-priority keywords (relevant to AI work)
|
|
medium:
|
|
# Core concepts
|
|
- llm
|
|
- large language model
|
|
- foundation model
|
|
- transformer
|
|
- attention mechanism
|
|
- prompting
|
|
- prompt engineering
|
|
- few-shot
|
|
- zero-shot
|
|
- in-context learning
|
|
|
|
# Architecture
|
|
- mixture of experts
|
|
- MoE
|
|
- retrieval augmented generation
|
|
- RAG
|
|
- vector database
|
|
- embeddings
|
|
- semantic search
|
|
|
|
# Inference
|
|
- inference optimization
|
|
- quantization
|
|
- model distillation
|
|
- knowledge distillation
|
|
- KV cache
|
|
- speculative decoding
|
|
- vLLM
|
|
|
|
# Open research
|
|
- open source
|
|
- open weight
|
|
- llama
|
|
- mistral
|
|
- qwen
|
|
- deepseek
|
|
|
|
# Companies
|
|
- openai
|
|
- anthropic
|
|
- claude
|
|
- gpt
|
|
- gemini
|
|
- deepmind
|
|
- google ai
|
|
|
|
# Low-priority keywords (general AI)
|
|
low:
|
|
- artificial intelligence
|
|
- machine learning
|
|
- deep learning
|
|
- neural network
|
|
- natural language processing
|
|
- NLP
|
|
- computer vision
|
|
|
|
# Source-specific bonuses (points added based on source)
|
|
source_bonuses:
|
|
arxiv_ai: 0.5
|
|
arxiv_cl: 0.5
|
|
arxiv_lg: 0.5
|
|
openai_blog: 0.3
|
|
anthropic_news: 0.4
|
|
deepmind_news: 0.3
|
|
|
|
# Filter settings
|
|
filter:
|
|
min_relevance_score: 2.0
|
|
max_entries_per_briefing: 15
|
|
embedding_model: "all-MiniLM-L6-v2"
|
|
use_embeddings: true
|