https://github.com/lotus-data/lotus
Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code
https://github.com/lotus-data/lotus
ai-data-processing data llm llm-data-processing llm-document-processing pandas python semantic-operators semantic-search unstructured-data
Last synced: 3 months ago
JSON representation
Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code
- Host: GitHub
- URL: https://github.com/lotus-data/lotus
- Owner: lotus-data
- License: apache-2.0
- Created: 2024-07-16T16:39:06.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-10-07T00:10:57.000Z (4 months ago)
- Last Synced: 2025-10-07T01:19:10.089Z (4 months ago)
- Topics: ai-data-processing, data, llm, llm-data-processing, llm-document-processing, pandas, python, semantic-operators, semantic-search, unstructured-data
- Language: Python
- Homepage: https://lotus-data.github.io
- Size: 1.85 MB
- Stars: 1,310
- Watchers: 15
- Forks: 112
- Open Issues: 44
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
- awesome - lotus-data/lotus - AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code (Python)
- awesome-github-repos - lotus-data/lotus - AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code (Python)
README
# LOTUS: LLM-Powered Data Processing Made Fast, Easy, and Robust
[](https://colab.research.google.com/drive/1mP65YHHdD6mnZmC5-Uqm2uCXJ4-Kbkhu?usp=sharing)
[][#arxiv-paper-package]
[][#slack]
[](https://lotus-ai.readthedocs.io/en/latest/?badge=latest)
[][#pypi-package]
[][#pypi-package]
[#license-gh-package]: https://lbesson.mit-license.org/
[#arxiv-paper-package]: https://arxiv.org/abs/2407.11418
[#pypi-package]: https://pypi.org/project/lotus-ai/
[#slack]: https://join.slack.com/t/lotus-fnm8919/shared_invite/zt-319k232lx-nEcLF~5w274dcQLmw2Wqyg
LOTUS is the framework that allows you to easily process your datasets, including unstructured and structured data, with LLMs. It provides an **intuitive Pandas-like API**, offers algorithms for **optimizing your programs for up to 1000x speedups**, and makes LLM-based data processing **robust with accuracy guarantees** with respect to high-quality reference algorithms.
LOTUS stands for **L**LMs **O**ver **T**ext, **U**nstructured and **S**tructured Data, and it implements [**semantic operators**](https://arxiv.org/abs/2407.11418), which extend the core philosophy of relational operators—designed for declarative and robust _structured-data_ processing—to _unstructured-data_ processing with AI. Semantic operators are expressive, allowing you to easily capture all of your data-intensive AI programs, from simple RAG, to document extraction, image classification, LLM-judge evals, unstructured data analysis, and more.
For trouble-shooting or feature requests, please raise an issue and we'll get to it promptly. To share feedback and applications you're working on, you can send us a message on our [community slack](https://join.slack.com/t/lotus-fnm8919/shared_invite/zt-319k232lx-nEcLF~5w274dcQLmw2Wqyg), or send an email (lianapat@stanford.edu).
# Installation
For the latest stable release:
```
conda create -n lotus python=3.10 -y
conda activate lotus
pip install lotus-ai
```
For the latest features, you can alternatively install as follows:
```
conda create -n lotus python=3.10 -y
conda activate lotus
pip install git+https://github.com/lotus-data/lotus.git@main
```
## Running on Mac
If you are running on mac, please install Faiss via conda:
### CPU-only version
```
conda install -c pytorch faiss-cpu=1.8.0
```
### GPU(+CPU) version
```
conda install -c pytorch -c nvidia faiss-gpu=1.8.0
```
For more details, see [Installing FAISS via Conda](https://github.com/facebookresearch/faiss/blob/main/INSTALL.md#installing-faiss-via-conda).
# Quickstart
If you're already familiar with Pandas, getting started will be a breeze! Below we provide a simple example program using the semantic join operator. The join, like many semantic operators, are specified by **langex** (natural language expressions), which the programmer uses to specify the operation. Each langex is parameterized by one or more table columns, denoted in brackets. The join's langex serves as a predicate and is parameterized by a right and left join key.
```python
import pandas as pd
import lotus
from lotus.models import LM
# configure the LM, and remember to export your API key
lm = LM(model="gpt-4.1-nano")
lotus.settings.configure(lm=lm)
# create dataframes with course names and skills
courses_data = {
"Course Name": [
"History of the Atlantic World",
"Riemannian Geometry",
"Operating Systems",
"Food Science",
"Compilers",
"Intro to computer science",
]
}
skills_data = {"Skill": ["Math", "Computer Science"]}
courses_df = pd.DataFrame(courses_data)
skills_df = pd.DataFrame(skills_data)
# lotus sem join
res = courses_df.sem_join(skills_df, "Taking {Course Name} will help me learn {Skill}")
print(res)
# Print total LM usage
lm.print_total_usage()
```
### Tutorials
Below are some short tutorials in Google Colab, to help you get started. We recommend starting with `[1] Introduction to Semantic Operators and LOTUS`, which will provide a broad overview of useful functionality to help you get started.
