aimclub/ProtoLLM
Framework for prototyping of LLM-based applications
Supports RAG pipelines with multi-database and web service integration, ensemble methods for combining multiple LLMs, structured output generation, and synthetic data generation with evolutionary optimization. Provides a plugin architecture for integrating external services and AutoML solutions, with native support for diverse LLM providers (GigaChat, YandexGPT, OpenRouter) alongside locally-deployed open-source models. Includes separate API and SDK packages for production deployment alongside the core prototyping framework.
Available on PyPI.
Stars
24
Forks
11
Language
Python
License
BSD-3-Clause
Category
Last pushed
Oct 24, 2025
Monthly downloads
982
Commits (30d)
0
Dependencies
47
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/aimclub/ProtoLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
llmware-ai/llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
Sinapsis-AI/sinapsis-chatbots
Monorepo for sinapsis templates supporting LLM based Agents
Azure-Samples/azureai-foundry-finetuning-raft
A recipe that will walk you through using either Meta Llama 3.1 405B or OpenAI GPT-4o deployed...
pkargupta/taxoadapt
Dynamically constructs and adapts an LLM-generated taxonomy to a given corpus across multiple dimensions.
xi029/Qwen3-VL-MoeLORA
在千问最新的多模态image-text模型Qwen3-VL-4B-Instruct 进行多种lora微调对比效果，通过langchain+RAG+多智能体(Multi-Agent)进行部署