Clelia Astra Bertelli's picture

Clelia Astra Bertelli

as-cle-bert

AI & ML interests

Biology + Artificial Intelligence = โค๏ธ | AI for sustainable development, sustainable development for AI | Researching on Machine Learning Enhancement | I love automation for everyday things | Blogger | Open Source

Recent Activity

posted an update 2 days ago
๐‘๐€๐†๐œ๐จ๐จ๐ง๐Ÿฆ - ๐€๐ ๐ž๐ง๐ญ๐ข๐œ ๐‘๐€๐† ๐ญ๐จ ๐ก๐ž๐ฅ๐ฉ ๐ฒ๐จ๐ฎ ๐›๐ฎ๐ข๐ฅ๐ ๐ฒ๐จ๐ฎ๐ซ ๐ฌ๐ญ๐š๐ซ๐ญ๐ฎ๐ฉ GitHub ๐Ÿ‘‰ https://github.com/AstraBert/ragcoon Are you building a startup and you're stuck in the process, trying to navigate hundreds of resources, suggestions and LinkedIn posts?๐Ÿ˜ถโ€๐ŸŒซ๏ธ Well, fear no more, because ๐—ฅ๐—”๐—š๐—ฐ๐—ผ๐—ผ๐—ป๐Ÿฆ is here to do some of the job for you: ๐Ÿ“ƒ It's built on free resources written by successful founders โš™๏ธ It performs complex retrieval operations, exploiting "vanilla" hybrid search, query expansion with an ๐—ต๐˜†๐—ฝ๐—ผ๐˜๐—ต๐—ฒ๐˜๐—ถ๐—ฐ๐—ฎ๐—น ๐—ฑ๐—ผ๐—ฐ๐˜‚๐—บ๐—ฒ๐—ป๐˜ approach and ๐—บ๐˜‚๐—น๐˜๐—ถ-๐˜€๐˜๐—ฒ๐—ฝ ๐—พ๐˜‚๐—ฒ๐—ฟ๐˜† ๐—ฑ๐—ฒ๐—ฐ๐—ผ๐—บ๐—ฝ๐—ผ๐˜€๐—ถ๐˜๐—ถ๐—ผ๐—ป ๐Ÿ“Š It evaluates the ๐—ฟ๐—ฒ๐—น๐—ถ๐—ฎ๐—ฏ๐—ถ๐—น๐—ถ๐˜๐˜† of the retrieved context, and the ๐—ฟ๐—ฒ๐—น๐—ฒ๐˜ƒ๐—ฎ๐—ป๐—ฐ๐˜† and ๐—ณ๐—ฎ๐—ถ๐˜๐—ต๐—ณ๐˜‚๐—น๐—ป๐—ฒ๐˜€๐˜€ of its own responses, in an auto-correction effort RAGcoon๐Ÿฆ is ๐—ผ๐—ฝ๐—ฒ๐—ป-๐˜€๐—ผ๐˜‚๐—ฟ๐—ฐ๐—ฒ and relies on easy-to-use components: ๐Ÿ”นLlamaIndex is at the core of the agent architecture, provisions the integrations with language models and vector database services, and performs evaluations ๐Ÿ”น Qdrant is your go-to, versatile and scalable companion for vector database services ๐Ÿ”นGroq provides lightning-fast LLM inference to support the agent, giving it the full power of ๐—ค๐˜„๐—ค-๐Ÿฏ๐Ÿฎ๐—• by Qwen ๐Ÿ”นHugging Face provides the embedding models used for dense and sparse retrieval ๐Ÿ”นFastAPI wraps the whole backend into an API interface ๐Ÿ”น๐— ๐—ฒ๐˜€๐—ผ๐—ฝ by Google is used to serve the application frontend RAGcoon๐Ÿฆ can be spinned up locally - it's ๐——๐—ผ๐—ฐ๐—ธ๐—ฒ๐—ฟ-๐—ฟ๐—ฒ๐—ฎ๐—ฑ๐˜†๐Ÿ‹, and you can find the whole code to reproduce it on GitHub ๐Ÿ‘‰ https://github.com/AstraBert/ragcoon But there might be room for an online version of RAGcoon๐Ÿฆ: let me know if you would use it - we can connect and build it together!๐Ÿš€
posted an update 7 days ago
