This template is designed to help you reflect on your past week, plan for the upcoming week, and align your activities with your broader life themes and goals. It's structured to encourage thoughtful consideration of your personal and professional development.
To begin, review your recent retrospectives to understand your progress and patterns over time.
| Consideration | RAG | Fine-Tuning | Notes |
|---|---|---|---|
| Data Requirements | Less reliant on domain-specific training data | Requires substantial domain-specific training data | RAG adapts easily to new data; fine-tuning is best for stable knowledge bases. |
| Model Adaptability | More flexible to new, unseen data | Less flexible, tailored to the training data | RAG |
| def generateParityBits(data): | |
| """ | |
| Generates parity bits for the given 4-bit data. | |
| """ | |
| p1 = data[0] ^ data[1] ^ data[3] | |
| p2 = data[0] ^ data[2] ^ data[3] | |
| p3 = data[1] ^ data[2] ^ data[3] | |
| return p1, p2, p3 | |
| def encodeHamming(data): |
| Skill | Level | Notes |
|---|---|---|
| Ruby | Basic | |
| React, Typescript, Tailwind | Expert | |
| ReScript | Not familiar | |
| Rust | Advanced | Love it! |
| PostgreSQL | Advanced | Used many times in production, did a lot of optimization |
| { | |
| "dependencies": { | |
| "@llama-node/llama-cpp": "^0.0.32", | |
| "llama-node": "^0.0.32" | |
| }, | |
| "devDependencies": { | |
| "@types/node": "^18.16.3" | |
| } | |
| } |
| #[cfg(test)] | |
| mod tests { | |
| use std::sync::Arc; | |
| use crate::{ | |
| assistants::{ | |
| create_assistant_handler, delete_assistant_handler, get_assistant_handler, | |
| list_assistants_handler, update_assistant_handler, | |
| }, | |
| messages::{ |
At the moment, you need both Docker installed to run the API.
Additionally, Assistants currently supports Anthropic and Open Source LLMs, you need some env vars that you can put in a .env file in the root of the project:
DATABASE_URL=postgres://postgres:secret@localhost:5432/mydatabase
REDIS_URL=redis://127.0.0.1/
S3_ENDPOINT=http://localhost:9000