| Tutorial | Difficulty | Colab Link |
|----------------------------------------------------|-----------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 1. Introduction to Semantic Operators and LOTUS |  | [](https://colab.research.google.com/drive/1mP65YHHdD6mnZmC5-Uqm2uCXJ4-Kbkhu?usp=sharing) |
| 2. Failure Analysis Over Agent Traces |  | [](https://colab.research.google.com/drive/1EJm9A8r_ShYxR0s218J70XhsopOgeT6k?usp=sharing) |
| 3. System Prompt Analysis with LOTUS |  | [](https://colab.research.google.com/drive/1NSVQYOMp2GCre5ZRgvgs6BPGOa20ySMc?usp=sharing) |
| 4. Processing Multimodal Datasets |  | [](https://colab.research.google.com/drive/18oaa12T6PrhHIYGw-L01gw1bDmTYaE_e) |
## Key Concept: The Semantic Operator Model
LOTUS introduces the semantic operator programming model. Semantic operators are declarative transformations over one or more datasets, parameterized by a natural language expression, that can be implemented by a variety of AI-based algorithms. Semantic operators seamlessly extend the relational model, operating over tables that may contain traditional structured data as well as unstructured fields, such as free-form text. These modular language-based operators allow you to write AI-based pipelines with high-level logic, leaving optimizations to the query engine. Each operator can be implemented and optimized in multiple ways, opening a rich space for execution plans, similar to relational operators. To learn more about the semantic operator model, read the full [research paper](https://arxiv.org/abs/2407.11418).
LOTUS offers a number of semantic operators in a Pandas-like API, some of which are described below. To learn more about semantic operators provided in LOTUS, check out the full [documentation](https://lotus-ai.readthedocs.io/en/latest/), run the [colab tutorial](https://colab.research.google.com/drive/1mP65YHHdD6mnZmC5-Uqm2uCXJ4-Kbkhu?usp=sharing), or you can also refer to these [examples](https://github.com/TAG-Research/lotus/tree/main/examples/op_examples).
| Operator | Description |
|------------|-------------------------------------------------|
| sem_map | Map each record using a natural language projection|
| sem_filter | Keep records that match the natural language predicate |
| sem_extract | Extract one or more attributes from each row |
| sem_agg | Aggregate across all records (e.g. for summarization) |
| sem_topk | Order the records by some natural langauge sorting criteria |
| sem_join | Join two datasets based on a natural language predicate |
| sem_sim_join | Join two DataFrames based on semantic similarity |
| sem_search | Perform semantic search the over a text column |
# Supported Models
There are 3 main model classes in LOTUS:
- `LM`: The language model class.
- The `LM` class is built on top of the `LiteLLM` library, and supports any model that is supported by `LiteLLM`. See [this page](CONTRIBUTING.md) for examples of using models on `OpenAI`, `Ollama`, and `vLLM`. Any provider supported by `LiteLLM` should work. Check out [litellm's documentation](https://litellm.vercel.app) for more information.
- `RM`: The retrieval model class.
- Any model from `SentenceTransformers` can be used with the `SentenceTransformersRM` class, by passing the model name to the `model` parameter (see [an example here](examples/op_examples/dedup.py)). Additionally, `LiteLLMRM` can be used with any model supported by `LiteLLM` (see [an example here](examples/op_examples/sim_join.py)).
- `Reranker`: The reranker model class.
- Any `CrossEncoder` from `SentenceTransformers` can be used with the `CrossEncoderReranker` class, by passing the model name to the `model` parameter (see [an example here](examples/op_examples/search.py)).
# Feature Requests and Contributing
We welcome contributions from the community! Whether you're reporting bugs, suggesting features, or contributing code, we have comprehensive templates and guidelines to help you get started.
## Getting Started
Before contributing, please:
1. **Read our [Contributing Guide](CONTRIBUTING.md)** - Comprehensive guidelines for contributors
2. **Check existing issues** - Avoid duplicates by searching existing issues and pull requests
3. **Join our community** - Connect with us on [Slack](https://join.slack.com/t/lotus-fnm8919/shared_invite/zt-319k232lx-nEcLF~5w274dcQLmw2Wqyg)
## Development Setup
For development setup and detailed contribution guidelines, see our [Contributing Guide](CONTRIBUTING.md).
## Community
- **Slack**: [Join our community](https://join.slack.com/t/lotus-fnm8919/shared_invite/zt-319k232lx-nEcLF~5w274dcQLmw2Wqyg)
- **Email**: lianapat@stanford.edu
- **Discussions**: [GitHub Discussions](https://github.com/lotus-data/lotus/discussions)
We're excited to see what you build with LOTUS! 🚀
# References
For recent updates related to LOTUS, follow [@lianapatel_](https://x.com/lianapatel_) on X.
If you find LOTUS or semantic operators useful, we'd appreciate if you can please cite this work as follows:
```bibtex
@article{patel2025semanticoptimization,
title = {Semantic Operators and Their Optimization: Enabling LLM-Based Data Processing with Accuracy Guarantees in LOTUS},
author = {Patel, Liana and Jha, Siddharth and Pan, Melissa and Gupta, Harshit and Asawa, Parth and Guestrin, Carlos and Zaharia, Matei},
year = {2025},
journal = {Proc. VLDB Endow.},
url = {https://doi.org/10.14778/3749646.3749685},
}
@article{patel2024semanticoperators,
title={Semantic Operators: A Declarative Model for Rich, AI-based Analytics Over Text Data},
author={Liana Patel and Siddharth Jha and Parth Asawa and Melissa Pan and Carlos Guestrin and Matei Zaharia},
year={2024},
eprint={2407.11418},
url={https://arxiv.org/abs/2407.11418},
}
```