amaiya / onprem
A toolkit for applying on-premises large language models to non-public data
☆716Updated last week
Alternatives and similar repositories for onprem:
Users that are interested in onprem are comparing it to the libraries listed below
- Structured and typehinted GPT responses in Python☆738Updated 9 months ago
- A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for vario…☆1,014Updated 2 months ago
- A fast and minimal framework for building agentic systems☆428Updated 9 months ago
- Large language model evaluation and workflow framework from Phase AI.☆458Updated 3 months ago
- Agents Capable of Self-Editing Their Prompts / Python Code☆764Updated last year
- fast vector database made in numpy☆751Updated last year
- This project provides an API with user level access support to transcribe speech to text using a finetuned and processed Whisper ASR mode…☆887Updated last year
- Prompt engineering for developers☆686Updated last year
- Marsha is a functional, higher-level, English-based programming language that gets compiled into tested Python software by an LLM☆470Updated last year
- A tiny nearest-neighbor embedding database built with SQLite and Pytorch. (In development!)☆772Updated last year
- Build browser agents for real world tasks☆1,004Updated last year
- RAG based tool for indexing and searching PDF text data using OpenAI API and FAISS (Facebook AI Similarity Search) index, designed for ra…☆675Updated 3 months ago
- AI-managed code blocks in Python ⏪⏩☆468Updated last year
- Build agents which are controlled by LLMs☆981Updated 4 months ago
- LLMFlows - Simple, Explicit and Transparent LLM Apps☆693Updated 2 months ago
- Build robust LLM applications with true composability 🔗☆418Updated last year
- Instruct-tune LLaMA on consumer hardware☆362Updated 2 years ago
- Complex LLM Workflows from Simple JSON.☆297Updated last year
- A script to effortlessly extract your entire ChatGPT data export from JSON files to nicely-formatted markdown files.☆751Updated 9 months ago
- A school for camelids☆1,209Updated 2 years ago
- An LLM-powered advanced RAG pipeline built from scratch☆836Updated last year
- Finetune llama2-70b and codellama on MacBook Air without quantization☆448Updated last year
- ☆82Updated 2 years ago
- A series of top performing Text to SQL LLMs☆871Updated last year
- AI-agents that automatically generate and use Langchain Tools and ChatGPT plugins☆535Updated 2 years ago
- Full stack voice chatbot☆197Updated 7 months ago
- Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.☆854Updated last year
- A reactive runtime for building durable AI agents☆1,313Updated 4 months ago
- Enforce structured output from LLMs 100% of the time☆249Updated 9 months ago
- Classify and extract structured data with LLMs☆425Updated last year