Documentation for Baidu Qianfan, covering setup, features, and practical usage.
Directory
Search the directory
Search published websites, apps and repositories.
BambooAI is an LLM-driven data analyst tool that operates in a persistent Python kernel. It is available as a web app with Docker-isolated execution, supports user-provided model keys, and is compatible with open weights models via provider or local deployment.
Bardeen is a platform for sourcing leads with an agentic web scraper, researching leads with AI search, enriching them with validated contact info, and qualifying them with AI. It supports exporting data to CSV, Google Sheets, Airtable and Notion, and lists use cases for solopreneurs, real estate and music.
Deploy and serve machine learnings models performantly, scalably, and cost-efficiently with Baseten.
BayesO is a Python framework for Bayesian optimization, described as a simple but essential Bayesian optimization package. It is installed via pip and is tested on Python 3.8 through 3.12. The repository includes documentation, examples and tests, and is released under the MIT License.
Beam is a platform for agentic automation and AI agents aimed at enterprise operations. It offers an agent hub for managing agents, pre-trained agents, templates and integrations with existing tools, and agents adapt to an organization's standard operating procedures. The platform also lists industry solutions such as a financial services AI suite.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
BELLE, short for Be Everyone's Large Language model Engine, is an open-source Chinese conversational large language model hosted on GitHub by LianjiaTech. The project provides relevant training code and open datasets for the model.
A Towards Data Science article by Hui Wen Goh evaluating popular hallucination detectors, including G-eval, Ragas and the Trustworthy Language Model, across four public RAG datasets. Using AUROC and precision/recall, it reports how well the methods automatically flag incorrect LLM responses in retrieval-augmented generation systems.
GPT Migrate team is working on adding for the agent.
Fast Neural Networks framework built on top of Metal. Supports TensorFlow models.
Browser-based visual editor for designing neural networks and automatically generating PyTorch and TensorFlow code.
CPU and GPU-accelerated Machine Learning Library.
BigML is a machine learning platform for classification, regression, time series forecasting, cluster analysis, anomaly detection, association discovery, topic modeling and principal component analysis. Models can be used for predictions through remote services or exported and embedded into applications. A three-day free trial gives access to all functionality.
BigModel provides machine-learning models, research, training resources, or evaluation tools.
Birdland is a collaborative filtering recommendation library written in Go. It performs a random walk on a biased user-items bipartite graph to generate user-item pairs, which the recommender processes into recommended items. The project includes sampler and explorer components such as Bird, Emu and Weaver.
bitnet.cpp is the official inference framework for 1-bit LLMs such as BitNet b1.58. It provides optimized kernels for inference of 1.58-bit models on CPU and GPU, with NPU support stated as coming next. The repository includes documentation and setup scripts, and the project is released under the MIT license.
Accessible large language models via k-bit quantization for PyTorch.
Black Headshots is an AI headshot service aimed at Black skin tones and features. Users upload 8-14 photos and receive generated headshots for social profiles, resumes and portfolios, with styles and backgrounds available. Plans are offered at $19, $39 and $69, and the service states a 24-hour money-back guarantee.
Blackbox AI provides machine-learning models, research, training resources, or evaluation tools.
Blinky is an open-source AI debugging agent for VSCode that uses LLMs to help identify and fix backend code errors. It uses the VSCode API, Language Server Protocol and print statement debugging. Users describe a bug and repro steps in a chat interface, then accept or reject the agent's changes.
Python bindings for the BLLIP natural language parser.
A blog post describing a small library for building agents controlled by large language models, inspired by langchain. The agent is instructed by a prompt and runs in a loop of Thought, Action and Observation. Implemented tools include executing Python code in a REPL, Google search and Hacker News search.
BigScience Large Open-science Open-access Multilingual Language Model.