Metadata-Version: 2.4
Name: fenic
Version: 0.6.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Operating System :: OS Independent
Requires-Dist: boto3>=1.38.28
Requires-Dist: botocore>=1.38.28
Requires-Dist: duckdb>=1.1.3
Requires-Dist: numpy>=2.0.0
Requires-Dist: polars>=1.20.0,<=1.30.0
Requires-Dist: tiktoken>=0.11.0
Requires-Dist: lancedb>=0.22.0,<0.25.0
Requires-Dist: openai>=1.101.0
Requires-Dist: sqlglot>=26.25.3,<28.0.0
Requires-Dist: pandas>=2.2.2
Requires-Dist: cloudpickle>=3.1.1
Requires-Dist: jinja2>=3.1.6
Requires-Dist: scikit-learn>=1.7.1
Requires-Dist: protobuf>=5.29.5
Requires-Dist: types-protobuf>=5.29.1.20250403
Requires-Dist: zstandard>=0.23.0
Requires-Dist: json-schema-to-pydantic>=0.4.1
Requires-Dist: pymupdf>=1.26.4
Requires-Dist: anthropic>=0.52.2 ; extra == 'anthropic'
Requires-Dist: google-genai[local-tokenizer]>=1.51.0 ; extra == 'google'
Requires-Dist: cohere>=5.16.1 ; extra == 'cohere'
Requires-Dist: pyarrow>=19.0.0,<20.0.0 ; extra == 'cloud'
Requires-Dist: grpcio>=1.60.0 ; extra == 'cloud'
Requires-Dist: pydantic-settings ; extra == 'cloud'
Requires-Dist: fenic-cloud>=0.1.3 ; extra == 'cloud'
Requires-Dist: fastmcp>=2.11.3 ; extra == 'mcp'
Requires-Dist: markdown-it-py>=4.0.0 ; extra == 'eval'
Provides-Extra: anthropic
Provides-Extra: google
Provides-Extra: cohere
Provides-Extra: cloud
Provides-Extra: mcp
Provides-Extra: eval
License-File: LICENSE
Summary: fenic is a Python DataFrame library for processing text data with APIs inspired by PySpark.
It includes text-specific utilities and special operators called semantic operators,
which use LLMs to batch transform data.

Author-email: typedef <hello@typedef.ai>
License-Expression: Apache-2.0
Requires-Python: >=3.10, <3.13
Description-Content-Type: text/x-rst
Project-URL: Homepage, https://github.com/typedef-ai/fenic
Project-URL: Issues, https://github.com/typedef-ai/fenic/issues

fenic: The dataframe (re)built for LLM inference
################################################

fenic is an opinionated, PySpark-inspired DataFrame framework for building AI and agentic applications. Transform unstructured and structured data into insights using familiar DataFrame operations enhanced with semantic intelligence. With first-class support for markdown, transcripts, and semantic operators, plus efficient batch inference across any model provider.

See `github.com/typedef-ai/fenic <https://www.github.com/typedef-ai/fenic>`_ for more information

