codebrain001

{"conversationTurns":[{"prompt":{"content":[{"text":"What are the three core layers required to build an LLM-based application?"}]},"referenceResponses":[{"content":[{"text":"A large-language model, a vector database to hold the embeddings, and a search / retrieval layer."}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"What does Deepchecks’ continuous evaluation for LLMs involve, and how does it work?"}]},"referenceResponses":[{"content":[{"text":"Deepchecks automatically extracts a rich set of ‘properties’ (e.g., relevance, grounding, toxicity, formatting) from every interaction, applies rule-based guard-rails to turn those properties into a pass/fail label, and tracks the resulting scores across versions and in production so teams can spot regressions and monitor quality in real time."}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"What are the common failure modes of RAG systems, and why do they occur?"}]},"referenceResponses":[{"content":[{"text":"• User-level: edge-case queries 

codebrain001

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts and experience preferred (super rare at this point).

My own notes from a few months back.

Background

• Survey of LLMS
• Self-attention and transformer networks

codebrain001

# USAGE
# python train_mask_detector.py --dataset dataset

# import the necessary packages
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras.layers import AveragePooling2D
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense

codebrain001

def get_facenet_masknet():
    
    ap = argparse.ArgumentParser()
    ap.add_argument("-f", "--face", type=str,
                    default="face_detector",
                    help="path to face detector model directory")
    ap.add_argument("-m", "--model", type=str,
                    default="mask_detector.model",
                    help="path to trained face mask detector model")
    ap.add_argument("-c", "--confidence", type=float, default=0.5,

codebrain001

from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import argparse
import imutils
import time
import cv2
import os

codebrain001

# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import argparse
import imutils
import time
import cv2

codebrain001

# Importing the Tello Drone Library
from djitellopy import Tello
# Importing OpenCV library
import cv2
# Importing time package
import time
# Importing OS module
import os

# Instatiating the Tello module

codebrain001

class Drone:

    """Wrapper class to setup the tello drone"""

    def __init__(self, width, height):
        self.StartCounter = 0
        self.width = width
        self.height = height
        self.back_velocity = 0
        self.left_right_velocity = 0

codebrain001

codebrain001