wandb / weave
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
☆748Updated this week
Alternatives and similar repositories for weave:
Users that are interested in weave are comparing it to the libraries listed below
- LLM Analytics☆626Updated last month
- LLM abstractions that aren't obstructions☆803Updated this week
- data cleaning and curation for unstructured text☆327Updated 4 months ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆869Updated 8 months ago
- Prompt engineering for developers☆675Updated 10 months ago
- Data-Driven Evaluation for LLM-Powered Applications☆454Updated 3 months ago
- The simplest way to serve AI/ML models in production☆931Updated this week
- Domain Adapted Language Modeling Toolkit - E2E RAG☆313Updated last month
- Creative interactive views of any dataset.☆830Updated 9 months ago
- VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of y…☆677Updated 7 months ago
- Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)☆390Updated last year
- Neural Search☆346Updated 6 months ago
- Reliable LLM Memory for AI Applications and AI Agents☆969Updated this week
- A tiny library for coding with large language models.☆1,221Updated 5 months ago
- Promptimize is a prompt engineering evaluation and testing toolkit.☆441Updated 2 months ago
- Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastr…☆1,366Updated this week
- wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk☆279Updated 3 weeks ago
- LLM fine-tuning and eval☆342Updated 8 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆1,755Updated this week
- Inspect: A framework for large language model evaluations☆666Updated this week
- Exact structure out of any language model completion.☆504Updated last year
- LLMFlows - Simple, Explicit and Transparent LLM Apps☆672Updated 8 months ago
- A tool for evaluating LLMs☆394Updated 7 months ago
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,609Updated 2 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆877Updated this week
- SUQL: Conversational Search over Structured and Unstructured Data with LLMs☆220Updated this week
- Manipulating Python Programs☆615Updated this week
- The Fastest State-of-the-Art Static Embeddings in the World☆508Updated 2 weeks ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,102Updated last week