I just released a fully automated evaluation framework for your RAG applications!๐Ÿ“ˆ GitHub ๐Ÿ‘‰ https://github.com/AstraBert/diRAGnosis PyPi ๐Ÿ‘‰ https://pypi.org/project/diragnosis/ It's called ๐๐ข๐‘๐€๐†๐ง๐จ๐ฌ๐ข๐ฌ and is a lightweight framework that helps you ๐—ฑ๐—ถ๐—ฎ๐—ด๐—ป๐—ผ๐˜€๐—ฒ ๐˜๐—ต๐—ฒ ๐—ฝ๐—ฒ๐—ฟ๐—ณ๐—ผ๐—ฟ๐—บ๐—ฎ๐—ป๐—ฐ๐—ฒ ๐—ผ๐—ณ ๐—Ÿ๐—Ÿ๐— ๐˜€ ๐—ฎ๐—ป๐—ฑ ๐—ฟ๐—ฒ๐˜๐—ฟ๐—ถ๐—ฒ๐˜ƒ๐—ฎ๐—น ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€ ๐—ถ๐—ป ๐—ฅ๐—”๐—š ๐—ฎ๐—ฝ๐—ฝ๐—น๐—ถ๐—ฐ๐—ฎ๐˜๐—ถ๐—ผ๐—ป๐˜€. You can launch it as an application locally (it's Docker-ready!๐Ÿ‹) or, if you want more flexibility, you can integrate it in your code as a python package๐Ÿ“ฆ The workflow is simple: ๐Ÿง  You choose your favorite LLM provider and model (supported, for now, are Mistral AI, Groq, Anthropic, OpenAI and Cohere) ๐Ÿง  You pick the embedding models provider and the embedding model you prefer (supported, for now, are Mistral AI, Hugging Face, Cohere and OpenAI) ๐Ÿ“„ You prepare and provide your documents โš™๏ธ Documents are ingested into a Qdrant vector database and transformed into a synthetic question dataset with the help of LlamaIndex ๐Ÿ“Š The LLM is evaluated for the faithfulness and relevancy of its retrieval-augmented answer to the questions ๐Ÿ“Š The embedding model is evaluated for hit rate and mean reciprocal ranking (MRR) of the retrieved documents And the cool thing is that all of this is ๐—ถ๐—ป๐˜๐˜‚๐—ถ๐˜๐—ถ๐˜ƒ๐—ฒ ๐—ฎ๐—ป๐—ฑ ๐—ฐ๐—ผ๐—บ๐—ฝ๐—น๐—ฒ๐˜๐—ฒ๐—น๐˜† ๐—ฎ๐˜‚๐˜๐—ผ๐—บ๐—ฎ๐˜๐—ฒ๐—ฑ: you plug it in, and it works!๐Ÿ”Œโšก Even cooler? This is all built on top of LlamaIndex and its integrations: no need for tons of dependencies or fancy workarounds๐Ÿฆ™ And if you're a UI lover, Gradio and FastAPI are there to provide you a seamless backend-to-frontend experience๐Ÿ•ถ๏ธ So now it's your turn: you can either get diRAGnosis from GitHub ๐Ÿ‘‰ https://github.com/AstraBert/diRAGnosis or just run a quick and painless: ```bash uv pip install diragnosis ``` To get the package installed (lightning-fast) in your environment๐Ÿƒโ€โ™€๏ธ Have fun and feel free to leave feedback and feature/integrations requests on GitHub issuesโœจ
View all activity

Organizations

Social Post Explorers's profile picture Hugging Face Discord Community's profile picture GreenFit AI's profile picture

as-cle-bert's activity

New activity in as-cle-bert/pdfitdown 3 days ago

Update requirements.txt

1
#1 opened 3 days ago by
not-lain
New activity in bluesky-community/README 4 months ago

Ideas!

2
#1 opened 4 months ago by
davanstrien
New activity in as-cle-bert/Llama-3.1-405B-FP8 8 months ago

why

1
#1 opened 8 months ago by
YaserDS-777
New activity in huggingchat/chat-ui 11 months ago

[ASSISTANTS] Community thread

187
#356 opened about 1 year ago by
victor
New activity in as-cle-bert/plastic-enzymes 12 months ago
New activity in as-cle-bert/genetics-arxiv-wiki 12 months ago
New activity in as-cle-bert/VirBiCla-training 12 months ago