VectorInstitute / fed-ragLinks
A framework for fine-tuning retrieval-augmented generation (RAG) systems.
β137Updated last week
Alternatives and similar repositories for fed-rag
Users that are interested in fed-rag are comparing it to the libraries listed below
Sorting:
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Modelsβ115Updated 8 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" π€β76Updated last year
- β79Updated 2 months ago
- β103Updated 9 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generaβ¦β246Updated last week
- Official Implementation of "Affordable AI Assistants with Knowledge Graph of Thoughts"β201Updated this week
- Dynamic Metadata based RAG Frameworkβ78Updated 3 weeks ago
- Demo of knowledge graph creation and Graph RAG with BAML and Kuzuβ73Updated 3 months ago
- Enterprise-grade memory framework for LLMs featuring GPU-optimized inference, vector storage, and automated scaling. Enables hyper-personβ¦β89Updated 7 months ago
- Build a Recommendation System Agent using LATS Agent Approachβ33Updated 10 months ago
- frozen-in-time version of our Paper Finder agent for reproducing evaluation resultsβ214Updated 4 months ago
- Optimized Large Language Models for Financial Applications β Efficient, Scalable, and Domain-Specific AI for Finance.β50Updated 5 months ago
- Fastest way to build multi-agent system, agent-to-agent communication, MCPs, production ready serverless environment.β127Updated this week
- This repo is the central repo for all the RAG Evaluation reference material and partner workshopβ77Updated 8 months ago
- A tutorial on DSPy and whether automated prompt engineering lives up to the hypeβ24Updated last year
- A curated list of materials on AI guardrailsβ43Updated 6 months ago
- Simple UI for debugging correlations of text embeddingsβ306Updated 7 months ago
- β80Updated last year
- A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.β173Updated 3 weeks ago
- Coding an LLM and its building blocks from scratch.β104Updated 9 months ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)β89Updated 2 weeks ago
- DSPY on action with OpenSource LLMs.β102Updated last year
- Fine-tune an LLM to perform batch inference and online serving.β115Updated 7 months ago
- β148Updated last year
- Benchmark and optimize LLM inference across frameworks with easeβ151Updated 3 months ago
- Research repository on interfacing LLMs with Weaviate APIs. Inspired by the Berkeley Gorilla LLM.β140Updated 4 months ago
- Simple examples using Argilla tools to build AIβ57Updated last year
- β89Updated 7 months ago
- A method for steering llms to better follow instructionsβ68Updated 4 months ago
- Turn topics, links, and files into AI-generated research notebooks β summarize, explore, and ask anything.β144Updated 6 months ago