Trending

On-device small language models with multimodality, RAG, and Function Calling

Show HN: Morphik – Open-source RAG that understands PDF images, runs locally

Transforming Your PDFs for RAG with Open Source Using Docling, Milvus, and Feast

Translate Fortran to C++ with AI and RAG

Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB

Mayo Clinic's secret weapon against AI hallucinations: Reverse RAG in action

Show HN: In-Browser Graph RAG with Kuzu-WASM and WebLLM

What's the most niche use case you've seen an agent solve?

Has anyone used google search for RAG in a script?

[R] Best way to combine multiple embeddings without just concatenating?

Is there a clean way to use multiple LLMs in one agent-like setup?

Building A RAG-Based Knowledge Assistant With Python • Scientyfic World

[D] Lessons learned while experimenting with scalable retrieval pipelines for large language models

How RAG actually works — a toy example with real math

What I’ve learned building RAG applications for enterprises

Reuse non-prefix KV Cache and speed up RAG by 3X with LMCache.

Jina AI

Save item

jina-embeddings-v4

Task: visual-document-retrieval

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

pathwaycom

Save item

pathway

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

langchain-ai

Save item

langchain

🦜🔗 Build context-aware reasoning applications