barun-saha — AI Stack & LLM Providers

AI Sophistication

50%

Basic API

Direct LLM API calls

Frameworks

Using LLM frameworks (LangChain, etc.)

Embeddings

Embedding models for semantic search

RAG

Retrieval-augmented generation with vector stores

Agents

Autonomous agent frameworks

Multi-Provider

Using 3+ LLM providers

Architecture Overview

LLM Providers

HuggingFaceGoogleCohere

Models

llama-3.3-70bgemini-2.5-pro

Provider Usage Across Repos

Google3 repos

rag2richgemini_senpaisys2doc

HuggingFace1 repo

slide-deck-ai

Cohere1 repo

Model Diversity

3 models

Barun Saha