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

davidberenstein1957Β  updated a Space about 1 month ago
ai-blueprint/rag-generate
davidberenstein1957Β  updated a Space about 2 months ago
ai-blueprint/README
davidberenstein1957Β  updated a Space about 2 months ago
ai-blueprint/rag-augment
View all activity

ai-blueprint's activity

davidberenstein1957Β 
posted an update 7 days ago
davidberenstein1957Β 
posted an update 9 days ago
view post
Post
4163
πŸ₯Š Epic Agent Framework Showdown! Available today!

πŸ”΅ In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!

πŸ›‘ In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!

πŸ”— URL: https://huggingface.co/agents-course

We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at

- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows

The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.

Who won? You decide!
davidberenstein1957Β 
posted an update 9 days ago
view post
Post
2977
🫸 New release to push vector search to the Hub with vicinity and work with any serialisable objects.

πŸ§‘β€πŸ« KNN, HNSW, USEARCH, ANNOY, PYNNDESCENT, FAISS, and VOYAGER.

πŸ”— Example Repo: minishlab/my-vicinity-repo
davidberenstein1957Β 
posted an update 29 days ago
view post
Post
3287
πŸš€ Find banger tools for your smolagents!

I created the Tools gallery, which makes tools specifically developed by/for smolagents searchable and visible. This will help with:
- inspiration
- best practices
- finding cool tools

Space: davidberenstein1957/smolagents-and-tools
  • 1 reply
Β·
davidberenstein1957Β 
posted an update about 1 month ago
davidberenstein1957Β 
posted an update about 1 month ago
davidberenstein1957Β 
posted an update about 1 month ago
davidberenstein1957Β 
posted an update about 1 month ago
davidberenstein1957Β 
posted an update about 1 month ago
view post
Post
1631
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
davidberenstein1957Β 
posted an update about 2 months ago