Andrej Baranovskij | Poke

Andrej Baranovskij @UCqSX0Z20QCEE7tZKaQ4pS3Q@youtube.com

5.8K subscribers - no pronouns :c

Useful tips & tricks about Machine Learning and Web developm

Videos Playlists

Recently Uploaded Popular Oldest

Document Querying with Qwen2-VL-7B and JSON Output

Qwen2-VL-7B for Data Extraction and Structured JSON Output

Sparrow Parse: Table Data Extraction with Table Transformer and OCR

Table Header Extraction with Table Transformer

Invoice Table Detection with Table Transformer

Sparrow OCR Service with PaddleOCR

FastAPI Endpoint for Sparrow LLM Agent

Sparrow Parse API for PDF Invoice Data Extraction

Avoid LLM Hallucinations: Use Sparrow Parse for Tabular PDF Data, Instructor LLM for Forms

Effective Table Data Extraction from PDF without LLM

Instructor and Ollama for Invoice Data Extraction in Sparrow [LLM, JSON]

Hybrid RAG with Sparrow Parse

Sparrow Parse - Data Processing for LLM

Invoice Data Preprocessing for LLM

You Don't Need RAG to Extract Invoice Data

LLM JSON Output with Instructor RAG and WizardLM-2

Local RAG Explained with Unstructured and LangChain

Local LLM RAG with Unstructured and LangChain [Structured JSON]

LlamaIndex Upgrade to 0.10.x Experience

LLM Structured Output for Function Calling with Ollama

FastAPI File Upload and Temporary Directory for Stateless API

Optimizing Receipt Processing with LlamaIndex and PaddleOCR

LlamaIndex Multimodal with Ollama [Local LLM]

LLM Agents with Sparrow

Extracting Invoice Structured Output with Haystack and Ollama Local LLM

Local LLM RAG Pipelines with Sparrow Plugins [Python Interface]

LLM Structured Output with Local Haystack RAG and Ollama

JSON Output with Notus Local LLM [LlamaIndex, Ollama, Weaviate]

FastAPI and LlamaIndex RAG: Creating Efficient APIs

Transforming Invoice Data into JSON: Local LLM with LlamaIndex & Pydantic

From Text to Vectors: Leveraging Weaviate for local RAG Implementation with LlamaIndex

Enhancing RAG: LlamaIndex and Ollama for On-Premise Data Extraction

Secure and Private: On-Premise Invoice Processing with LangChain and Ollama RAG

Easy-to-Follow RAG Pipeline Tutorial: Invoice Processing with ChromaDB & LangChain

Vector Database Impact on RAG Efficiency: A Simple Overview

JSON Output from Mistral 7B LLM [LangChain, Ctransformers]

Structured JSON Output from LLM RAG on Local CPU [Weaviate, Llama.cpp, Haystack]

Invoice Data Processing with Llama2 13B LLM RAG on Local CPU [Weaviate, Llama.cpp, Haystack]

Invoice Data Processing with Mistral LLM on Local CPU

Skipper MLOps Debugging and Development on Your Local Machine

Pros and Cons of Developing Your Own ChatGPT Plugin

LLama 2 LLM for PDF Invoice Data Extraction

Data Filtering and Aggregation with Receipt Assistant Plugin for ChatGPT

Computer Vision with ChatGPT - Receipt Assistant Plugin

How to Host FastAPI from Your Computer with ngrok

ChatGPT Plugin OAuth with Logto

Deploy Local ML Apps with Ngrok

ChatGPT Plugin Backend with FastAPI

ChatGPT Plugin with Persistent Storage

FastAPI, Pydantic and MongoDB for Beginners

File Upload App for ChatGPT

Building Your Own ChatGPT Plugin

PaddleOCR as a Service with FastAPI

ChatGPT/GPT-4 for Receipt OCR Data Analysis

Document AI: How To Convert Colab ML Notebook Into FastAPI App

Speeding Up FastAPI App with Background Tasks

Optimizing FastAPI for Concurrent Users when Running Hugging Face ML Models

Optimizing ML Model Loading Time Using LRU Cache in FastAPI 📈

Efficient Document Data Extraction with Sparrow UI: Streamlit, FastAPI, and Hugging Face's Donut ML

Deploying FastAPI Applications to Hugging Face Spaces