Search Results for "llms and python-pptx"

bitnet.cpp is the official open-source inference framework and ecosystem designed to enable ultra-efficient execution of 1-bit large language models (LLMs), which quantize most model parameters to ternary values (-1, 0, +1) while maintaining competitive performance with full-precision counterparts. At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous...

When I first found FastAPI, I got it immediately. I was excited to find something so innovative and ergonomic built on Pydantic. Virtually every Agent Framework and LLM library in Python uses Pydantic, but when we began to use LLMs in Pydantic Logfire, I couldn't find anything that gave me the same feeling. PydanticAI is a Python Agent Framework designed to make it less painful to build production-grade applications with Generative AI. Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor, and many more).

Backtrack Sampler is a framework designed for experimenting with custom sampling strategies for language models (LLMs), enabling the ability to rewind and revise generated tokens. It allows developers to create and test their own token generation strategies by providing a base structure for manipulating logits and probabilities, making it a flexible tool for those interested in fine-tuning the behavior of LLMs.

Raglite is a lightweight framework for building Retrieval-Augmented Generation (RAG) pipelines with minimal configuration. It connects large language models to vector databases for context-aware responses, enabling developers to prototype and deploy RAG systems quickly. Raglite focuses on simplicity and modularity for fast experimentation.

The bu-agent-sdk from the Browser Use project is a minimalistic Python framework that defines an AI agent as a simple loop of tool calls, aiming to keep abstractions low so developers can build autonomous agents without unnecessary complexity. At its core, the agent loop repeatedly queries a large language model, interprets its output, and executes defined “tools” — functions annotated with task names — to perform actions, allowing the agent to complete tasks like arithmetic,...

Superduper is a Python-based framework for building end-2-end AI-data workflows and applications on your own data, integrating with major databases. It supports the latest technologies and techniques, including LLMs, vector-search, RAG, and multimodality as well as classical AI and ML paradigms. Developers may leverage Superduper by building compositional and declarative objects that out-source the details of deployment, orchestration versioning, and more to the Superduper engine. ...

EasyR1 is a streamlined training framework for building “R1-style” reasoning models from open-source LLMs with minimal boilerplate. It focuses on the full reasoning stack—data preparation, supervised fine-tuning, preference or outcome-based optimization, and lightweight evaluation—so you can iterate quickly on chain-of-thought–heavy tasks. The project’s philosophy is practicality: sensible defaults, one-command recipes, and compatibility with popular base models let you stand up experiments...