AI Blueprint

https://github.com/huggingface/ai-blueprint

AI & ML interests

A blueprint for AI development, focusing on applied examples of RAG, information extraction, analysis and fine-tuning in the age of LLMs.

Recent Activity

davidberenstein1957 updated a Space 6 days ago

ai-blueprint/rag-generate

davidberenstein1957 updated a Space 12 days ago

ai-blueprint/README

davidberenstein1957 updated a Space 12 days ago

ai-blueprint/rag-augment

View all activity

ai-blueprint's activity

davidberenstein1957

posted an update about 11 hours ago

Post

463

Creating an agentic RAG stack on the Hugging Face Hub - part 1 - retrieval (1/5).

🚀 Web apps and microservices included!

Chunk, embed and index documents at a huge scale without overhead.

Blog: https://huggingface.co./blog/davidberenstein1957/ai-blueprint-agentic-rag-part-1-retrieve

davidberenstein1957

updated a Space 6 days ago

RAG - generate

⚡

Generate a response to a query using a language model

davidberenstein1957

posted an update 6 days ago

Post

1518

tldr; Parquet is awesome, DuckDB too!

Datasets on the Hugging Face Hub rely on parquet files. We can interact with these files using DuckDB as a fast in-memory database system. One of DuckDB’s features is vector similarity search which can be used with or without an index.

blog:
https://huggingface.co./learn/cookbook/vector_search_with_hub_as_backend

davidberenstein1957

posted an update 9 days ago

Post

1735

Let's uncover the post-training dataset from DeepSeek-R1 with Magpie!

Pass pre-query tokens <｜begin▁of▁sentence｜>User: , let the model generate the rest.

We can get realistic examples!

Gist: https://gist.github.com/davidberenstein1957/3f20046ce57395a6aba13f8b4e956b59

6 replies

davidberenstein1957

updated 2 Spaces 12 days ago

README

📉

RAG - augment

📚

Rerank documents based on a query

davidberenstein1957

updated a Space 13 days ago

RAG - retrieve

🐠

Retrieve news articles based on a query

davidberenstein1957

updated a collection 14 days ago

Retrieval Augemented Generation (RAG)

Collection

A blueprint for RAG on the Hugging Face Hub. https://github.com/huggingface/ai-blueprint • 6 items • Updated 12 days ago

davidberenstein1957

updated a dataset 14 days ago

ai-blueprint/fineweb-bbc-news-embeddings

Viewer • Updated 14 days ago • 353k • 63

davidberenstein1957

published a dataset 14 days ago

ai-blueprint/fineweb-bbc-news-embeddings

Viewer • Updated 14 days ago • 353k • 63

davidberenstein1957

updated a collection 14 days ago

Retrieval Augemented Generation (RAG)

Collection

A blueprint for RAG on the Hugging Face Hub. https://github.com/huggingface/ai-blueprint • 6 items • Updated 12 days ago

davidberenstein1957

published a Space 14 days ago

README

📉

davidberenstein1957

posted an update 15 days ago

Post

1859

The RAG's in the bag!

You can now use the Synthetic Data Generator with your own domain-specific seed data to generate a dataset for fine-tuning retrieval or reranking models.

GitHub: https://buff.ly/49IDSmd
Spaces: https://buff.ly/3Y1S99z
Blog: https://huggingface.co./blog/sdiazlor/fine-tune-modernbert-for-rag-with-synthetic-data

1 reply

davidberenstein1957

posted an update 19 days ago

Post

1237

You can now use the "Synthetic Data Generator" at a much larger scale with your preferred inference engine: Ollama, vLLM, TGI, and serverless inference! 🔥

Install, configure, launch!

Space: argilla/synthetic-data-generator
Examples: https://github.com/argilla-io/synthetic-data-generator/tree/main/examples