DEV Community: Amrendra N Mishra

RAG Pipeline from Scratch: Ask Your Documents Questions

Amrendra N Mishra — Sat, 01 Aug 2026 04:17:51 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Multi-Agent AI Systems: Build Without CrewAI or AutoGen

Amrendra N Mishra — Fri, 31 Jul 2026 04:19:35 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

How I Run 9 YouTube Channels Without Lifting a Finger

Amrendra N Mishra — Thu, 30 Jul 2026 03:53:10 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

5 Local AI Tools That Replace Expensive Cloud APIs

Amrendra N Mishra — Wed, 29 Jul 2026 04:08:52 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

The Zero Cost Tech Stack: Everything Free Everything Automated

Amrendra N Mishra — Tue, 28 Jul 2026 03:57:12 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Personal AI Assistant That Learns About You

Amrendra N Mishra — Mon, 27 Jul 2026 04:33:20 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

Auto-Documentation Generator for Any Code Repo

Amrendra N Mishra — Sun, 26 Jul 2026 04:23:07 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Knowledge Graph from Your Documents Using AI

Amrendra N Mishra — Sat, 25 Jul 2026 04:01:29 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

Habit Tracker with AI Coaching: My Daily System

Amrendra N Mishra — Fri, 24 Jul 2026 04:10:57 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Telegram Bot with Local AI: No API Costs

Amrendra N Mishra — Thu, 23 Jul 2026 04:11:48 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

Amazon Q in Production: 72 Percent Time Saved

Amrendra N Mishra — Wed, 22 Jul 2026 04:14:04 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Kafka Migration: 200 Percent Data Freshness Improvement

Amrendra N Mishra — Tue, 21 Jul 2026 04:12:39 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev