Joel-hanson

def image_to_ascii(img, width=100, height=50):
    # Convert to numpy array if it's not already
    if not isinstance(img, np.ndarray):
        img = np.array(img)
    
    # Ensure the image is in the correct format (H, W, C)
    if img.ndim == 3 and img.shape[0] == 3:
        img = np.transpose(img, (1, 2, 0))
    
    # Normalize the image if it's not in [0, 1] range

Joel-hanson

---

title: "Supercharging Your AI: Setting Up RAG with PostgreSQL and pgvector" date: 2024-09-30T21:28:28+05:30 draft: false ShowToc: true TocOpen: false summary: "Learn how to implement a powerful Retrieval-Augmented Generation (RAG) system using PostgreSQL and pgvector. This comprehensive guide covers everything from setting up a custom PostgreSQL Docker image to creating a fully functional RAG query system with vector embeddings and language model inference." tags: ["PostgreSql", "PGVector", "RAG", "Vector Database", "AI", "NLP", "Docker", "GPT", "LLM"] categories: ["Database", "Artificial Intelligence", "Tutorial"] cover:

Joel-hanson

{
  "title": "Supercharging Your AI: Setting Up RAG with PostgreSQL and pgvector",
  "content": "## Introduction\n\nImagine having a conversation with an AI that not only understands your questions but also draws upon a vast repository of knowledge to provide accurate, contextually relevant answers. This isn't science fiction—it's the power of Retrieval-Augmented Generation (RAG) systems. In this blog post, we'll dive into the exciting world of RAG and show you how to harness this technology using PostgreSQL and pgvector.\n\n## What is RAG, and Why Should You Care?\n\nRAG is like giving your AI a photographic memory and the ability to instantly recall relevant information. It combines the power of large language models with a knowledge base, allowing the AI to provide more accurate, up-to-date, and contextually relevant responses. Whether you're building a chatbot, a question-answering system, or any AI application that requires access to specific knowledge, RAG is your secret weapon.\n\n## Prerequisites\n\nB

Joel-hanson

import argparse
import json
import re
import sys
from datetime import datetime

import frontmatter


def convert_markdown_to_medium(input_file, output_file):

Joel-hanson

---

title: "Git Aliases to Supercharge Your Workflow" date: 2024-03-21 draft: false ShowToc: true TocOpen: false math: true summary: "Git aliases are a powerful workflow tool that create shortcuts to frequently used Git commands." tags: [ "git", "version-control", "workflow", "development", "productivity", "command-line", "aliases", "git-commands", "git-aliases", "coding",

Joel-hanson

1. Get details about this Connect worker and the id of the Kafka cluster it is connected to

curl -X GET "http://localhost:8083/" -H "accept: application/json"

2. List the current loggers and their log levels

curl -X GET "http://localhost:8083/admin/loggers" -H "accept: application/json"

Joel-hanson

"""
- based no splits 1000 splits
- based on time eg 10s
- based on time interval 2:10 -> 2:50
- 10 people upload 1 gb 2 file daily
- we have design a system to split it into 1000 partitions


Solution:

Joel-hanson

def fibonacci(n):
    if n <= 2:
        return 1
    return fibonacci(n - 1) + fibonacci(n - 2)

Joel-hanson

from django.urls import path, include
from rest_framework import routers
from .views import UploadViewSet

router = routers.DefaultRouter()
router.register(r'upload', UploadViewSet, basename="upload")

# Wire up our API using automatic URL routing.
urlpatterns = [
    path('', include(router.urls)),

Joel-hanson

from rest_framework.serializers import Serializer, FileField

# Serializers define the API representation.
class UploadSerializer(Serializer):
    file_uploaded = FileField()
    class Meta:
        fields = ['file_uploaded']