Metadata-Version: 2.1
Name: ldsi
Version: 1.0.3
Summary: LDSI
Home-page: https://github.com/laiss-labs/laiss-dsi
Author: Júlio Papel
Author-email: info@juliopapel.com
License: MIT License
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: anyio
Requires-Dist: asyncer==0.0.8
Requires-Dist: backoff
Requires-Dist: cachetools
Requires-Dist: cloudpickle
Requires-Dist: datasets
Requires-Dist: diskcache
Requires-Dist: httpx
Requires-Dist: jinja2
Requires-Dist: joblib~=1.3
Requires-Dist: json-repair
Requires-Dist: litellm[proxy]==1.55.3
Requires-Dist: magicattr~=0.1.6
Requires-Dist: openai
Requires-Dist: optuna
Requires-Dist: pandas
Requires-Dist: pydantic~=2.0
Requires-Dist: regex
Requires-Dist: requests
Requires-Dist: tenacity>=8.2.3
Requires-Dist: tqdm
Requires-Dist: ujson
Provides-Extra: chromadb
Requires-Dist: chromadb~=0.4.14; extra == "chromadb"
Provides-Extra: lancedb
Requires-Dist: lancedb~=0.11.0; extra == "lancedb"
Provides-Extra: qdrant
Requires-Dist: qdrant-client; extra == "qdrant"
Requires-Dist: fastembed; extra == "qdrant"
Provides-Extra: marqo
Requires-Dist: marqo~=3.1.0; extra == "marqo"
Provides-Extra: mongodb
Requires-Dist: pymongo~=3.12.0; extra == "mongodb"
Provides-Extra: pinecone
Requires-Dist: pinecone-client~=2.2.4; extra == "pinecone"
Provides-Extra: weaviate
Requires-Dist: weaviate-client~=4.6.5; extra == "weaviate"
Provides-Extra: faiss-cpu
Requires-Dist: sentence_transformers; extra == "faiss-cpu"
Requires-Dist: faiss-cpu; extra == "faiss-cpu"
Provides-Extra: milvus
Requires-Dist: pymilvus~=2.3.7; extra == "milvus"
Provides-Extra: google-vertex-ai
Requires-Dist: google-cloud-aiplatform==1.43.0; extra == "google-vertex-ai"
Provides-Extra: myscale
Requires-Dist: clickhouse-connect; extra == "myscale"
Provides-Extra: snowflake
Requires-Dist: snowflake-snowpark-python; extra == "snowflake"
Provides-Extra: fastembed
Requires-Dist: fastembed; extra == "fastembed"
Provides-Extra: groq
Requires-Dist: groq~=0.8.0; extra == "groq"
Provides-Extra: langfuse
Requires-Dist: langfuse~=2.36.1; extra == "langfuse"
Provides-Extra: pgvector
Requires-Dist: psycopg2~=2.9.9; extra == "pgvector"
Requires-Dist: pgvector~=0.2.5; extra == "pgvector"
Provides-Extra: falkordb
Requires-Dist: falkordb; extra == "falkordb"
Requires-Dist: redis; extra == "falkordb"
Requires-Dist: async-timeout; extra == "falkordb"

<p align="center">
  <img align="center" src="https://avatars.githubusercontent.com/u/190006171?s=200&v=4" width="160px" />
</p>
<p align="left">


----

LDSI (Laiss Declarative Self Improve) is a powerful framework for programming and optimizing language models. It empowers developers to rapidly build, iterate, and enhance modular AI systems with the following key features:

1. **Systematic Optimization**: LDSI offers a range of optimizers to refine your AI programs, from generating improved instructions to fine-tuning model weights.

2. **Modular Architecture**: Build complex AI systems using pre-defined, interchangeable modules, simplifying the development process and reducing reliance on intricate prompting techniques.

3. **Cross-LM Compatibility**: Seamlessly integrate and enhance performance across various language models, from state-of-the-art GPT models to local options like T5-base or Llama2.

4. **Declarative Approach**: Define your AI system's behavior and goals declaratively, allowing LDSI to handle the underlying optimization and execution details.

5. **Rapid Prototyping**: Accelerate your development cycle with LDSI's intuitive API and built-in tools for testing and evaluation.

LDSI is designed to streamline the process of creating sophisticated AI applications, making it an invaluable tool for both researchers and practitioners in the field of natural language processing and AI development.


## Installation


```bash
pip install ldsi
```

To install the very latest from `main`:

```bash
pip install git+https://github.com/laiss-labs/laiss-dsi.git
````
