skillfed

cohere-melody

Templating rendering and generation parsing for Cohere models

cohere-melody v0.13.3 243.7K downloads/30d#8,780 on PyPI1
Permissive license MIT Active released

What it is and what it does

Cohere Melody is a Rust library with Python bindings that parses and renders templates for Cohere language models. It handles two main tasks: parsing model outputs to extract citations and structured content (including vision generation markdown with embedded visual elements), and rendering conversation templates into formatted prompts. The library is designed to work with Cohere's Command and other models, supporting streaming text with incremental parsing and batch vision parsing. It has no runtime dependencies beyond the compiled Rust core.

The package is intended for developers integrating Cohere models into applications where citation tracking, prompt templating, and structured output parsing are required. It exposes a Python API built on PyO3 and also provides Go bindings, making it usable across multiple languages. Installation requires no external system dependencies beyond Python itself, though the wheels are pre-compiled for specific platforms.

Use it for:

  • Extract and track citations from Cohere model outputs during streaming or batch inference.
  • Render multi-turn conversation histories into properly formatted prompts for Cohere Command models.
  • Parse vision model outputs to separate markdown text from embedded visual element metadata.
  • Build LLM applications that need structured prompt templating and citation attribution.
  • Integrate Cohere models into production systems requiring standardized output parsing.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Parses and renders templated text for Cohere language models, handling citations, vision generation markup, and prompt formatting across Python and Rust.

Yes, if you are building with Cohere models and need reliable citation parsing or prompt templating. The package is actively maintained, has no security vulnerabilities, carries a permissive MIT license, and offers pre-built wheels for common platforms. Install friction is moderate but acceptable for a compiled library. Not necessary if you are not using Cohere models or do not require structured parsing of their outputs.

Install

cohere-melody on PyPI

pip

pip install cohere-melody

uv

uv add cohere-melody

poetry

poetry add cohere-melody

Installing cohere-melody

Before you install

Medium install friction due to compiled Rust bindings; wheels are pre-built for common platforms (Python 3.10–3.11, Linux, macOS, Windows). Active maintenance with recent release.

License in practice

MIT license permits unrestricted use, modification, and distribution with minimal attribution requirements.

Quickstart

pip install cohere-melody

import cohere_melody

# Parse vision generation
parsed = cohere_melody.parse_vision_generation(model_output)
for segment in parsed.segments:
    if hasattr(segment, 'text'):
        print(segment.text)

Requires Python 3.10 or later. Pre-built wheels available for Linux (x86_64, aarch64, armv7l, ppc64le, s390x, i686), macOS (x86_64, arm64), Windows (x86_64), and musl-based systems; other platforms may require building from source.

Verify before relying

  • Whether the package works with Python versions beyond 3.10–3.11 despite the requires_python constraint.
  • Performance characteristics when parsing large or streaming generations.
  • Stability and API surface of the Python bindings relative to the Rust core.

Package facts

License MIT (permissive)
Python support supports the current Python release (>=3.10)
Install friction medium — platform-specific wheel
Runtime dependencies none
Maintenance actively maintained — 0 days since the last release
Last repo commit
First released
Downloads 243,717/month — #8,780 on PyPI (30-day window, as of 2026-08-14)
Known vulnerabilities none known (OSV.dev, checked 2026-08-14)

Evidence: cohere_melody-0.13.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; cohere_melody-0.13.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl; cohere_melody-0.13.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl; cohere_melody-0.13.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl; cohere_melody-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; cohere_melody-0.13.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl; cohere_melody-0.13.3-cp310-cp310-musllinux_1_2_aarch64.whl; cohere_melody-0.13.3-cp310-cp310-musllinux_1_2_armv7l.whl; cohere_melody-0.13.3-cp310-cp310-musllinux_1_2_i686.whl; cohere_melody-0.13.3-cp310-cp310-musllinux_1_2_x86_64.whl; cohere_melody-0.13.3-cp310-cp310-win_amd64.whl; cohere_melody-0.13.3-cp311-cp311-macosx_10_12_x86_64.whl; cohere_melody-0.13.3-cp311-cp311-macosx_11_0_arm64.whl; cohere_melody-0.13.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; cohere_melody-0.13.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl; cohere_melody-0.13.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl; cohere_melody-0.13.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl; cohere_melody-0.13.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; cohere_melody-0.13.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl; cohere_melody-0.13.3-cp311-cp311-musllinux_1_2_aarch64.whl

Keywords: cohere, llm, templating, parsing

Development Status :: 5 - Production/StableIntended Audience :: DevelopersProgramming Language :: Python :: Implementation :: CPythonProgramming Language :: Python :: Implementation :: PyPyProgramming Language :: RustTopic :: Software Development :: Libraries

Tags

cohere model templatingllm prompt renderingcitation parsingvision generation parsingcohere melody librarytemplate generation for llmsmarkdown citation extraction
cohere-integrationllm-toolingrust-bindings

More Libraries packages