Intro to Large Language Models
Author(s): cai zhang Originally published on Towards AI. Image from Andrej Karpathy’s YouTube video PS: This writing is from the Andrej Karpathy’s channel that is “Intro to Large Language Models”. If you would prefer to watch video, you can watch it by …
3 Powerful AutoGen Features You Must Know
Author(s): Sayanteka Chakraborty Originally published on Towards AI. 3 Powerful AutoGen Features You Must Know One of the most exciting features of AutoGen is its ability to generate, execute, and verify code automatically using conversational AI agents. AutoGen Features OverviewThe article discusses …
10 Perplexity Comet Agents to Automate Your Work in the Browser
Author(s): Shauvik Kumar Originally published on Towards AI. 10 Perplexity Comet Agents to Automate Your Work in the Browser You do not need yet another AI tool. You need a set of browser-native agents that reduce context switching. You need fast answers …
Beyond Basic RAG: A Practical Guide to Advanced Indexing Techniques
Author(s): Saif Ali Kheraj Originally published on Towards AI. https://en.wikipedia.org/wiki/Retrieval-augmented_generation#/media/File:RAG_diagram.svg Retrieval Augmented Generation (RAG) has become the go to approach for building AI systems that can access and reason over large document collections. But here is the reality most developers face: basic …
GANs: How AI Creates Images from Noise
Author(s): Aditya Gupta Originally published on Towards AI. We all love pranks right. Think of a friend that you like to prank. The first time you prank them it works, you get a few laughs and maybe they get annoyed. The next …
“Smart Hiring with GenAI: Evaluating Leadership and Cultural Fit”
Author(s): Alok Lamech Originally published on Towards AI. Smart Hiring with GenAI: Evaluating Leadership and Cultural Fit “Imagine a panel interviewing a candidate for a senior product role. The candidate shares a story about resolving team conflict. Using the GenAI tool, the …
Converting Unstructured data into Neo4j Graphs for GraphRAG
Author(s): Krishna Kumar S Originally published on Towards AI. TL;DR The LLM (Gemini) is used with structured output via ChatGoogleGenerativeAI.with_structured_output(...) to directly return validated Pydantic objects from text files containing plans data. The pipeline then writes the cleaned records into Neo4j. Source: …
IBM’s Granite-4.0 Fine-Tuning Made Simple: Create Custom AI Models with Python and Unsloth
Author(s): Krishan Walia Originally published on Towards AI. Granite-4.0 could be the model you have been looking for. Learn to fine-tune it for all your needs! That’s exactly what fine-tuning does. Instead of forcing a general-purpose model to fit every scenario, fine-tuning …
The $200 AI Browser That Freaked Out Google Is Now Free — Here’s Why It Matters
Author(s): Muhammad Saeed Originally published on Towards AI. Perplexity’s Comet isn’t just another browser. It’s a bold, aggressive play to redefine our relationship with the internet, and it represents the first real existential threat to Google’s search empire. Introduction: The Shot Heard …
Unifying Indian Mobile & Internet Plans with AI and Graph Databases — (Production-ready, Gemini structured outputs)
Author(s): Krishna Kumar S Originally published on Towards AI. TL;DR The LLM (Gemini) is used with structured output via ChatGoogleGenerativeAI.with_structured_output(...) to directly return validated Pydantic objects from text files containing plans data. The pipeline then writes the cleaned records into Neo4j. Source: …
Recent Posts
