Metadata-Version: 2.1
Name: blendsql
Version: 0.0.1
Summary: Orchestrate SQLite logic and LLM reasoning within a unified dialect.
Home-page: https://github.com/parkervg/blendsql
Author: Parker Glenn
Author-email: parkervg5@gmail.com
License: Apache License 2.0
License-File: LICENSE
Requires-Dist: openai==0.28.0
Requires-Dist: guidance==0.0.64
Requires-Dist: pyparsing==3.1.1
Requires-Dist: pandas>=2.0.0
Requires-Dist: bottleneck>=1.3.6
Requires-Dist: sqlglot
Requires-Dist: pre-commit
Requires-Dist: attrs
Requires-Dist: tqdm
Requires-Dist: dateparser
Requires-Dist: colorama
Requires-Dist: fiscalyear
Requires-Dist: tabulate
Requires-Dist: typeguard
Requires-Dist: azure-identity
Requires-Dist: nbformat
Provides-Extra: research
Requires-Dist: datasets==2.16.1; extra == "research"
Requires-Dist: nltk; extra == "research"
Requires-Dist: wikiextractor; extra == "research"
Requires-Dist: rouge_score; extra == "research"
Requires-Dist: rapidfuzz; extra == "research"
Requires-Dist: records; extra == "research"
Requires-Dist: SQLAlchemy; extra == "research"
Requires-Dist: recognizers-text; extra == "research"
Requires-Dist: recognizers-text-suite; extra == "research"
Requires-Dist: emoji==1.7.0; extra == "research"
Requires-Dist: transformers; extra == "research"
Provides-Extra: test
Requires-Dist: pytest; extra == "test"

BlendSQL is a scalable SQL dialect for problem decomposition and heterogenous question-answering with LLMs. It builds off of the syntax of SQLite to create an intermediate representation for tasks requiring complex reasoning over both structured and unstructured data.
