8.5
TFLOPS
Clelia Astra Bertelli
as-cle-bert
1127
followers
ยท
37 following
AI & ML interests
Biology + Artificial Intelligence = โค๏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
๐๐๐๐๐จ๐จ๐ง๐ฆ - ๐๐ ๐๐ง๐ญ๐ข๐ ๐๐๐ ๐ญ๐จ ๐ก๐๐ฅ๐ฉ ๐ฒ๐จ๐ฎ ๐๐ฎ๐ข๐ฅ๐ ๐ฒ๐จ๐ฎ๐ซ ๐ฌ๐ญ๐๐ซ๐ญ๐ฎ๐ฉ
GitHub ๐ 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?๐ถโ๐ซ๏ธ
Well, fear no more, because ๐ฅ๐๐๐ฐ๐ผ๐ผ๐ป๐ฆ is here to do some of the job for you:
๐ It's built on free resources written by successful founders
โ๏ธ It performs complex retrieval operations, exploiting "vanilla" hybrid search, query expansion with an ๐ต๐๐ฝ๐ผ๐๐ต๐ฒ๐๐ถ๐ฐ๐ฎ๐น ๐ฑ๐ผ๐ฐ๐๐บ๐ฒ๐ป๐ approach and ๐บ๐๐น๐๐ถ-๐๐๐ฒ๐ฝ ๐พ๐๐ฒ๐ฟ๐ ๐ฑ๐ฒ๐ฐ๐ผ๐บ๐ฝ๐ผ๐๐ถ๐๐ถ๐ผ๐ป
๐ It evaluates the ๐ฟ๐ฒ๐น๐ถ๐ฎ๐ฏ๐ถ๐น๐ถ๐๐ of the retrieved context, and the ๐ฟ๐ฒ๐น๐ฒ๐๐ฎ๐ป๐ฐ๐ and ๐ณ๐ฎ๐ถ๐๐ต๐ณ๐๐น๐ป๐ฒ๐๐ of its own responses, in an auto-correction effort
RAGcoon๐ฆ is ๐ผ๐ฝ๐ฒ๐ป-๐๐ผ๐๐ฟ๐ฐ๐ฒ and relies on easy-to-use components:
๐นLlamaIndex is at the core of the agent architecture, provisions the integrations with language models and vector database services, and performs evaluations
๐น Qdrant is your go-to, versatile and scalable companion for vector database services
๐นGroq provides lightning-fast LLM inference to support the agent, giving it the full power of ๐ค๐๐ค-๐ฏ๐ฎ๐ by Qwen
๐นHugging Face provides the embedding models used for dense and sparse retrieval
๐นFastAPI wraps the whole backend into an API interface
๐น๐ ๐ฒ๐๐ผ๐ฝ by Google is used to serve the application frontend
RAGcoon๐ฆ can be spinned up locally - it's ๐๐ผ๐ฐ๐ธ๐ฒ๐ฟ-๐ฟ๐ฒ๐ฎ๐ฑ๐๐, and you can find the whole code to reproduce it on GitHub ๐ https://github.com/AstraBert/ragcoon
But there might be room for an online version of RAGcoon๐ฆ: let me know if you would use it - we can connect and build it together!๐
posted
an
update
7 days ago
I just released a fully automated evaluation framework for your RAG applications!๐
GitHub ๐ https://github.com/AstraBert/diRAGnosis
PyPi ๐ https://pypi.org/project/diragnosis/
It's called ๐๐ข๐๐๐๐ง๐จ๐ฌ๐ข๐ฌ and is a lightweight framework that helps you ๐ฑ๐ถ๐ฎ๐ด๐ป๐ผ๐๐ฒ ๐๐ต๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ผ๐ณ ๐๐๐ ๐ ๐ฎ๐ป๐ฑ ๐ฟ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ถ๐ป ๐ฅ๐๐ ๐ฎ๐ฝ๐ฝ๐น๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป๐.
You can launch it as an application locally (it's Docker-ready!๐) or, if you want more flexibility, you can integrate it in your code as a python package๐ฆ
The workflow is simple:
๐ง You choose your favorite LLM provider and model (supported, for now, are Mistral AI, Groq, Anthropic, OpenAI and Cohere)
๐ง You pick the embedding models provider and the embedding model you prefer (supported, for now, are Mistral AI, Hugging Face, Cohere and OpenAI)
๐ You prepare and provide your documents
โ๏ธ Documents are ingested into a Qdrant vector database and transformed into a synthetic question dataset with the help of LlamaIndex
๐ The LLM is evaluated for the faithfulness and relevancy of its retrieval-augmented answer to the questions
๐ 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 ๐ถ๐ป๐๐๐ถ๐๐ถ๐๐ฒ ๐ฎ๐ป๐ฑ ๐ฐ๐ผ๐บ๐ฝ๐น๐ฒ๐๐ฒ๐น๐ ๐ฎ๐๐๐ผ๐บ๐ฎ๐๐ฒ๐ฑ: you plug it in, and it works!๐โก
Even cooler? This is all built on top of LlamaIndex and its integrations: no need for tons of dependencies or fancy workarounds๐ฆ
And if you're a UI lover, Gradio and FastAPI are there to provide you a seamless backend-to-frontend experience๐ถ๏ธ
So now it's your turn: you can either get diRAGnosis from GitHub ๐ 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 environment๐โโ๏ธ
Have fun and feel free to leave feedback and feature/integrations requests on GitHub issuesโจ
View all activity
Organizations
as-cle-bert 's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
published
an
article
about 1 month ago
view article
Building an AI-powered search engine from scratch
view article
_Repetita iuvant_: how to improve AI code generation