Vladimir Blagojevic Claim this profile

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Automatically generate comprehensive Pull Request descriptions with LLMs

Convert and invoke OpenAPI specifications as LLM tool/function definitions

No description.

Enables LLM integration with OpenAPI-defined services through function-calling JSON

Automatically generate Reno release notes for your pull requests using LLMs

A flexible Haystack 2.0 pipeline integrating Retrieval-Augmented Generation (RAG) with any OpenAPI service

No description.

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

👩🏻‍🍳 A collection of example notebooks

MCP server that calculates optimal routes between multiple POIs using Google Routing Maps APIs.

Update Pull Request Description

GitHub Action to create or update a Reno release note for a pull request

Finds Reno release note in pull requests

A Python package that creates default objects from a JSON schema

[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

Infinispan is an open source data grid platform and highly scalable NoSQL cloud data store.

Notebooks to demonstrate ART (Agent Reinforcement Trainer) in practice!

No description.

Huggingface Transformers + Adapters = ❤️

Training setup for Langchain's Open Deep Research

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

sharing current agents in use

A Python3 OpenAPI 3 Spec Parser

No description.

🧪 Experimental features for Haystack

No description.

An integration of Qdrant ANN vector database backend with Haystack

Code for Stanford CS224u

Weaviate is a cloud-native, modular, real-time vector search engine

Train transformer language models with reinforcement learning.

No description.

🔌 A central repository collecting pre-trained adapter modules

Repo for the Deep Reinforcement Learning Nanodegree program