Andrejus Baranovski

Subscribe to Andrejus Baranovski feed
Blog about Oracle, Full Stack, Machine Learning and Cloud
Updated: 58 min 57 sec ago

Structured Data Extraction with Sparrow Agent: Vision LLM & Prefect in Action

Mon, 2025-02-10 07:15
Discover how to streamline your data extraction process with Sparrow Agent! In this tutorial, I showcase how Sparrow Agent leverages Vision LLM to intelligently handle complex data tasks, while Prefect ensures every step is logged and monitored for maximum transparency and efficiency. Join me as I break down the process and share tips for optimizing your automated workflows. 

 

Building Web UI Apps with Python Gradio – A Java Developer’s Perspective

Tue, 2025-02-04 06:52
I explain building Web UI apps with Python Gradio framework. I used to work with Java in the past and was building enterprise Web UI apps with JSF. Based on this experience I can tell, Gradio is awesome framework for server side generated UI - it is easy to define UI components and control UI flow with event triggers.

 

Improving Qwen-VL Structured Output with Image Cropping

Tue, 2025-01-28 02:07
Explaining how I'm improving structured output results from Qwen-VL with image cropping in Sparrow.
 
 

Apple MLX Vision LLM Server with Ngrok, FastAPI and Sparrow

Mon, 2025-01-20 02:01
I show how I run Apple MLX backend on my local Mac Mini M4 Pro 64GB and access it from the Web through Ngrok, with automatically provisioned HTTPS certificate. 

 

Vision LLM Structured Output with Sparrow

Tue, 2025-01-14 06:06
I show how Sparrow UI Shell works with both image and PDF docs to process and extract structured data with Vision LLM (Qwen2) in the MLX backend. 

 

Stateless MLX Inference with FastAPI in Sparrow

Mon, 2024-12-23 08:11
I show how to run inference with MLX in stateless mode, when loaded model is released after inference completes. This is useful when inference requests are less frequent and it helps to reclaim resources reserved by MLX.

 

Streamlined Table Data Extraction with Sparrow | Table Transformer, Qwen2 VL, MLX, & Mac Mini M4 Pro

Tue, 2024-12-17 02:08
Learn how to streamline table data extraction with Sparrow, Table Transformer, Qwen2 VL, and MLX on the Mac Mini M4 Pro. Simplify your workflow and get accurate results! 

 

Structured Output from Multipage PDF with Sparrow (Qwen2 Vision LLM and MLX)

Mon, 2024-12-09 02:23
I explain how multipage PDFs are handled in Sparrow to extract structured data in a single call. 

 

Sparrow Apple MLX Backend on Mac Mini M4 (Qwen2 72B 4bit)

Tue, 2024-12-03 09:12
I show how I’m running the Qwen2 72B 4bit model locally on a Mac Mini M4 for Sparrow’s backend. MLX (and MLX-VLM) is the main platform I’m using for local data extraction in Sparrow. 

 

Batch Inference with Qwen2 Vision LLM (Sparrow)

Mon, 2024-11-25 02:38
I'm explaining several hints how to optimize Qwen2 Visual LLM performance for batch processing. 

 

Visual LLM Structured Output Validation with Sparrow

Sun, 2024-11-17 09:24
I explain how Sparrow validates the structured output of visual LLMs to ensure it complies with the JSON schema provided in the query. This process helps prevent errors and hallucinations generated by the LLM.

 

Extracting Financial Market Stock Data from Images with Vision LLM

Sun, 2024-11-10 09:01
In this video, I demonstrate how to extract financial market stock data from images using the powerful Vision LLM Qwen2, all within a Gradio interface. This setup allows quick and easy extraction of key stock stats from screenshots and other image-based data sources—perfect for analysts, traders, and finance enthusiasts looking to streamline data processing. Watch to see how this AI tool can simplify your workflow and make stock data analysis faster and more efficient! 

 

Structured Output Example with Sparrow UI Shell

Mon, 2024-11-04 00:52
Structured output is all you need. I deployed a Sparrow demo UI with Gradio to demonstrate the output Sparrow can produce by running a JSON schema query. You can see examples for the Bonds table, Lab results, and Bank statement. 

 

Qwen2-VL Performance Boost

Sun, 2024-10-20 08:29
I share performance-boosting tips based on my experience using Qwen2-VL in production. 

 

Sparrow Parse Vision LLM FastAPI Endpoint

Sun, 2024-10-13 14:20
Sparrow provides an API for accessing the Sparrow Parse agent, allowing you to run document extraction workflows directly from your existing systems. It helps simplify how data is pulled from documents and integrated into your workflows. 

 

Sparrow Parse Invoice Query with Vision LLM

Tue, 2024-10-08 03:30
New Sparrow Agent - Sparrow Parse, works with Qwen2 Vision LLM. 

What it does: 

1. Accepts query with JSON schema, this helps to solve few things at once - provides JSON structure for LLM to generate response, and hints LLM what types to use for each response element 

2. Runs inference on your GPU of choice, either cloud or local GPU 

3. Validates JSON response, based on query schema

Running Qwen2 Vision LLM on Hugging Face ZeroGPU API

Mon, 2024-09-30 07:38
Explaining my experience running Sparrow Parse with Qwen2 Vision LLM inference on Hugging Face ZeroGPU instance. 

 

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

Sun, 2024-09-15 13:30
In this video, I demonstrate how to perform document queries using Qwen2-VL-7B. By simplifying field names, we streamline the prompts, making them more efficient and reusable across different documents. This approach is similar to running SQL queries on a database, but tailored for language models like Qwen2-VL-7B, with results returned in JSON format. 

 

Table Parsing with Qwen2-VL-7B

Sun, 2024-09-08 14:00
I show how to retrieve structured JSON output from table image using Qwen2-VL-7B. This VLLM performs OCR and data mapping tasks all out of the box, also it can return structured JSON output without use of intermediate frameworks. 

 

Sparrow Parse: Table Data Extraction with Table Transformer and OCR

Sun, 2024-08-18 08:03
I explain how we extract data with Sparrow Parse, using Table Transformer to identify table area and build table structure to be processed by OCR. Sparrow Parse implements additional logic to clear-up and improve (removing noise, merging columns, adjusting rows) table structure generated by Table Transformer.

 

Pages