somewheresystems / dataclysm
Pull high-quality, efficient embeddings for PubMed, arXiv and Wikipedia from Huggingface and use for local LLM inference/Retrieval Augmented Generation (RAG)
β42Updated last year
Alternatives and similar repositories for dataclysm:
Users that are interested in dataclysm are comparing it to the libraries listed below
- π The open-source autonomous agent LLM initiative πβ91Updated last year
- they've simulated websites, worlds, and imaginary CLIs... but what if they simulated *you*?β116Updated 2 weeks ago
- Fluid Databaseβ114Updated 6 months ago
- auto fine tune of models with synthetic dataβ74Updated last year
- β50Updated last year
- A strongly typed Python DSL for developing message passing multi agent systemsβ52Updated 11 months ago
- β29Updated 4 months ago
- An Apache 2.0 licensed starter kit for making Discord bots which converse via direct address (@) and LLMs.β32Updated last year
- A dictionary, but it shows you position in embedding space relative to some synonyms/antonyms instead of a definition.β73Updated last month
- β81Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)β63Updated 4 months ago
- Annoucing Instructor Cloudβ34Updated 7 months ago
- β136Updated last year
- β111Updated 3 months ago
- A Python library to orchestrate LLMs in a neural network-inspired structureβ46Updated 5 months ago
- β37Updated last year
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.β30Updated last year
- LUI: Autonomous Collective Decision Making via Large Language Modelsβ104Updated last year
- A replication of Andy Ayrey's "Backrooms" (https://dreams-of-an-electric-mind.webflow.io/), but runnable with Opus 3, Sonnet 3.5, GPT 4o,β¦β101Updated 4 months ago
- Demo of AI chatbot that predicts user message to generate response quickly.β101Updated last year
- A simple wrapper for OpenAI to log input/outputs.β105Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.β31Updated 3 weeks ago
- A seamless matchmaking application that is programmed with Cohere Command R+, Stanford NLP DSPy framework, Weaviate Vector store and Crewβ¦β59Updated 11 months ago
- CLAIRe: Conversational Learning AI with Recallβ67Updated last year
- β4Updated 7 months ago
- A framework for orchestrating AI agents using a mermaid graphβ75Updated 10 months ago
- A library that allows interacting with Replit's code-exec APIβ23Updated 2 months ago
- A memory manager essential for evolving AI to be more human-like, enabling dynamic, context-aware responses through structured memory hanβ¦β28Updated 11 months ago
- Recursive self-improvementβ55Updated last year
- MCP Server to run python code locallyβ42Updated 3 months ago