#87 · Primary category： LLM Application Frameworks
scikit-llm
Seamlessly integrate LLMs into scikit-learn.
Project last updated：08/01/26
GitHub Stars
3.5K
Forks
287
Contributors
14
License
MIT
Why we included this project
Teams that already build models in scikit-learn can add LLM-backed classifiers and embeddings without reworking their pipeline, because the library hides provider calls behind the same fit/predict interface they already know. Zero-shot text classification, few-shot labeling, and text vectorization then behave like ordinary estimators, whether the model behind them is GPT or something hosted locally. That is a real convenience for data people who are comfortable with sklearn conventions but do not want to hand-write API calls to a language model. The training loop and evaluation code stay as they are, so adopting LLMs feels like a small step rather than a separate stack.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform